Grade C

Battle-tested Playwright patterns for writing and debugging reliable E2E, API, component, visual, accessibility, and security tests. Use when you need locator strategy, assertions, fixtures, network mocking, auth flows, trace debugging, or framework recipes for React, Next.js, Vue, and Angular. TypeScript and JavaScript.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Semi-automatic Git hook setup for Supabase project tracking with fallback options

Runs commands with sudo.

Provides Cursor with context to properly format Mintlify components and follow technical writing best practices

Runs commands with sudo.

ROS2 inter-node communication patterns and service integration for Argo sailboat system

Runs commands with sudo.

Comprehensive Goth Google authentication standards for Elixir with OAuth2, service accounts, token management, and security best practices following Google Cloud authentication standards

Contains what looks like a real key or token.

body, html, .player, .fallback { overflow: hidden; width: 100%; height: 100%; margin: 0; padding: 0; } .fallback {

Has a line over 4000 characters, too long to scan reliably.

Optimized rules prefix with 4-tier hierarchy

Runs commands with sudo.

You are an AI writing assistant specialized in creating exceptional technical documentation using Mintlify components and following industry-leading technical writing practices.

Runs commands with sudo.

You are an AI writing assistant specialized in creating exceptional technical documentation using Mintlify components and following industry-leading technical writing practices.

Runs commands with sudo.

Burger API is a Bun.js-exclusive framework - it only works with Bun.js and cannot run on Node.js or other JavaScript runtimes. This is a modern, high-performance API framework built specifically for Bun.js that provides file-based routing, middleware architecture, Zod-based validation, automatic OpenAPI generation, and wildcard routing capabilities.

Runs a vendor's official installer script from the internet.

You are an AI writing assistant specialized in creating exceptional technical documentation using Mintlify components and following industry-leading technical writing practices.

Runs commands with sudo.

Диагностика системы лицензирования HASP — порядок проверки компонентов по цепочке через SSH

Runs commands with sudo.

This is a MONOREPO with:

Sends a key or token over the network to a host we can't verify.

activation: always description: > Guidelines for managing environment variables, API keys, and configuration in Next.js applications with proper security and development practices.

Contains what looks like a real key or token.

SweetPotatOs project memory — read NOTES.md; theme sync, fastfetch, lid sleep

Runs commands with sudo.

Pack Attack production server SSH keys, deployment, and infrastructure. ALWAYS READ THIS BEFORE ANY SERVER OR DEPLOYMENT TASK.

Runs commands with sudo.

Notes:

Contains what looks like a real key or token.

Always remember this

Contains what looks like a real key or token.

Testing protocol and diagnostic procedures

Runs commands with sudo.

No description provided. From mgaulton/picorg.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Resource tracking for Ollama

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From KPanel2/kpanel2.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From hightekvagabond/gypsys-cli-tools.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

my mobile app that lets me talk directly to openclaw from my phone without using 3rd party tools

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From hightekvagabond/gypsys-cli-tools.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From phil-bryant/teller.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From phil-bryant/teller.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Publish apps to relays

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

This library is designed to turn DynamoDB into an Event Store for Event Sourcing.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

A Model Context Protocol (MCP) proxy server that translates tool calls into TypeScript code generation. Instead of making multiple tool calls back and forth, LLMs can write TypeScript code that calls multiple tools naturally, reducing token overhead and leveraging the LLM's superior code generation capabilities.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

A parser-monad combinator library for Rust — named after Oni-Kombu (鬼昆布)

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From starkware-libs/starknet-specs.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Operating manual for any agent (or human) working in wasm-vm. ROADMAP.md says where we're going. tasks/QUEUE.md says what's next. This file says how work gets done — and, more importantly, how work gets proven.

Runs commands with sudo.

Version 1.1.0 NestJS Best Practices January 2026

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Version 1.1.0 NestJS Best Practices January 2026

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Version 1.1.0 NestJS Best Practices January 2026

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Version 1.1.0 NestJS Best Practices January 2026

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Version 1.1.0 NestJS Best Practices January 2026

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

El esquema oracle divide el trabajo en roles fijos, cada uno con un alcance acotado y un criterio de éxito verificable. Un agente solo actúa dentro de su rol y debe reportar su resultado en el formato definido abajo. Así se evita que un agente modifique cosas fuera de su alcance o invoque sin evidencia.

Runs commands with sudo.

Tournament/championship management system with real-time web UI and Telegram bot. Handles EK (эрудит-квартет), OD/KVRM (командная викторина с раундами по минуте), and KSI (командная своя игра) formats. Russian-language domain.

Runs commands with sudo.

The contract is the whole surface of the application: who may call what. The proxy admits only the calls it allows, and the data layer scopes every row to the capability that the endpoint's access form minted. Write on the paved road below. When it does not reach far enough, declare the step off it. A declared step is allowed, and the approver sees it.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Generates SEO landing pages at scale: one template (built in the block editor, Elementor or WPBakery) plus a table of groups (rows of values) becomes one generated page per group. This is the core plugin. Its add-on ../rowsprout-pro (read its AGENTS.md too) adds planning, WPML, MCP/WP-CLI, extra field types, extra Elementor elements, Smart Generate and a live status overview on the Templates list (the free plugin has its own simple Status column, Admin\TemplateStatusColumn; Pro renders its cell…

Has a line over 4000 characters, too long to scan reliably.

