Grade D

Production-ready CI/CD configurations for Playwright — GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, parallel sharding, reporting, code coverage, and global setup/teardown.

Tells the agent to skip permissions or safety checks.

History Bookmarks CRISPRO.ai Claude Describe crispro startup and/or your product and what it does. Recent Agent 1

Contains invisible or bidi Unicode (U+200B).

Here is the workflow you need to follow:

Tells the agent to skip permissions or safety checks.

Expert civil and structural engineer with global standards coverage — Eurocode, DIN, ACI, AISC, ASCE, AS/NZS, CSA, GB, IS, AIJ, and more. Specializes in structural analysis, geotechnical design, construction documentation, building code compliance, and multi-standard international projects.

Contains lookalike Unicode characters that mimic Latin letters in commands.

Expert civil and structural engineer with global standards coverage — Eurocode, DIN, ACI, AISC, ASCE, AS/NZS, CSA, GB, IS, AIJ, and more. Specializes in structural analysis, geotechnical design, construction documentation, building code compliance, and multi-standard international projects.

Contains lookalike Unicode characters that mimic Latin letters in commands.

We use playwright with pytest to e2e test Streamlit library. E2E tests verify the complete Streamlit system (frontend, backend, communication, state, visual appearance) from a user's perspective (black-box). They complement Python/JS unit tests, which are faster and focus on internal logic, input/output validation, and specific message sequences. Use E2E tests when testing behavior that requires the full stack or visual verification, especially for new elements or significant changes to existin…

HTML comment contains hidden instructions.

We use playwright with pytest to e2e test Streamlit library. E2E tests verify the complete Streamlit system (frontend, backend, communication, state, visual appearance) from a user's perspective (black-box). They complement Python/JS unit tests, which are faster and focus on internal logic, input/output validation, and specific message sequences. Use E2E tests when testing behavior that requires the full stack or visual verification, especially for new elements or significant changes to existin…

HTML comment contains hidden instructions.

Expert civil and structural engineer with global standards coverage — Eurocode, DIN, ACI, AISC, ASCE, AS/NZS, CSA, GB, IS, AIJ, and more. Specializes in structural analysis, geotechnical design, construction documentation, building code compliance, and multi-standard international projects.

Contains lookalike Unicode characters that mimic Latin letters in commands.

We use playwright with pytest to e2e test Streamlit library. E2E tests verify the complete Streamlit system (frontend, backend, communication, state, visual appearance) from a user's perspective (black-box). They complement Python/JS unit tests, which are faster and focus on internal logic, input/output validation, and specific message sequences. Use E2E tests when testing behavior that requires the full stack or visual verification, especially for new elements or significant changes to existin…

HTML comment contains hidden instructions.

This template is a general-purpose business website starter — the kind agencies clone per client for service businesses, portfolios, and local companies. It replaces the CodeStitch Intermediate Kit (Eleventy 3 + LESS + Decap CMS).

HTML comment contains hidden instructions.

ts 虽然有类型，但类型要求不严格。而 uts 为了编译为原生语言，是完全的强类型。

Contains invisible or bidi Unicode (U+200C).

OpenAI API (Text Generation & Moderation) Choosing the Right Model: Use the latest GPT-4 or GPT-3.5-turbo model for content generation. GPT-4 generally yields higher quality and more reliable adherence to instructions (important for brand voice). Use the Chat Completion API with a structured message (system message could be the .mdc content for ContentCreatorAgent, user message could contain the specific prompt with trends and product info). Prompt Engineering: We’ve crafted detailed prompts in…

Contains invisible or bidi Unicode (U+200B).

This template is a general-purpose business website starter — the kind agencies clone per client for service businesses, portfolios, and local companies. It replaces the CodeStitch Intermediate Kit (Eleventy 3 + LESS + Decap CMS).

HTML comment contains hidden instructions.

ts 虽然有类型，但类型要求不严格。而 uts 为了编译为原生语言，是完全的强类型。

Contains invisible or bidi Unicode (U+200C).

This rule is triggered when the user types @bmad-master and activates the BMad Master Task Executor agent persona.

Tells the agent to skip permissions or safety checks.

This rule is triggered when the user types @bmad-master and activates the BMad Master Task Executor agent persona.

Tells the agent to skip permissions or safety checks.

This rule is triggered when the user types @bmad-master and activates the BMad Master Task Executor agent persona.

Tells the agent to skip permissions or safety checks.

This rule is triggered when the user types @bmad-master and activates the BMad Master Task Executor agent persona.

