skills/repo-skill-generator/SKILL.md
Generate repo-local coding and review skills from a repository's git history and GitHub PR review activity. Use when asked to create, refresh, or update repository-specific coding/review skills, learn from PRs, analyze commit history, extract coding patterns, or generate coding guidelines for the current repo or a specific module.
npx skillsauth add samzong/samzong repo-skill-generatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Generate two repo-local skills from repository history:
coding skill derived from Git commits and diffs.review skill derived from GitHub PR review activity.Generated artifacts are installed into:
./.agents/skills/ as the canonical repo-local source../.claude/skills as a symlink pointing to ./.agents/skills.All generated content is in English.
repo-root is not a Git repository, THEN terminate. FIX: cd to a valid Git repository or pass --repo-root pointing to one.gh is missing when generating review data, THEN terminate. FIX: Install GitHub CLI (refer to https://cli.github.com/).gh is unauthenticated, THEN terminate. ACTION: Run gh auth status before generating review data. If not logged in, run gh auth login.--install-root to specify a writable path.gh auth status.gh is not authenticated, THEN instruct the user to run gh auth login.Execute the command that matches the use case:
# Current repo
python3 skills/repo-skill-generator/scripts/generate_repo_skills.py
# Different repo
python3 skills/repo-skill-generator/scripts/generate_repo_skills.py \
--repo-root /path/to/repo
# Module-level coding skill only
python3 skills/repo-skill-generator/scripts/generate_repo_skills.py \
--repo-root /path/to/repo \
--module src/router
# Safe install root for testing
python3 skills/repo-skill-generator/scripts/generate_repo_skills.py \
--repo-root /path/to/repo \
--install-root /tmp/repo-skill-generator-smoke
# Solo-repo preset (sparse review activity)
python3 skills/repo-skill-generator/scripts/generate_repo_skills.py \
--repo-root /path/to/repo \
--review-evidence-preset solo
# Strict preset (heavier review history expected)
python3 skills/repo-skill-generator/scripts/generate_repo_skills.py \
--repo-root /path/to/repo \
--review-evidence-preset strict
# Override preset thresholds (advanced)
python3 skills/repo-skill-generator/scripts/generate_repo_skills.py \
--repo-root /path/to/repo \
--min-effective-reviews 12 \
--min-unique-human-reviewers 3 \
--min-substantive-excerpts 6
After generation completes, confirm all three conditions:
generator-meta.json exists in each generated skill directory..repo-skill-generator-manifest.json exists at the skill root..claude/skills symlink points to .agents/skills/.IF any check fails, THEN review the script's stderr for the erroring step and re-run from step 2.
For each generated skill:
SKILL.mdprofiles/*.jsonprofiles/*-summary.mdreferences/evidence.mdreferences/anti-patterns.md or references/blocking-patterns.mdreferences/examples.mdgenerator-meta.jsonAt the skill root:
.repo-skill-generator-manifest.jsondefault: 8 effective reviews, 2 unique human reviewers, 5 substantive excerpts.solo: 3 effective reviews, 1 unique human reviewer, 2 substantive excerpts.strict: 20 effective reviews, 3 unique human reviewers, 10 substantive excerpts..claude/skills symlink.documentation
撰写微信公众号技术文章的结构化工作流。使用场景:用户要写一篇公众号文章、需要创建文章目录、组织素材、迭代草稿。强制遵循 blogs/wechat/README.md 的命名规范和目录结构。
tools
Cross-tool vibe coding profiler. Scans AI coding tool data on the machine (Claude Code sessions, OpenCode DB, Codex sessions), combined with git history and project memory, to build a true user portrait, discover workflow automation opportunities, and update the target tool's instruction file (CLAUDE.md or AGENTS.md) accordingly. Use when: "calibrate", "vibe-calibrate", "分析我的习惯", "profile me", "update my CLAUDE.md based on my history", "我的效率怎么提升", "analyze my patterns", "优化我的配置", or at the start of a long-term engagement with a new user.
development
Ruthless code simplifier: flatten abstractions, inline wrappers, remove unnecessary layers, delete dead code — without changing behavior. Use when: user says "simplify", "simplify this", "flatten", "inline", "too complex", "over-engineered", "remove abstraction", "unwrap", "reduce complexity", "make it simpler", "this is too complicated", or points at code that has unnecessary indirection. Does NOT change behavior, break public APIs, or remove meaningful error handling.
testing
Ship staged changes through a narrow release flow: auto-clean staged files, block unexpected non-i18n CJK additions, create or keep a branch, commit staged work, push, and open a pull request — all without confirmation. Use mainly when the user explicitly invokes `/ship` or says "ship it", "push and PR", or "commit and PR". Do not use for commit-only, push-only, PR-only, or existing-PR editing requests. All generated git and GitHub text must be in English.