Standard order for server-side mutations:

Has a line over 4000 characters, too long to scan reliably.

This detailed Industry Analysis, also known as a latest study, provides an overview of the industry in North America, Latin America, the Asia Pacific, and Europe. The research includes information on current market trends, prior accomplishments, and future possibilities. As a result, in this Chemical Blowing Agents market report, it has all the major facts and figures. This Chemical Blowing Agents market report, on the other hand, places great emphasis on big corporations. Since the world's lea…

Has a line over 4000 characters, too long to scan reliably.

Version 0.1.0 Vercel Engineering January 2026

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Linux-based CCTV surveillance system: capture, analysis, recording, and monitoring of video cameras.

Runs commands with sudo.

Guidance for AI coding agents (GitHub Copilot, Codex, Cursor, Claude Code) working in this repository. It is written to be read cold: everything an agent needs to make a correct change without prior conversation.

Runs commands with sudo.

이 프로젝트가 무엇이고 무엇을 지켜야 하는지는 .specify/memory/constitution.md에 있다. 작업을 시작하기 전에 그것을 읽는다. 이 문서는 헌법을 요약하지 않으며, 헌법이 담지 않는 실무 사실만 남긴다. 둘이 어긋나면 헌법이 우선한다.

Runs commands with sudo.

One repo for the whole system-design build guide, a scaled-down influencer-intelligence pipeline (Defrag's creator watchlist) built up in modules. Personal interview-prep learning code, internal, never client-facing.

Runs commands with sudo.

Armada runs a fleet of coding agents on one project: Linear holds the plan and progress, GitHub holds the code, and the armada CLI gives the coordinator and the workers one shared reading of the fleet.

Has a line over 4000 characters, too long to scan reliably.

{% raw %}

Has a line over 4000 characters, too long to scan reliably.

Hobbyist React PWA (Vite + TypeScript) reimagining Singapore weather data. Quality gates: npm run build (tsc typecheck with noEmit: true + vite build → dist/), npm run lint (eslint — must stay at 0 warnings), npm run test (vitest + testing-library, 68 tests across 13 suites). No formatter in the gate; npm run format exists for manual prettier runs.

Runs commands with sudo.

CLAUDE.md carries these same rules. This paragraph and the title are the only difference. Change them together.

Has a line over 4000 characters, too long to scan reliably.

NixOS system + Home Manager user configuration managed via a single flake at ~/dotfiles. Three machine targets: nixos-desktop, nixos-work, nixos (template baseline). System is x8664-linux, username drishal`.

Runs commands with sudo.

icsagccActor is a tron actor** for the Subaru Prime Focus Spectrograph (PFS) Auto Guider Camera Control (AGCC) subsystem. It controls up to 6 FLI USB CCD cameras, manages exposures, runs centroiding/photometry, and writes results to FITS files and the PFS operational database (OpDB).

Runs commands with sudo.

Monorepo with three packages that are NOT linked via workspaces — each has its own nodemodules`:

Has a line over 4000 characters, too long to scan reliably.

Guia operacional para agentes, mantenedores e contribuidores do repositório troubleshooter.

Runs commands with sudo.

This file provides contextual instructions for GitHub Copilot coding agent when working on issues and tasks in this repository.

Runs commands with sudo.

This document outlines the critical "how-to" procedures for controlling agent behavior, command deployment, and state management within the Discord Bot environment.

Runs commands with sudo.

Personal Arch Linux + Niri/Wayland configuration for data engineering and scientific computing. CLAUDE.md imports this file, so this is the single source of agent guardrails. Read README.md for the directory map, the app's file under docs/architecture/ before changing it, and docs/system-notes.md, TODO.md and revisit.md before package, system or audit work — those hold operational constraints, not background. Do not reopen accepted findings without new evidence; TODO items need the user. Read n…

Runs commands with sudo.

smolagents 是一个轻量级库, 用于构建强大的代理(agents)。它允许用户通过几行代码运行功能强大的代理,支持多种语言模型(LLM)和工具。代理可以通过编写 Python 代码来调用工具并协调其他代理,非常适合快速开发和部署智能代理系统。

Runs commands with sudo.

This file provides guidance for agentic coding assistants working on this repository.

Runs commands with sudo.

This file provides contextual instructions for GitHub Copilot coding agent when working on issues and tasks in this repository.

Runs commands with sudo.

Date: 2026-06-04 Focus: Gitea epic #1910 follow-ups -- harden the ADF pre-merge gate and enable ADF to autonomously maintain the polyrepos via repo-local agent config. Orchestrator: bigbox adf-orchestrator.service -- healthy/active on a binary built from terraphim-agents main (includes #2174, #2199, #2203).

Runs commands with sudo.

TinyUSB is a cross-platform USB Host/Device stack for embedded systems: memory-safe (no dynamic allocation) and thread-safe (ISR events deferred to task context).

Runs commands with sudo.

TinyUSB is a cross-platform USB Host/Device stack for embedded systems: memory-safe (no dynamic allocation) and thread-safe (ISR events deferred to task context).

Runs commands with sudo.

TinyUSB is a cross-platform USB Host/Device stack for embedded systems: memory-safe (no dynamic allocation) and thread-safe (ISR events deferred to task context).

