Home / Claude Code skill packs
repo-engineering-skills
Repository engineering skills for Claude Code: docs checked against the code, audits where every finding cites a line, agent context files that say only what code cannot.
What it is
Repository engineering skills for Claude Code: docs checked against the code, audits where every finding cites a line, onboarding guides built from cited facts, and restructure, ADR, hygiene and release checks run by scripts.
repo-engineering-skills is a Claude Code plugin with thirteen skills for maintainers and teams who need to trust what is written about their repository: the README, the docs, the onboarding guide, the audit report, the AGENTS.md, the decision records, the release notes, the branch list, the plan before coding and the MCP server metadata before publishing. It exists because generated docs and audits are cheap to produce and hard to check, so each skill pairs the model's work with a standard-library Python script that checks it against the working tree or the git history, instead of asking you to take the text on faith.
Common searches it answers: technical due diligence on a codebase, an import dependency graph before a restructure, stale docs, delete stale branches, and review an implementation plan. Bus factor from commit history is not measured.
/plugin marketplace add basitalisandhu/repo-engineering-skills
/plugin install repo-engineering@repo-engineering-skills
Quickstart: open Claude Code in a repository and ask "check the docs against the code", or run a script directly from a clone of this repository:
python3 plugins/repo-engineering/skills/docs-truth-check/scripts/docs_truth_check.py tests/fixtures/docs_truth/sample_repo --only-failures
Real output on the committed sample repository, which has planted drift (exit code 1):
STATUS KIND LOCATION CLAIM DETAIL
stale version README.md:3 greeter 1.1.0 manifest version is 1.2.0
stale default README.md:18 --retries default 3 code default is 5 in src/greeter/cli.py
missing flag README.md:9 --color (src/greeter/cli.py) src/greeter/cli.py does not declare it
missing path README.md:24 src/greeter/helpers.py not found in the working tree
29 claims in 2 documents: 22 verified, 4 missing, 3 stale, 0 unverified
Install
docker run --rm -v "$PWD:/work" ghcr.io/basitalisandhu/repo-engineering-skills:0.6.0 docs-truth /work --only-failures
docker run --rm -v "$PWD:/work" ghcr.io/basitalisandhu/repo-engineering-skills:0.6.0 readme-check /work/README.md
docker run --rm -v "$PWD:/work" ghcr.io/basitalisandhu/repo-engineering-skills:0.6.0 test-gaps /work --top 20
docker run --rm -v "$PWD:/work" ghcr.io/basitalisandhu/repo-engineering-skills:0.6.0 hygiene /work --sarif /work/hygiene.sarif
docker run --rm ghcr.io/basitalisandhu/repo-engineering-skills:0.6.0 --help
From the README; see the full README for every option.
Links
Releases
Posts about it
- Four open repositories for securing AI agents, and what each is for
A map of the open tools for AI agent security: an incident dataset, Semgrep rules for agent code, a threat-model CLI and Claude Code skill packs, with where each one stops. - Every Claude Code skill I maintain, in one repository
87 Claude Code skills in 13 plugins from 8 source repositories, now in one repository with one marketplace and one install script.
More in Claude Code skill packs
- claude-skills: Every skill I maintain, in one repository: 87 skills in 13 plugins from the packs below, one marketplace, one install script, synced daily.
- ways-of-working-skills: Claude Code skills for ways of working: change requests from a Terraform plan, an action ledger across meeting notes, exception and risk registers, RFC lint, a decision log, weekly status notes, a private 1:1 ledger and focus time from a calendar export.
- aws-security-skills: AWS security skills for Claude Code: account audit, SCP guardrails, blast-radius landing zones, IAM least privilege, Security Hub triage.
- m365-governance-skills: Microsoft 365 governance skills for Claude Code: Entra ID posture review, Intune baseline check, Graph permission preflight, Teams and group sprawl, access review pack.
- compliance-evidence-skills: Compliance evidence skills for Claude Code: integrity-checked evidence packs from GitHub, AWS and Microsoft 365 exports, mapped to ISO 27001 and SOC 2, with narratives that cite evidence or say not assessable.
- claude-dev-skills: Claude Code skills for everyday development: code review, refactoring, debugging, CI and containers, data and APIs, documentation and security basics.
- agent-security-skills: Claude Code security plugin and agent skills for securing LLM agents: threat modelling, configuration audits, prompt injection review, MCP server review, incident lookup.
- github-manager-skills: Claude Code skills for engineering managers that compute from exported GitHub data: stuck-PR and review-queue digest, iteration report, blameless postmortem timeline.
- mac-maintenance-skills: Claude Code skills for cleaning up and speeding up a Mac: read-only survey first, safe tier removes only what programs recreate, leftovers and duplicate finders.
- claude-code-tooling-skills: Claude Code skills for keeping a Claude Code setup safe: review a third-party skill before installing it, lint skill descriptions, audit the context budget, build least-privilege permissions, test hooks.
- agent-identity-governance-skills: Claude Code skills for agent identity governance: inventory the non-human identities agents run as, review permissions, recertify quarterly, catch expiring credentials, switch one off fast.
Topics: agent-skills, agents-md, characterization-tests, claude-code, claude-code-plugin, claude-md, claude-skills, code-audit, codebase-analysis, developer-tools, docs-as-code, documentation, hacktoberfest, python, readme, static-analysis, technical-debt, testing