Tells the agent to skip permissions or safety checks.

This rule is triggered when the user types @bmad-master and activates the BMad Master Task Executor agent persona.

Tells the agent to skip permissions or safety checks.

Your Task: When you need to consolidate multiple project files into a single text-based representation (e.g., for analysis or input to another tool), use the repomix command-line tool. Adhere strictly to the default behaviors specified below unless explicitly overridden by the user or task requirements.

Tells the agent to skip permissions or safety checks.

Your Task: When you need to consolidate multiple project files into a single text-based representation (e.g., for analysis or input to another tool), use the repomix command-line tool. Adhere strictly to the default behaviors specified below unless explicitly overridden by the user or task requirements.

Tells the agent to skip permissions or safety checks.

Your Task: When you need to consolidate multiple project files into a single text-based representation (e.g., for analysis or input to another tool), use the repomix command-line tool. Adhere strictly to the default behaviors specified below unless explicitly overridden by the user or task requirements.

Tells the agent to skip permissions or safety checks.

Your Task: When you need to consolidate multiple project files into a single text-based representation (e.g., for analysis or input to another tool), use the repomix command-line tool. Adhere strictly to the default behaviors specified below unless explicitly overridden by the user or task requirements.

Tells the agent to skip permissions or safety checks.

This rule is triggered when the user types @pm and activates the Product Manager agent persona.

Tells the agent to skip permissions or safety checks.

Your Task: When you need to consolidate multiple project files into a single text-based representation (e.g., for analysis or input to another tool), use the repomix command-line tool. Adhere strictly to the default behaviors specified below unless explicitly overridden by the user or task requirements.

Tells the agent to skip permissions or safety checks.

This rule is triggered when the user types @game-pm and activates the Godot Game Product Manager agent persona.

Tells the agent to skip permissions or safety checks.

This rule is triggered when the user types @game-pm and activates the Godot Game Product Manager agent persona.

Tells the agent to skip permissions or safety checks.

The Promptyoo-1 Prompt Optimizer interface with a clean, modern design.

Contains invisible or bidi Unicode (U+200B).

A structured interview that pins down what you are actually building before you build it.

HTML comment contains hidden instructions.

personas-web agent guidance, projected from .claude/CLAUDE.md

HTML comment contains hidden instructions.

Communication and response style for Cursor sessions

Tells the agent to skip permissions or safety checks.

Communication and response style for Cursor sessions

Tells the agent to skip permissions or safety checks.

Communication and response style for Cursor sessions

Tells the agent to skip permissions or safety checks.

Communication and response style for Cursor sessions

Tells the agent to skip permissions or safety checks.

Communication and response style for Cursor sessions

Tells the agent to skip permissions or safety checks.

description: "Functions-specific EazyTrack rules" alwaysApply: false globs:

HTML comment contains hidden instructions.

Goal: Allow MultiClaude projects and individual tasks to run with Claude Code, Codex, or Cursor while preserving worktree isolation, MCP completion reporting, and legacy configuration.

Tells the agent to skip permissions or safety checks.

The parts of TermHQ built specifically for running Claude Code, Codex, and other coding agents.

Tells the agent to skip permissions or safety checks.

By Arrya Thakur — June 2026

Tells the agent to skip permissions or safety checks.

Rust tests live inline in the modules under core/src/, including configuration, display, distribution, FFI, licensing, logging, metrics, policy, and secrets.

HTML comment contains hidden instructions.

This repository uses mandatory semantic traceability. Trace integrity is part of the Definition of Done. Follow the repository traceability skill and any trace instructions injected by hooks. Do not invent trace fields, replace stable IDs during refactors, or remove markers to silence validation. Before completing implementation work, trace verify --changed must pass under the active policy.

HTML comment contains hidden instructions.

This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in nodemodules/next/dist/docs/` before writing any code. Heed deprecation notices.

Contains invisible or bidi Unicode (U+2060).

Nome: Nexus Tagline: "Where your agents think together." Tipo: Web app local-first — não é SaaS, roda na máquina do usuário Fase atual: 0 — Landing page + Auth Usuários: Uso pessoal + times pequenos por convite

Tells the agent to skip permissions or safety checks.

Copy page

Contains invisible or bidi Unicode (U+200B).

Vite SPA (React 19 + TanStack Router/Query + Tailwind CSS 4) for the analytics dashboard. Built and bundled into packages/canonry/assets/ for distribution. This is the lowest-priority surface — never block a release on UI work.