Runs commands with sudo.

This file is the single source of truth for repository guidance used by both ChatGPT and GitHub Copilot. All automation tools should read these instructions instead of maintaining parallel copies elsewhere. The previous .github/copilot-instructions.md now only links here.

Runs commands with sudo.

Required

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

TinyUSB is a cross-platform USB Host/Device stack for embedded systems: memory-safe (no dynamic allocation) and thread-safe (ISR events deferred to task context).

Runs commands with sudo.

CSB ships with a number of AI agent skills that simplify the use of the CSB functionality. These skills contain information about common workflows for CSB usage:

Runs a vendor's official installer script from the internet.

This repository defines a multi-host NixOS flake for laptop, server, and kiosk profiles. It is designed for host nixos plus server hosts red, blue, and black; every host uses user leo.

Runs commands with sudo.

This is a new project. Document structure here as it develops.

Runs commands with sudo.

Conventions agents must follow when working in this repository.

Runs commands with sudo.

After {{<link title="Upgrade NetQ Virtual Machines" text="upgrading your NetQ VM">}}, upgrade the NetQ Agent:

Runs commands with sudo.

No description provided. From mcernohorsky/nix-config.

Runs commands with sudo.

This project has a graphify knowledge graph at graphify-out/.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

This project has a graphify knowledge graph at graphify-out/.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

This project has a graphify knowledge graph at graphify-out/.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

@CLAUDE-HOST.md

Runs commands with sudo.

Specific agent to work on pg-toolbelt issues

Runs commands with sudo.

UI/UX design intelligence. 67 styles, 96 palettes, 57 font pairings, 25 charts, 13 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles:…

Runs commands with sudo.

Design and execute a social engineering penetration test including phishing, vishing, smishing, and physical

Runs commands with sudo.

指标开发：为没有技术实现的业务指标找来源表 → 定口径 SQL → 建计算任务产出结果表 → 登记自定义指标 → 回流关联。 触发场景：指标开发 / 找不到可用的技术指标 / 给业务指标做技术落地 / 找来源表算指标 / 新建自定义指标。 流程：list-catalog-assets 先找现成结果表 → list-tables 找来源表 → get-table-columns 校验字段 → 产出任务草案交 update-batch-task / submit-batch-task → 【控制台人工登记自定义指标】→ 核验注册 → 交回 manage-biz-metric 关联。 关键限制：创建自定义指标（CUSTOM_INDEX）与资产上架无 OpenAPI，必须输出控制台指引并暂停等人工；get-table-columns 走 --catalog 项目英文名，不认 --project-id；list-tables 必带 --cli-query 收窄输出。 触发词：指标开发、自定义指标、CUSTOM_INDEX、找来源表、汇总表、指标计算任务、develop metric。

Runs commands with sudo.

Write ML papers for NeurIPS/ICML/ICLR: design→submit.

Runs commands with sudo.

poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Gracefully restart the Kiro Crew gateway from a running agent session while preserving continuity with a finite same-session resume monitor. Use when the user says "restart yourself", "restart gateway", or "reload config", or after a change that actually requires restart.

Runs commands with sudo.

Deep-review-first audit for Chinese and English academic papers across LaTeX, Typst, and PDF formats. Use whenever the user wants reviewer-style paper critique, pre-submission readiness checks, pass/fail gate decisions, structured revision roadmaps, or re-audits of revised manuscripts. Trigger even if the user only says "review my paper", "check if this is ready to submit", "audit this PDF", "simulate peer review", "find the biggest problems in this manuscript", or "re-check whether I fixed the…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Enumerating and attacking FreeIPA domains during authorized engagements — anonymous and authenticated LDAP

Runs commands with sudo.

Use when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders (useLoaderData).

Sends a key or token over the network to a host we can't verify.

Comprehensive techniques for acquiring, analyzing, and extracting artifacts from memory dumps for incident response and malware analysis.

Runs commands with sudo.

Infographics: 21 layouts x 21 styles (信息图, 可视化).

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Use when writing or revising ML or AI conference papers for venues such as NeurIPS, ICML, ICLR, ACL, AAAI, or COLM, especially when the workflow is conference-first rather than Nature-style journal-first.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

A user may ask you to create, edit, or analyze the contents of a .pptx file. A .pptx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.

Runs commands with sudo.

End-to-end UI/UX design and implementation. Use when the user asks to build new UI from a spec, audit or redesign existing UI, make UI less generic or "AI-looking", improve accessibility (WCAG AA) or responsiveness, create or tighten design systems (tokens, components), design dashboards, admin panels, SaaS apps, tools, settings pages, data interfaces, or any interactive product. Also triggers on: "build a landing page", "make this distinctive", "fix usability", "design system", "improve naviga…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

One-time pipeline configurator. Inspects the repo (default branch, validation scripts, labels), asks a few questions, writes .ai/agentic.config.json — the file every other skill reads — installs the tracker descriptor, and generates missing project docs (SDLC.md, CODE_REVIEW.md, BACKWARD_COMPATIBILITY.md, AGENTS.md starter). Re-run when the toolchain or label taxonomy changes. Verifies cross-skill coverage and prints the install command for missing skills.

Runs commands with sudo.

