Audit any repository for Gibson-readiness: what the product is, stack, test/CI/gate coverage, backlog shape, risk surfaces (money, auth, consent/PII, security boundaries, production data), and a plain-English readiness report with concrete gaps. First stage of the /gibson pipeline; also useful standalone ('audit this repo', 'is this repo ready for the fleet', 'gibson readiness check').
Scanned 9/28/2026
Install to Claude Code
npx -y skills add The-AIE/the-gibson --skill gibson-audit --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Gibson Audit?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/the-aie-gibson-audit)More formats (shields.io, HTML) on the badges page.
---
name: gibson-audit
description: "Audit any repository for Gibson-readiness: what the product is, stack, test/CI/gate coverage, backlog shape, risk surfaces (money, auth, consent/PII, security boundaries, production data), and a plain-English readiness report with concrete gaps. First stage of the /gibson pipeline; also useful standalone ('audit this repo', 'is this repo ready for the fleet', 'gibson readiness check')."
---
# gibson-audit — know the repo before touching it
Input: a repo path or GitHub URL (clone to a scratch location if URL-only).
Output: a readiness report the owner can read without knowing how to code, plus
a machine-usable gap list the `gibson-setup` skill consumes.
## What to inspect (read-only by default — the ONLY write this skill may ever make is persisting the audit report, and that goes through a worktree per Law 3)
1. **Product identity** — README, package.json/pyproject, deployed URLs. One
paragraph: what this software does, for whom.
2. **Stack + build reality** — language, framework, how to build/test/run.
Actually run the test suite if cheap; report pass/fail truthfully.
3. **Guardrails present vs missing** — checklist against the Gibson baseline:
- `AGENTS.md` (or section) with fleet rules?
- CI running tests on PRs? Required checks configured?
- Branch protection on the default branch?
- Risk classifier / Tier-C gating (money, auth, consent/PII, security
boundaries, production data)?
- DCO or sign-off convention?
- Secrets hygiene (gitleaks or equivalent)?
- Kill switch (`gibson/HALT` support comes free with the loop)?
4. **Backlog shape** — open issues: how many are well-scoped with acceptance
criteria vs vague? Is there a plan doc? (No usable backlog → the pipeline
must run `gibson-direct` before `gibson-run`.)
5. **Risk surfaces** — grep for ALL Law 7 categories: money/payments, auth,
consent/PII, security boundaries (headers, rate limits, sandboxing), and
anything touching production data. These paths get Tier-C treatment
regardless of what the repo's own docs say.
6. **Deployment posture** — if a live/preview URL exists, run
`scripts/posture-probe.sh <url>` from the Gibson clone for headers/cookies/
rate-limit reality. Preview/staging only — never burst production.
## Report format
Two parts, always both:
- **For the owner (plain English, Ask Contract style):** what the repo is, how
healthy it is, what's missing before agents can safely run unattended, and
anything that genuinely needs their decision. No jargon unexplained.
- **Gap list (machine part):** checkbox list of missing guardrails with the
exact `gibson-setup` action for each. Return it inline by default. If asked
to persist it as `gibson/audit.md` in the target, that write goes through a
worktree + branch like any other mutation (Law 3) — persisting the audit is
the one thing that graduates this skill out of read-only mode, so it follows
the write rules.
Truthfulness rule (Law 8): report what IS, including pre-existing test failures
and scary findings. Never soften a gap because it's awkward.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!