Tells the agent to skip permissions or safety checks.

IMPORTANT: The following general instructions apply to the DevAIFlow project and MUST be followed when contributing to this codebase.

Runs commands with sudo.

After a few years of prompt engineering being the focus of attention in applied AI, a new term has come to prominence: context engineering. Building with language models is becoming less about finding the right words and phrases for your prompts, and more about answering the broader question of “what configuration of context is most likely to generate our model’s desired behavior?"

Image alt text contains hidden instructions.

(Auth, Products, Generations, Creative, Editing, Media, Billing, Calendar, Notifications, Search, Security, Templates, Brand)

Contains invisible or bidi Unicode (U+200C).

**Andrew Ng's The Batch** highlighted the significant improvement in code generation performance when using an iterative agent workflow, with **GPT-3.5** wrapped in an agent loop achieving up to **95.1%** accuracy on the HumanEval benchmark, surpassing **GPT-4** zero-shot at **67.0%**. The report also covers new developments in **Stable Diffusion** models like **Cyberrealistic_v40**, **Platypus XL**, and **SDXL Lightning** for Naruto-style image generation, alongside innovations in LoRA and ups…

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

Welcome, friend! This file documents the codebase for DeepSeek Code — a terminal-native AI coding agent. Thanks for being here. Reading this first will set you up for success. Let's build something great together!

Tells the agent to skip permissions or safety checks.

If you're a coding agent (Codex, Cursor, Claude Code) and a user said "use vibatchium," read this. Saves ~15 min of environment-discovery friction.

Tells the agent to skip permissions or safety checks.

No direct source-URL match in the current correction register.

Tells the agent to skip permissions or safety checks.

Konfigurer og brug specialiserede agenter.

Contains invisible or bidi Unicode (U+200B).

Subagents are separate agent instances that your main agent can spawn to handle focused subtasks. Use them to isolate context, run multiple analyses in parallel, and apply specialized instructions without adding to the main agent's prompt.

Tells the agent to skip permissions or safety checks.

Настройте и используйте специализированные агенты.

Contains invisible or bidi Unicode (U+200B).

本檔案是給在這個 repository 裡工作的 AI coding agent 看的操作細節；README 保持面向使用者、簡潔扼要。

Tells the agent to skip permissions or safety checks.

This is an autonomous development workspace. Agents build agents.

Tells the agent to skip permissions or safety checks.

이 레포에서 모든 에이전트가 항상 지키는 핵심 규칙 3가지입니다. 상세는 각 스킬 문서를 참조합니다.

Tells the agent to skip permissions or safety checks.

Docker sandbox templates that extend upstream sandbox images with file-based environment injection for agentic workflows. See README.md for the full mechanism and usage; this file covers what an agent needs to work safely here.

Tells the agent to skip permissions or safety checks.

Turkish entry point: tr/README.md.

HTML comment contains hidden instructions.

GitHub Copilot の [カスタム エージェント][custom-agents-concept] を使うと、開発ワークフロー内の特定のタスクや領域に合わせた専門的な AI アシスタントを作成できます。リポジトリの .github/agents フォルダー内にある markdown ファイルで agent を定義することで、focused instruction、best practice、コーディング パターン、ドメイン固有の知識を Copilot に与え、特定の種類の作業をより効果的に進められるようにできます。チームは自分たちの専門知識を再利用可能な agent として定義できます。たとえば、[WCAG][wcag] への準拠を徹底するアクセシビリティ agent、secure coding practice に従うセキュリティ agent、一定の test pattern を保つ testing agent などです。

Tells the agent to skip permissions or safety checks.

GitHub Copilot の [カスタム エージェント][custom-agents-concept] を使うと、開発ワークフロー内の特定のタスクや領域に合わせた専門的な AI アシスタントを作成できます。リポジトリの .github/agents フォルダー内にある markdown ファイルで agent を定義することで、focused instruction、best practice、コーディング パターン、ドメイン固有の知識を Copilot に与え、特定の種類の作業をより効果的に進められるようにできます。チームは自分たちの専門知識を再利用可能な agent として定義できます。たとえば、[WCAG][wcag] への準拠を徹底するアクセシビリティ agent、secure coding practice に従うセキュリティ agent、一定の test pattern を保つ testing agent などです。

Tells the agent to skip permissions or safety checks.

