This directory owns tracked, project-scoped agent instructions. Claude reads the directories directly. Codex uses the ignored .agents/skills projection created by scripts/agents/linkcodexskills.ps1; it is not a second authored copy.
agents
agents
ANo problem foundNishDJ/supabase-openai-realtime-compendium
エージェントはアプリの主要な構成ブロックです。エージェントは、大規模言語モデル ( LLM ) に instructions と tools を設定したものです。
agents got grade A on our automated scan on 2026-10-23.
Before you install
- Read any scripts this skill ships.
- Note every URL it fetches.
- Check allowed-tools and hooks.
Embed this grade
Add this badge to your README. It shows the current grade from CheckSkills.
Report this skill if the grade looks wrong, or if something slipped through.
Related
Please refer to the actual skill definition located at ../../.skills/implement/SKILL.md.
Run project onboarding — reads START_HERE.md and executes the protocol there. Auto-detects new project vs. existing codebase, interviews you (new) or reads the code and asks only what it can't answer (existing), fills docs, builds the backlog. Usage: /start
Use the Azure DevOps MCP server for project management
Claude adapter for PlainTab test-first feature work, bug fixes, regression scripts, and behavior-focused validation.