← Browse

@majiayu000/create-agents-md

B

Create concise, repository-specific AGENTS.md files with operational contract, precedence rules, and drift-control guidance.

skillclaude

Install

agr install @majiayu000/create-agents-md --target claude

Writes 2 files into .claude/skills/, pinned to git-0ef99887.

  • .claude/skills/create-agents-md/SKILL.md
  • .claude/skills/create-agents-md/metadata.json

Document


name: "create-agents-md" description: "Create concise, repository-specific AGENTS.md files with operational contract, precedence rules, and drift-control guidance." metadata: source_prompt: "prompts/create-agents-md.prompt.md" workflow_type: "generation"

Create AGENTS.md

Purpose

Generate a complete root AGENTS.md file that acts as an operational entrypoint while preserving source-of-truth and repository governance rules.

When To Use

  • Use this skill when adding or refreshing repository AGENTS.md.
  • Use this skill when repository map, precedence, and session controls must be documented concisely.
  • Do not use this skill for project/user instruction file generation.

Required Inputs

  • Repository purpose and canonical paths.
  • Source precedence and key references.
  • Session-state defaults and command namespace rules.
  • Drift-control requirements.

Workflow

  1. Run seven-phase discovery using references/discovery-phases.md.
  2. Apply required element contract from references/required-elements.md.
  3. Generate artifact using references/output-format.md.
  4. Validate result against references/quality-checklist.md.
  5. Ensure links/paths remain relative and repository-accurate.

Output Expectations

  • One complete root AGENTS.md file.
  • Includes purpose, precedence, repo map, command policy, and drift-control.
  • Uses provider-neutral wording and valid relative links.
  • Remains scannable and operationally actionable.
  • Output contract and summary format follow references/output-format.md.

Resources

  • Discovery workflow: references/discovery-phases.md
  • Required element contract: references/required-elements.md
  • Output contract: references/output-format.md
  • Quality checklist: references/quality-checklist.md
  • Canonical template: ../../templates/AGENTS_template.md
  • Repository example: ../../AGENTS.md

Constraints And Safety

  • Do not duplicate full normative specs in AGENTS.
  • Preserve canonical path stability.
  • Keep guidance deterministic and testable.
  • Use relative path references only.

Repository README

Describes majiayu000/claude-skill-registry-data as a whole, which may contain artifacts other than this one. Where this artifact had no useful description of its own, its summary was taken from here.

Claude Skill Registry (Data)

This repo contains the archived skill contents (the heavy, browsable skill files).

Canonical layout

  • Category folders at repo root (e.g. development/, documents/, data/, ...)
  • Each skill lives under a category: <category>/<skill>/SKILL.md + <category>/<skill>/metadata.json
  • Case conflicts are resolved with {name}-{owner}-{repo} suffixes (fallback: -{short-hash}).

Archive status

  • Live badges above are sourced from claude-skill-registry-core stats.json.
  • Counts in this README are intentionally dynamic, not hardcoded.
  • If the badges look stale, refresh the core build/index pipeline rather than editing numbers here.

Where the index + site live

Trustgrade B

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • passType matchnot applicable to this artifact type

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • warnLicenseno SPDX license detected

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-0ef99887aeb92026-07-31