GitHub Copilot の [カスタム エージェント][custom-agents-concept] を使うと、開発ワークフロー内の特定のタスクや領域に合わせた専門的な AI アシスタントを作成できます。リポジトリの .github/agents フォルダー内にある markdown ファイルで agent を定義することで、focused instruction、best practice、コーディング パターン、ドメイン固有の知識を Copilot に与え、特定の種類の作業をより効果的に進められるようにできます。チームは自分たちの専門知識を再利用可能な agent として定義できます。たとえば、[WCAG][wcag] への準拠を徹底するアクセシビリティ agent、secure coding practice に従うセキュリティ agent、一定の test pattern を保つ testing agent などです。

Tells the agent to skip permissions or safety checks.

GitHub Copilot の [カスタム エージェント][custom-agents-concept] を使うと、開発ワークフロー内の特定のタスクや領域に合わせた専門的な AI アシスタントを作成できます。リポジトリの .github/agents フォルダー内にある markdown ファイルで agent を定義することで、focused instruction、best practice、コーディング パターン、ドメイン固有の知識を Copilot に与え、特定の種類の作業をより効果的に進められるようにできます。チームは自分たちの専門知識を再利用可能な agent として定義できます。たとえば、[WCAG][wcag] への準拠を徹底するアクセシビリティ agent、secure coding practice に従うセキュリティ agent、一定の test pattern を保つ testing agent などです。

Tells the agent to skip permissions or safety checks.

GitHub Copilot の [カスタム エージェント][custom-agents-concept] を使うと、開発ワークフロー内の特定のタスクや領域に合わせた専門的な AI アシスタントを作成できます。リポジトリの .github/agents フォルダー内にある markdown ファイルで agent を定義することで、focused instruction、best practice、コーディング パターン、ドメイン固有の知識を Copilot に与え、特定の種類の作業をより効果的に進められるようにできます。チームは自分たちの専門知識を再利用可能な agent として定義できます。たとえば、[WCAG][wcag] への準拠を徹底するアクセシビリティ agent、secure coding practice に従うセキュリティ agent、一定の test pattern を保つ testing agent などです。

Tells the agent to skip permissions or safety checks.

Coding agent guide for codecompanion-run-bash.nvim.

Tells the agent to skip permissions or safety checks.

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Tells the agent to skip permissions or safety checks.

A lightweight, security-conscious CLI "Worker" agent designed to perform local file implementation tasks using a local LLM (like LM Studio or Ollama).

Tells the agent to skip permissions or safety checks.

Stop and ask when:

HTML comment contains hidden instructions.

This repository contains a Model Context Protocol (MCP) server written in TypeScript that integrates with the Planfix CRM REST API. The server exposes several tools located in src/tools which can be called by MCP clients.

Contains lookalike Unicode characters that mimic Latin letters in commands.

Read CLAUDE.md, at this root, before changing anything. It is written for every agent, not only Claude Code: the stack, the build and test commands, the invariants, the module structure, and its section "Under another agent", which says which of this project's checks hold for you and which do not.

HTML comment contains hidden instructions.

No description provided. From pankaj28843/learn-danish.

Tells the agent to skip permissions or safety checks.

Generates lab-work reports for the "Програмування" course (NTU «Dnipro Polytechnic») as DOCX + PDF, fully compliant with Appendix А formatting rules of the 2025 methodical guide. Use when the user asks to create/generate a lab report («створити звіт з лабораторної роботи», «зробити звіт по роботі №…», "lab report for programming", «оформи звіт»).

Contains lookalike Unicode characters that mimic Latin letters in commands.

Bootstrap, coordinate, inspect, and recover human-directed multi-agent engineering workflows inside Herdr. Use for session setup, workspace provisioning, role packet binding (Manager, Delegator, Worker, Verifier, Critic), Markdown state or an explicit SQLite run, serial verification locks, model launch routing, and fail-closed crash recovery.

Tells the agent to skip permissions or safety checks.

Build automated evaluation suites for AI agents using golden datasets,

Tells the agent to skip permissions or safety checks.

Audit and safely repair cross-runtime Skill governance: canonical-source ownership, divergent or duplicate projections, exposure scopes and budgets, lifecycle drift, quarantine, and retirement. Use when the user explicitly requests cross-runtime or cross-scope Skill governance; ignore project-local Skill inventory, product/runtime loading or enablement checks, usage statistics, and mentions/traces.

Tells the agent to skip permissions or safety checks.

Turn a raw product, app, bot or feature idea into one evidence-backed build blueprint (researched stack, epics, Given/When/Then criteria, tests) that coding agents build one epic per session.