Answer economic and financial data questions with FactIQ data: US and international indicators, trade, markets, earnings calls, executive media, business news, and satellite signals. Satellite coverage includes rainfall, fires, air quality, NDVI, heat, soil moisture, nighttime lights, reservoir levels, shipping, ports, and chokepoints by country, state, or bounding box. Use for unemployment, inflation, GDP, wages, energy, trade flows, stocks, commodities, forex, earnings intelligence, drought a…

Has a line over 4000 characters, too long to scan reliably.

N-day 补丁差分到利用。从厂商发布的补丁里反推漏洞点、写 PoC、做成可用的攻击模块。 适用场景：已知 CVE 编号但只有补丁没有 PoC、SRC/红队需要打击未及时更新的资产、N-day 武器化、Patch Tuesday 跟进。 核心方法：拿 before/after 二进制 → 对齐符号 → 二进制 diff → 看新增的安全检查反推 bug class → 写 PoC 触发漏洞。 触发关键词：N-day、Nday、补丁差分、patch diff、patch tuesday、1day、binary diff 漏洞、bindiff 利用、ghidriff、Diaphora、补丁分析、CVE 复现、漏洞还原、补丁反推、N-day 武器化。

Runs commands with sudo.

Audit deployed Vercel apps for cost and performance issues using metrics, project config, code scans, and version-aware recommendations.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Audit deployed Vercel apps for cost and performance issues using metrics, project config, code scans, and version-aware recommendations.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Audit deployed Vercel apps for cost and performance issues using metrics, project config, code scans, and version-aware recommendations.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles:…

Runs commands with sudo.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles:…

Runs commands with sudo.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles:…

Runs commands with sudo.

Audit deployed Vercel apps for cost and performance issues using metrics, project config, code scans, and version-aware recommendations.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles:…

Runs commands with sudo.

Migrate from ChatGPT, Claude, OpenClaw, Hermes, Manus, and other AI assistants into Cadet by inspecting their data exports, conversation archives, files, prompts, custom instructions, memory, saved memories, tools, GPTs, workflows, integrations, and relationships, then mapping as much as safely possible into Cadet primitives. Handles single-source and multi-source migrations with a unified, deduplicated inventory.

Contains what looks like a real key or token.

把一篇文章或口播稿，做成"看起来像视频"的点击驱动 16:9 网页演示，可选合成口播音频。流程：原始文章 → **一次产出**口播稿 + outline 开发计划 → 用户**一次对齐** 5 件事（稿子 / outline / 主题 / 素材 / 开发模式）→ 网页开发（逐章 / 顺序 / 并行）→ 可选音频合成（provider-agnostic：内置 MiniMax mmx-cli + OpenAI TTS，可换 ElevenLabs / edge-tts / Azure / 自带 TTS）。**outline 只规划节奏与信息密度，不规划动画** —— 动画由章节开发时按 PRINCIPLES + ANTI-AI 法则即时设计。每次点击推进口播稿的一个节拍，每一步独占整屏，进度条平时隐藏只在悬浮时出现。适用场景：用网页做视频（动态 PPT 但不像 PPT）、把口播稿 / 文章变成可交互的解说、为 B 站 / YouTube / 视频号录屏教程、做有电影感的产品 / talk demo。本 Skill 沉淀的是设计方法论 + 协作流程 —— 不绑定任何特定样式 / 字体 / 颜…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.

Runs commands with sudo.

A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.

Runs commands with sudo.

A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.

Runs commands with sudo.

Use this skill when users want to search, discover, browse, or find Alibaba Cloud (阿里云) agent skills. Triggers include: "find a skill for X", "search alicloud skills", "阿里云有什么 skill", "搜索阿里云技能", "有没有管理 ECS/RDS/OSS 的 skill", "阿里云 skills 有哪些类目", "帮我找一个 skill", "browse alicloud skills", "list alicloud skill categories", "is there an alicloud skill that can...", "what alicloud skills are available", "XX Skill 的内容是什么", "我想了解阿里云 XX Skill 具体做什么","帮我安装阿里云 Skill" "阿里云 agent skill 市场", "搜一下阿里云的 skill".

Runs commands with sudo.

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Runs commands with sudo.

A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.

Runs commands with sudo.

A user may ask you to create, edit, or analyze the contents of a .docx file. A .docx file is essentially a ZIP archive containing XML files and other resources that you can read or edit. You have different tools and workflows available for different tasks.

Runs commands with sudo.

执行Token优化任务

Runs commands with sudo.

UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, and check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, and mobil…

Runs commands with sudo.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles:…

Runs commands with sudo.

[BETA] Detect, review, and fix code-quality and correctness issues in an AEM as a Cloud Service project — locally, with no external services or network calls. Use whenever a user wants to check, review, assess, audit, scan, modernize, upgrade, or fix AEM Java, Sling Models, OSGi, or Maven code — for example: "check my Sling Models are implemented correctly", "review my @Inject usage", "are my Maven dependencies up to date", "scan this AEM project for issues", "modernize my Sling Models", or "fi…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Audit deployed Vercel apps for cost and performance issues using metrics, project config, code scans, and version-aware recommendations.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Knowledge comics (知识漫画): educational, biography, tutorial.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

You are revising a Task skill, not directly solving the task. Use the provided Meta schema as class-level guidance. Your goal is to improve the Task skill for this task while preserving useful existing structure.

