Stats
Actions
Tags
From shipwright
Branch-aware audit orchestrator. On main — scans whole project, opens tracker issue. On feature branch — scopes to diff, auto-fixes, stages changes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/shipwright:audit-fullsonnetThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Smart audit that changes behavior based on where you are.
Smart audit that changes behavior based on where you are.
| Branch | Mode | Behavior |
|---|---|---|
main | Standalone | Scan whole project → open ONE consolidated GitHub issue |
feat/*, fix/* | In-ticket | Scope to diff vs main → auto-fix → stage changes (no commit) |
The skill detects your branch automatically. No flags needed.
Orchestrates three audit passes in sequence:
Issues found are classified:
| Priority | Meaning | Auto-fixed? |
|---|---|---|
| P0 (Critical) | Security, data loss | Yes |
| P1 (Major) | Bugs, perf regression | Yes |
| P2 (Warning) | Convention violations | Yes |
| P3 (Suggestion) | Style, naming nits | No — user decides |
In-ticket mode auto-fixes P0-P2. Standalone mode reports all issues in the tracker issue for human triage.
1. Scan full project
2. Group findings by module/area
3. Open ONE GitHub issue with all findings
4. Title: "Audit: <date> — <N> findings across <M> areas"
Why one issue? Avoid GitHub spam. One consolidated tracker is easier to triage than 20 tiny issues.
1. git diff origin/main...HEAD → changed files only
2. Run audit passes on changed files
3. Auto-fix P0-P2
4. Stage fixes (git add) — do NOT commit
5. Report what was fixed and what needs manual attention
No commit because /ship handles commits per-phase. The staged changes become part of Phase A's commit.
/audit-full # Auto-detect mode from current branch
npx claudepluginhub cloverink/shipwright --plugin shipwrightFetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Applies a firm's KYC/AML rules grid to parsed onboarding records: assigns risk rating, checks required documents, outputs rule outcomes with citations, and routes for escalation.
Generates daily or weekly digests of activity from connected sources (chat, email, docs, tasks, CRM), highlighting action items, decisions, mentions, and project updates.