Contains invisible or bidi Unicode (U+200C).

Author and review high-quality agent skills with triggers, progressive disclosure, and safety notes.

Tells the agent to skip permissions or safety checks.

本技能用于生成、修改或完善可直接使用的中国法律文书 DOCX 成品，可根据事实、证据、判决书、原文书或案件材料完成文书识别、缺失信息占位、法律依据核验、专业写作和 Word 排版。覆盖民事诉讼与执行、仲裁、刑事、行政及其他普通非诉法律文书，包括起诉状、答辩状、反诉状、上诉状、再审申请书、申请执行书、财产保全申请书、管辖权异议书、仲裁申请书、辩护词、代理意见、质证意见、证据目录、授权委托书、律师函、通知、合同和协议等；合同和协议属于次级类型。 用户未准确说出文书名称，但明确表示“我要起诉对方”“收到传票需要回应”“不服一审判决”“判决后对方不付款”“申请冻结财产”“公司拖欠工资需要仲裁”“整理成法院能用的材料”，并希望形成正式材料时，本技能也可识别文书类型并完成 Word 成品；信息不足时使用待补充占位符，不编造事实。 不要用于法律意见书的起草、修改、完善、审查或复核，此类任务必须使用 `legal-opinion`；不要用于企业法律尽职调查或法律尽调报告，此类任务必须使用 `legal-due-diligence`。也不要用于仅咨询法律规则、只查法条或案例、评估案件胜算、制定诉讼策略…

Contains lookalike Unicode characters that mimic Latin letters in commands.

An SEO agent skill for quick, lightweight, default single-page SEO audits. Performs basic on-page and site-level checks and outputs a structured basic SEO audit report. Use when the user asks for "SEO audit", "SEO check", "check my page SEO", "page analysis", or wants a first-pass review of a URL. If the user requests "deep audit", "full report", "technical SEO audit", or "advanced SEO", use seo-audit-full instead.

HTML comment contains hidden instructions.

INVOKE WHEN: - Starting any task — query first (cq catches blind spots your training data missed: stale versions, integration gotchas, undocumented quirks) - You just resolved a non-obvious error, confusing error message, or surprising tool behavior — present a draft KU to the user and call `propose` if they approve - Retrieved guidance proved correct or wrong — confirm or flag it SKIP WHEN: - You already queried cq for this exact topic earlier in this session Propose with user approval mid-tas…

Tells the agent to skip permissions or safety checks.

Web saldırılarında ve phishing sayfalarında kullanılan gizlenmiş JavaScript kötü amaçlı yazılımını eval zincirleri ve dize manipülasyonunu tersine çevirerek açar.

Decodes an obfuscated payload and executes it.

流程评价工作流管理 — 当专职推动流程效率优化工作、需要有序管理单个或多个流程评价（SCOPE→BASELINE→ASSESS→REPORT→TRACK 生命周期）、组装评价基线并管理其版本时使用。管理评价组合与生命周期门禁，调度能力层技能（policy-digest / goal-alignment / rcm-analysis / control-testing / efficiency-diagnosis）。

Contains invisible or bidi Unicode (U+FEFF).

SQL injection, XSS, CSRF, LFI/RFI, command injection.

Decodes an obfuscated payload and executes it.

SQL injection, XSS, CSRF, LFI/RFI, command injection.

Decodes an obfuscated payload and executes it.

Use when adding or editing an OpenCode Desktop injection mod for this repo's CDP toolchain (shuaqii.py + scripts/core.js) — registering overlay lines, reading session/message state from the bundled server, detecting running/idle, or sending messages. Triggers: "new inject mod", "新增脚本", "写个脚本注入", "overlay", "session-timer", "retry", "shuaqii".

Contains invisible or bidi Unicode (U+FEFF).

లెర్నర్ ఈ క్రింద ఉన్నప్పుడు ఈ నైపుణ్యాన్ని సక్రియం చేయండి:

Contains invisible or bidi Unicode (U+200C).

Index the team's own documents — PDFs, Word files, Markdown, plain text — into a per-space catalog the AI-DLC agents can cite. Wraps `aidlc-knowledge.ts`: onboard, sync, list, show, associate, dissociate, rebind, summarize. Every catalog row is written by the tool under a workspace lock; this skill never edits the catalog by hand and never advances workflow state.

Tells the agent to skip permissions or safety checks.