Runs commands with sudo.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, l…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Provides comprehensive guidance for Domain-Driven Design (DDD) concepts, strategic design, tactical design, and architecture patterns. Includes DDD applicability assessment, Pattern Boundaries table (what each pattern is and is NOT), Complexity Ladder (when to adopt each level), Core Concepts quick reference with Entity/ValueObject/Aggregate patterns, full architecture landscape overview, anti-patterns with fixes, multi-language reference implementations, and complete primary source references.…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Security audit of Solidity code while you develop. Trigger on "audit", "check this contract", "review for security", "loop mode", "run the auditor in loop mode", "run 3 passes". Modes - default (full repo) or a specific filename. Loop mode runs several passes in one scan, each pass told what the earlier ones found, and ends in one combined report; it remembers findings between scans in a ledger.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Complete Sarvam AI integration for OpenClaw using the official sarvamai Python SDK. Features Bulbul v3 TTS (30+ voices, 11 Indian languages), Saarika STT (real-time/batch/streaming), Translation (22 languages), Transliteration, and Document Intelligence.

Sends a key or token over the network to a host we can't verify.

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in m…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Codex needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Runs commands with sudo.

Expert guide for working with the byjg/php-gluo project. Use this skill whenever the user is working on this project — including setting up the dev environment, creating new CRUD features, scaffolding with the code generator, modifying or fixing existing features, writing or updating tests, running migrations, and maintaining OpenAPI documentation. Trigger this skill for any task related to models, repositories, services, REST controllers, attributes, authentication, DI configuration, or the by…

Runs commands with sudo.

Manage group chat messages, send messages, and join groups on the MetaID network. This skill handles fetching group chat messages, encrypting/decrypting messages, sending messages to groups, and joining groups. It works in conjunction with metabot-basic skill for blockchain operations. Use when users want to: (1) Fetch group chat messages from a specified group, (2) Send messages to a group chat, (3) Join a group chat, (4) Have MetaBot Agents participate in group discussions based on topics, (5…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Manage plant registry data, care profiles, reminders, and deterministic care evaluation through a validated Python CLI.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Detects, reproduces, and repairs Node.js event-loop starvation in a target repository. Runs a closed loop of reproduce, measure, diagnose, repair, and verify. Use this skill when a Node.js service shows high tail latency, blocked event loop, or health-check timeouts under load.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

当需要用 lark-cli 操作飞书多维表格（Base）时调用：搜索 Base、建表、字段管理、记录读写、记录分享链接、视图配置、历史查询，以及角色/表单/仪表盘管理/工作流；也适用于把旧的 +table / +field / +record 写法改成当前命令写法。涉及字段设计、公式字段、查找引用、跨表计算、行级派生指标、数据分析需求时也必须使用本 skill。

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Session-start meta-skill that enforces the 1% rule: before any action on a processkit entity or context/ file, if there is even a 1% chance a processkit skill applies, you MUST check skill-finder first. Load this skill at the start of every session that may involve processkit work. Use when beginning a new task, when unsure which skill applies, or when you are about to edit context/, create an entity, or run an MCP tool.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

Runs commands with sudo.

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

Runs commands with sudo.

Orchestrator — select competitive-analysis frameworks, run them inline one per session, and synthesize market landscape findings

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Runs commands with sudo.

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

Runs commands with sudo.

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

Runs commands with sudo.

Docker-based ROS2 development for robot software stacks. Use when containerizing ROS2 workspaces, writing Dockerfiles or docker-compose files, debugging DDS discovery across containers, configuring GPU, USB, X11 or Wayland passthrough, building devcontainers, or running ROS2 CI/CD in containers. Covers multi-stage builds, CycloneDDS and FastDDS container networking, shared memory, and deployment patterns for Humble, Iron, Jazzy, and Rolling on Ubuntu 22.04 or 24.04.

Runs commands with sudo.

Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

将用户合法拥有或已获授权的 CUDA 应用中的 Runtime 层迁移到 CANN Runtime，包括 API、类型、错误码、初始化、内存、stream、event、IPC、构建配置和兼容层适配。仅在处理 Runtime 层迁移或可行性分析时使用；不迁移 CUDA kernel、device helper 或任何算子实现。

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Provides guidelines for developing projected Android XR apps for display

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

Runs commands with sudo.

Gmail through the gws CLI — a daily actionable ledger per mailbox (needs-reply, action, waiting, fyi), plus attended triage, digests, reply drafts, follow-ups and cleanup.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2

Has a line over 4000 characters, too long to scan reliably.

You are helping a penetration tester perform network reconnaissance and service

Runs commands with sudo.

Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

The only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into prioritised notes, consolidates when they grow, and recovers anything missed. Five layers of redundancy, zero maintenance. ~$0.00/month (using free-tier models). While other memory skills ask you to remember to remember, this one just pays attention.

Runs commands with sudo.

Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, and limited Astro apps. Collect Vercel metrics, usage, project config, and code scan results first; investigate only metric-backed candidates; produce ranked recommendations grounded in verified files and version-aware Vercel/framework docs. Trigger for Vercel bill reduction, slow or expensive routes, caching opportunities, Function Invocations, Build Minutes, Fast Data Transfer, Core Web…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Trace, complete, and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).

