From mcollina-skills-1
Creates, updates, or prunes AGENTS.md with minimal, non-discoverable rules that agents cannot infer from code. Use when setting up agent config or fixing repeated agent mistakes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mcollina-skills-1:initThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when creating or updating `AGENTS.md` for a repository.
Use this skill when creating or updating AGENTS.md for a repository.
Use it especially when:
AGENTS.md is long, generic, or staleTreat AGENTS.md as a living list of non-discoverable landmines and workflow gotchas, not a codebase overview.
Before adding any line, ask:
Can an agent discover this by reading the repo (
README, code, config, scripts, directory tree)?
AGENTS.md.Include only guidance that is:
Typical examples:
uv instead of pip)--no-cache due to fixture behavior)Do not include:
Prefer short, high-signal sections such as:
Scope & routing (which areas need separate/module-local AGENTS files)Non-discoverable commandsLandmines / do-not-touch areasTask-specific constraintsFor large repos, recommend hierarchical AGENTS.md files near relevant modules instead of one monolithic root file.
AGENTS.mdREADME.mdPROJECT.md (if present).cursor/rules/ or .cursorrules).github/copilot-instructions.md)GEMINI.mdIf AGENTS.md exists, improve it incrementally instead of replacing it blindly.
AGENTS.md is temporary guidance, not permanent configuration.
When recurring issues appear:
For each line in AGENTS.md, verify:
Delete any line that fails one of these checks.
npx claudepluginhub mcollina/skillsCreates and maintains minimal AGENTS.md/CLAUDE.md files using research-backed best practices for concise, high-signal agent documentation under 60 lines.
Generates and maintains AGENTS.md files for AI agents by detecting project structure, extracting commands, CI rules, and architecture boundaries. Useful for onboarding agents and standardizing documentation.
Analyzes a codebase and creates or improves an AGENTS.md file to capture hidden conventions, constraints, and rationale for future agent instances.