Use whenever the user wants to DEPLOY, host, or purchase anything on Huawei Cloud that creates billable resources: application deployments (部署应用到华为云, deploy my app, 上线, 搭建), architecture proposals, cost estimation, multi-resource provisioning (VPC, subnet, security group, ECS, EIP, RDS, OBS, CDN, DNS, FunctionGraph, CCE, GaussDB and more), session-scoped state tracking, and reverse-order destroy. Trigger words: 部署, 部署到华为云, 上线, 购买, 搭建, 开通, 成本估算, 多少钱, 销毁, deploy, deploy to Huawei Cloud, provision…

Contains invisible or bidi Unicode (U+FEFF).

Version 2.35.0 | PRD to Production | Zero Human Intervention > Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025)

Tells the agent to skip permissions or safety checks.

Version 2.35.0 | PRD to Production | Zero Human Intervention > Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025)

Tells the agent to skip permissions or safety checks.

Version 2.35.0 | PRD to Production | Zero Human Intervention > Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025)

Tells the agent to skip permissions or safety checks.

Run health checks on the vault for inconsistencies, stale data, orphaned notes, and missing connections. Use periodically or when user says "lint", "health check", or "audit".

HTML comment contains hidden instructions.

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

Runs commands with sudo.

Run a multi-agent pipeline to produce detailed technical requirements and a ticket-ready summary. Creates a feature branch, persists session state, and supports resume. Optionally seeds from a prior brainstorm or meeting session, takes the ticket from --ticket <KEY> and auto-fetches its Jira description, or starts ticket-less via --no-ticket (reconcile with a real ticket later via the reconcile subcommand). --help prints usage and starts nothing.

Tells the agent to skip permissions or safety checks.

Version 2.35.0 | PRD to Production | Zero Human Intervention > Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025)

Tells the agent to skip permissions or safety checks.

Generate and iterate images with Google Antigravity's agy CLI in headless mode, and script non-interactive agent runs with machine-readable output. Use whenever the user asks for a generated or edited image (illustration, texture, icon, concept art, variation), mentions agy or Antigravity, or wants an agent run from a script, a batch or CI.

Tells the agent to skip permissions or safety checks.

Audit and harden your OpenClaw configuration. Checks AGENTS.md, gateway settings, sandbox config, and permission

Tells the agent to skip permissions or safety checks.

Manages Franklin Baldo's Suno profile as a whole — bio, genre tags, pinned songs and their captions, and playlists — using the reverse-engineered Suno write API. Use when wording or applying a profile bio, choosing genre tags, writing pinned-song captions, creating or curating a playlist, or drafting the profile's overall curatorial identity. Every write to Suno requires Franklin's explicit per-action authorization; this skill documents what's possible and how to word it well, it does not grant…

Tells the agent to skip permissions or safety checks.

Delegate coding tasks to Blackbox AI CLI agent. Multi-model agent with built-in judge that runs tasks through multiple LLMs and picks the best result. Requires the blackbox CLI and a Blackbox AI API key.

Tells the agent to skip permissions or safety checks.

Boot, recover, tune, and verify the SCBE Android emulator phone lane for AetherCode and Polly Pad. Use when Codex needs to operate the `SCBE_Pixel_6_API35` emulator, repair stale lock state, resize the phone surface, or prove the current lane state from local artifacts.

Tells the agent to skip permissions or safety checks.

Use when a task spans multiple steps, files, or unknowns — before planning the order of work, whenever about to report completion or success in any wording, and when picking the next action after a result, failure, or surprise. Also under deadline pressure, or when resuming work built on questionable foundations.

Tells the agent to skip permissions or safety checks.

AI 자율 개발 루프 제어 스킬. codeloop start/stop/status 서브커맨드로 Stop Hook 기반 무한 루프를 시작·중지·모니터링한다. Triggers: codeloop, codeloop start, codeloop stop, codeloop status, 루프 시작, 루프 중지, 루프 상태, ループ開始, ループ停止, 循环启动

Tells the agent to skip permissions or safety checks.

clawd

Tells the agent to skip permissions or safety checks.

Facilitate game brainstorming sessions with game-specific techniques. Use when the user says "brainstorm game" or "game ideas"

Tells the agent to skip permissions or safety checks.

Test plans, unit/integration/contract/load testing, coverage targets

Contains invisible or bidi Unicode (U+200B).

Avoid slow, research-heavy, half-delivered implementation loops by enforcing execution discipline, verification-first delivery, and immediate root-cause patching. Use when building complex systems where the temptation is to over-research instead of finishing the main line of work.

Tells the agent to skip permissions or safety checks.