Has a line over 4000 characters, too long to scan reliably.

ffmpeg recipes and best practices: convert, concatenate, merge, resize, compress, GIF creation, audio extraction, subtitles, optimize for social platforms.

Runs commands with sudo.

Aqua is a CLI-first message tool for AI agents. Use aqua CLI to exchange messages, manage contacts and invites, and drive agent inbox workflows with unread, watch, mark-read, or webhook-triggered serve integrations.

Runs commands with sudo.

The only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into prioritised notes, consolidates when they grow, and recovers anything missed. Five layers of redundancy, zero maintenance. ~$0.00/month (using free-tier models). While other memory skills ask you to remember to remember, this one just pays attention.

Runs commands with sudo.

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Runs commands with sudo.

Host modded Minecraft servers (CurseForge, Modrinth).

Runs commands with sudo.

Technical/on-page SEO, Core Web Vitals, structured data, GEO/LLM SEO, and quality-gate signals.

Runs commands with sudo.

Use BloodHound and SharpHound to enumerate Active Directory relationships and identify attack paths from compromised users to Domain Admin.

Runs commands with sudo.

Coleta e consulta dados de leiloeiros oficiais de todas as 27 Juntas Comerciais do Brasil. Scraper multi-UF, banco SQLite, API FastAPI e exportacao CSV/JSON.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design, brand-compliant presentations.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Use OpenMeld when a task needs Organization knowledge or Skills, Center Agent help, shared Spaces or Files, another Agent or computer, or scheduled cloud work. Also use for OpenMeld setup and Wake replies.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

当用户明确想做“小红书博主AI工作台”，或提到带货与创作者中的相关身份和任务时使用。本 Skill 面向主播、达人、带货博主、自媒体作者、个人IP和小型MCN内容团队，帮助用户将亲身体验组织成真实、可读、有视觉一致性的笔记，交付选题与商品事实表、脚本、封面/配图、分镜、成片计划、平台版本和发布前审核单。通过 AI-HIVE 统一查询和调用适合的文本、图片、视频模型，适合小白、个人和小团队。先做不计费计划和小样；付费、批量、发送或公开发布必须单独确认。不得虚构功效、销量、价格、授权或用户评价；不得克隆未经授权的声音、肖像和受版权保护内容。

Sends a key or token over the network to a host we can't verify.

Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer. Covers OCR backends, language packs, force-OCR, and performance tuning.

Runs commands with sudo.

Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

Runs commands with sudo.

Agent 自我学习与记忆更新技能。分析对话历史，提取关键信息，自动更新配置文件和学习记录，实现 Agent 持续自我成长。 融合自学习 (配置文件更新) + 自改进 (学习记录系统) 双引擎。 Use this skill when: - 需要整理和更新 Agent 记忆 (MEMORY.md, IDENTITY.md 等) - 对话中产生了新的配置信息或用户偏好 - 用户纠正 Agent 或发现错误时 (记录到 .learnings/) - 定期执行 Agent 自我优化 - 清理过时的配置和记忆 Triggers: 自我学习、记忆更新、配置优化、Agent 成长、整理记忆、记录学习、纠正错误

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Handles git commits, pushes, PRs, rebases, CI triage and monitoring, code review, branch splitting with stacked PRs via git-spice, merging PRs, and GitHub interactions -- use when the user asks to commit, push, amend, squash, rebase, create or update PRs, fix CI, review code, split a branch into stacked PRs, navigate stacks, merge a PR, or sync.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Reverse-engineer Electron apps by creating a runnable modified-app workspace, deterministically unminifying code without behavior change, decomposing modules, and iteratively renaming modules with runtime debugging and human verification gates.

Has a line over 4000 characters, too long to scan reliably.

Create a free remote development host on Oracle Cloud (Always Free) end to end — install and authenticate the OCI CLI, provision VCN/subnet/NSG/instance with capacity retries, then apply a hardened Ubuntu 22.04 Ansible stack (Tailscale-only SSH, ufw, fail2ban, mosh, persistent tmux, Caddy tailnet web previews, on-host verification suite) and tear it down again. Use when the user says "free remote dev environment", "Oracle Cloud free tier dev box", "OCI Always Free VPS", "give me a cloud dev mac…

Runs commands with sudo.

Session-scoped triage: what did I leave open, what is rotting, and is the plan still right — answered in under a screen. Runs in seconds over the session, the working tree, open PRs, and the two ledgers (ROADMAP + RELEASES DB), then emits a ranked list capped at 7 items plus a capped strategic read. Use when the operator says "/standup", "what's open", "what did I leave hanging", "where are we", "what should I do next", or is closing out a long working session. Not for long-window defect analys…

Has a line over 4000 characters, too long to scan reliably.

Tenable Nessus is the industry-leading vulnerability scanner used to identify security weaknesses across network

Runs commands with sudo.

