메뉴
Regenerate catalog counts, layout claims, and README summaries from canonical sources. Run after adding, removing, or renaming skills, commands, or bundles.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Audit the skills library for duplicates, stale content, spec violations, and structural issues. Run periodically or before releases.
Validate SKILL.md files against the Agent Skills spec and Claude Code extensions. Run on new or modified skills before committing.
Audit AI agent instruction files (AGENTS.override.md, AGENTS.md, configured fallbacks, CLAUDE.md, hooks, and settings) across workspaces in read-only report mode. Use when agent configs drift, rules duplicate, files go stale, or after workspace restructuring; apply fixes only when explicitly requested.
Exercises rejection of an unsupported Codex project command path.
Design and operate LLM-as-a-Judge evaluation systems using direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment. Use when building LLM-as-judge systems, comparing model responses, calibrating rubrics, debugging inconsistent evaluations, or designing A/B tests for prompt or model changes.
Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, debug agent behavior, or design content generation prompts.
| name | readme-sync |
| description | Regenerate catalog counts, layout claims, and README summaries from canonical sources. Run after adding, removing, or renaming skills, commands, or bundles. |
| metadata | {"internal":true,"version":"1.1.0","tags":"readme, sync, maintenance, automation"} |
Regenerate catalog.json and every marked count/layout summary from the actual
skill, command, bundle, and tracked-path sources.
bun run catalog:generate
The generator derives:
skills/*/SKILL.md;commands/*.md;scripts/plugin-categories.json;git ls-files.It writes the single generated source catalog.json, then updates marked blocks in
README.md, AGENTS.md, and memory/architecture docs plus the package description.
Do not edit text between catalog-*:start and catalog-*:end markers manually.
bun run catalog:check
The lightweight repository validator also runs this check, and CI regenerates the catalog and fails if any generated file changes.
catalog.json and generated documentation diffs before committing.