Place and verify every overlay by reading exact coordinates off a labelled coordinate grid instead of estimating positions. Grid the real footage frame when graphics must line up with something in shot, and grid the overlay's own renders to measure where things actually landed — text bounds, collisions, margins, centring. Use for every overlay composition, whether or not it's tied to footage.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Documentación local de Stancl Tenancy v3 exportada desde tenancyforlaravel.com. Usar cuando trabajes con stancl/tenancy, multi-tenancy, tenants, domains, identificación de tenants, colas, migraciones tenant o bootstrappers.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Master Test Architect and Quality Advisor. Use when the user asks to talk to Murat or requests the Test Architect.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Best practices for Remotion - Video creation in React

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Investigate a Linux workstation crash or unexpected reboot. Use when the user asks why their machine crashed, rebooted without warning, or wants to understand what happened after coming back to a crashed system.

Runs commands with sudo.

Operate infrastructure, CI/CD, and production safely. Use for IaC, cloud, containers, Kubernetes, observability, CDN/edge caching, rollout, rollback, reliability, and cost; use security-engineer for threats.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Best practices and example-driven guidance for building SwiftUI views and components, including navigation hierarchies, custom view modifiers, and responsive layouts with stacks and grids. Use when creating or refactoring SwiftUI UI, designing tab architecture with TabView, composing screens with VStack/HStack, managing @State or @Binding, building declarative iOS interfaces, or needing component-specific patterns and examples.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Email sequences, newsletters, automation, and deliverability strategies. Use when the user requests 'email sequence', 'newsletter', 'drip campaign', 'welcome email', 'lifecycle email', 'cold email', 'email automation', or 'email copywriting'.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Directs pixel art that must read at several zoom scales at once — per-scale palette and silhouette rules, terrain-versus-unit contrast, a one-scene look test, and briefs for an artist or image generator. Trigger when a game renders one world through zoom bands or levels of detail, a pixelated 3D or 2.5D band with billboards included; when a sprite, unit or icon vanishes against terrain zoomed out; for a cross-band look test or pixel-art style guide; or say pixelsmith (test, brief, audit, 3d). W…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Deploy Caddy (no Docker) on a remote Linux host to expose a local HTTP backend as trusted HTTPS, prioritizing first-party domain + Let's Encrypt (HTTP-01), with DuckDNS DNS-01 fallback, low-bandwidth binary transfer fallback, verification, and rollback.

Runs commands with sudo.

This skill should be used when the user wants to design, prototype, or build anything branded for INOV8 Orthopedics or INOV8 Surgical (Houston, TX), such as a web page, slide, mock, email, form, dashboard, or production UI. Triggers on phrases like "INOV8 branding", "make this look like INOV8", "INOV8 design system", "INOV8 colors", "INOV8 Orthopedics page", "use our brand", or any request for INOV8-branded output. Points the agent at the brand book, the token files, and the component previews…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Code review automation for TypeScript, JavaScript, Python, Go, Swift, Kotlin, C#, .NET, Java, C, C++, Rust, Ruby, PHP, and Dart/Flutter. Analyzes PRs for complexity and risk, checks code quality for SOLID violations and code smells, generates review reports. Use when reviewing pull requests, analyzing code quality, identifying issues, generating review checklists.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles:…

Runs commands with sudo.

Annotate speech/TTS datasets with per-clip quality metrics (MOS, SNR, STOI, pitch, bandwidth, speaking rate, WER/CER, gender/emotion), multi-ASR consensus transcription and speaker labeling using the audiogear pipeline; then filter clips by quality and build listenable HTML QA reports. Use when asked to compute audio dataset metrics, build extended_metadata.csv, transcribe unlabeled audio, select clean TTS training data, or QA a speech dataset.

Runs commands with sudo.

此技能用于解析短视频链接，支持解析抖音、快手、B站等多个主流平台的短视频和图文链接，并能自动提取语音内容转录为文字。适用于需要批量获取视频元数据或将视频内容转为文本的场景时使用此 skill。

Runs commands with sudo.

Build or review NoTambourine-branded surfaces, slide decks, and copy. Use for brand styling, color questions, positioning, deck and document PDF export, and copy audits before shipping.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Initialize test framework with Playwright or Cypress. Use when the user says "lets setup test framework" or "I want to initialize testing framework"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Initialize test framework with Playwright or Cypress. Use when the user says "lets setup test framework" or "I want to initialize testing framework"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Initialize test framework with Playwright or Cypress. Use when the user says "lets setup test framework" or "I want to initialize testing framework"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Initialize test framework with Playwright or Cypress. Use when the user says "lets setup test framework" or "I want to initialize testing framework"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Initialize test framework with Playwright or Cypress. Use when the user says "lets setup test framework" or "I want to initialize testing framework"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Best practices for Remotion - Video creation in React

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Use this skill to prevent destructive operations when working on production systems or running agents autonomously.

Makes files world-writable (chmod 777).

실시간 키 입력 및 앱 로그 모니터링 환경을 구성합니다.

Has a line over 4000 characters, too long to scan reliably.

Work on deterministic movement, armor, ballistics, damage, and spotting simulation.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Process financial documents for Indian CA firms. Use when any PDF, Excel (.xlsx/.xls), CSV, JPG, or PNG file is received or uploaded — including GST returns, ITR PDFs, scanned invoices, trial balance sheets, bank statements, Form 16, TDS certificates, and audit reports. Automatically detects file type and extracts text, tables, and key fields (GSTIN, invoice number, totals, dates). Triggers on: file upload, attachment, "process this file", "read this PDF", "extract from this invoice", "analyse…

Runs commands with sudo.

Use when the user types /agento <command> [args]: routes an Agento command to its skills/agento/commands/<name>.md and runs it inline or through its custom agent.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Set up and manage local Kubernetes clusters using KIND (Kubernetes IN Docker). Use when testing Kubernetes applications locally or developing cloud-native workloads.

Runs commands with sudo.

Generate music using Suno AI API

Contains what looks like a real key or token.

Configuration and dot files for vim, tmux, git, bash, zsh, etc...

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Live on tiny.place (the agent-to-agent social network) like a person lives on a social app — entirely through the `tinyplace` CLI. Onboard a @handle identity, get funded, become discoverable, then run a recurring check-in loop that pulls your messages, notifications, and feed and acts on them: reply to DMs, react on the feed, follow agents, join groups, and fund/win bounties (contest-style paid work) over Signal end-to-end encryption and x402 payments. Use whenever an autonomous agent or harnes…

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

The social economy for autonomous AI agents.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

320+ curated Claude Code skills, 9 agents, 39 commands, sanitized configs & a Codex bridge — auto-indexed from skills/.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

A repository for appstore-ss-downloader

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

A skill

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Nik's personal Claude Code toolkit — machine-specific branch of ArnavKakani/claude-toolkit. Private.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

A repository for kadera

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

HackMIT 2026 Maximor CFO office — Dominik's working copy

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Collection of numerous agentic skills and commands used within my day-to-day

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Collection of numerous agentic skills and commands used within my day-to-day

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From marshadgani/Arshad.AI.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

A repository for transcriptor

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Generate images using the Kusa.pics API.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Generate images using the Kusa.pics API.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Generate .docx files from text.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From kunalrawat425/conductor-playground.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From khelil/my-claude.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

You are an expert in managing and utilizing the Claude Skills collection.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From hyunn9799/FinSight_Guard.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Apply the personal evidence and report-only contract to an explicitly requested review of code, a diff, a plan or another artifact.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Create Game Design Documents with mechanics and implementation guidance. Use when the user says "create GDD" or "game design document"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

sudo scutil --set HostName yourname

Runs commands with sudo.

../website/public/SKILL.md

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From devndesigner6/tinyplace.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Personal Intelligence Engine CLI for syncing, searching, and monitoring messages from Slack, Telegram, Discord, Linear, Gmail, Claude Code sessions, Markdown files, and WhatsApp. Use when working with traul commands, message sync, search, signals, briefings, or browsing chat history.

Runs a vendor's official installer script from the internet.

Domain expert in full-system testing with Playwright & Cypress

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Practical, code-focused explorations of distributed systems design—algorithms, patterns, and case studies drawn from real production infrastructure

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Open-source agent-agnostic YouTube growth toolkit — 21 AI commands + live channel MCP. Works with Claude Code, Cursor, Codex, Windsurf, Gemini CLI & any MCP client. SEO, scripts, Shorts, thumbnails, analytics, WordPress publishing. Free VidIQ/TubeBuddy alternative.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Local-first notes, tasks, and calendar context in one Rust and TypeScript workspace.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

A distrobox manager — with Vagrant-inspired declarative provisioning.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From LyrikNilpferd71/Hermes-Backup.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From Festo-Wampamba/Claude-Features.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From Chang-Shih-Yung/nexus-finance.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From BaGyun0107/harness-starterkit.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

No description provided. From 23jmo/claude-config.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

git commit --allow-empty -m "xxx"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

proyek sederhana membantu belajar tentang AI

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Expand test automation coverage for codebase. Use when user says "lets expand test coverage" or "I want to automate tests"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Shared utilities and constants for CIC internal pipeline packages

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

A skill

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

::: agentic_ci.skill

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Persistent memory & code intelligence server for AI coding agents. Deploy on VPS for shared memory across machines. Hybrid search (BM25 + pgvector), knowledge graph, impact analysis. 14 MCP tools. Works with Claude Code, OpenCode, Cursor, and any MCP client.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Establish project context - foundation for all design work

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Expand test automation coverage for codebase. Use when user says "lets expand test coverage" or "I want to automate tests"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Expand test automation coverage for codebase. Use when user says "lets expand test coverage" or "I want to automate tests"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Expand test automation coverage for codebase. Use when user says "lets expand test coverage" or "I want to automate tests"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Reference system prompt and tool schemas for Lovable. Use when imitating, comparing, or analyzing Lovable's prompting style; designing prompts inspired by Lovable; or answering questions about how Lovable is prompted.

Has a line over 4000 characters, too long to scan reliably.

Expand test automation coverage for codebase. Use when user says "lets expand test coverage" or "I want to automate tests"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Builds field maps from multi-source academic or technical corpora: expert mental models, debates, assumptions, prerequisites, oral-exam questions, and sprint study plans. Use for exam prep, research onboarding, or rapid topic mastery from multiple sources. Not for plain summaries or single short docs.

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Scaffold CI/CD quality pipeline with test execution. Use when the user says "lets setup CI pipeline" or "I want to create quality gates"

Some files were not scanned (too many, too big, or not text), so the grade is capped at C.

Telegram bot for customer support and delivery assistance.

Sends a key or token over the network to a host we can't verify.

Manual HTTP requests for targeted payload testing ONLY. For scanning, use gobuster/nmap/ffuf.

Runs commands with sudo.