audit-and-fix
Audit an existing codebase, then autonomously implement the fixes it judges worth making against your next goal — composing deep-dive → triage → prompt-pack → build-loop to turn "here's what's wrong" into verified, receipted local commits + an honest ledger. ALWAYS invoke when the user says any of "audit this repo and fix what you find", "audit and edit", "deep dive then fix the bugs", "implement the audit's recommendations", "plan and execute these fixes", or "autopilot this repo but skip the ideation". It composes those skills, never reimplementing them. Honest bounds: a receipt records what
npx skills add nelsonwerd/idea-to-ship-skills --skill audit-and-fix --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Audits an existing codebase in read-only mode to judge what is worth fixing, then automatically sequences and implements triaged fixes using a fixed pipeline: deep-dive → triage → prompt-pack → build-loop, producing verified local commits with receipts and an honest ledger. It never reimplements sub-skills; it orchestrates them and stops after local commits.
How it works
It operates as an orchestrator that points at the repository, performs a read-only audit, and, based on a triage verdict, moves through the phases: deep-dive to gather evidence, prompt-pack to assemble fixes and a mandatory ledger, and build-loop to apply fixes per unit, emitting one commit per verified boundary. It maintains a single gate between audit and write, uses a resumption model via resume, and records results in a receipts-based ledger. It never pushes, merges, tags, or publishes, and it only commits when a unit PASS is achieved. The live verification stage rechecks the cumulative diff before concluding.
When to use it
Use when the user explicitly requests one of these cues: "Audit this repo and fix what you find"; "deep dive then fix the bugs"; "audit and edit"; "Implement the audit's recommendations"; "Autopilot this repo, but skip the ideation"; or "Plan and execute these fixes" after a deep-dive briefing.
What it can touch
It touches the execution flow and the local repository through the orchestration of deep-dive, prompt-pack, and build-loop, and maintains a per-unit commit record in the local git history as part of its receipts workflow.
Caveats
It produces a read-only audit plus a fixed sequence of fixed changes; it does not prove correctness, and the live/real-world tail is not cleared by fixes. Local commits only; no push/merge/tag/publish. The live seam of build-loop is unproven in some contexts and may require real use to trust fully. Keys: one mandatory gate between audit and write; receipts discipline; and explicit, unit-based stopping conditions.
# Audit-and-Fix — autonomous audit→fix orchestrator `audit-and-fix` points at an **existing repo**, runs a rigorous **read-only audit**, makes a **value judgment about what's worth fixing**, takes **one human go**, then autonomously **sequences and implements** the triaged fixes — receipted, unit by unit, one commit per verified boundary — and **stops at local commits**. It is an **orchestrator: it composes the existing skills and never reimplements them.** It invokes `deep-dive`, `prompt-pack`, and `build-loop`, carries each one's file output into the next, and adds only the connective tissue — the triage verdict, the single gate, the regression fence, the receipt discipline, the resume contract, and the honest ledger. If a phase tempts you to paste a sub-skill's procedure into this run, stop: invoke the skill instead. **It is `autopilot` pointed backwards.** autopilot builds something that doesn't exist and risks *inventing demand*; `audit-and-fix` repairs something that does and risks *breaking working software*. Dropping `ideate` isn't a shortcut — **the codebase replaces it as the source of truth.** There is nothing to invent, so there's no grounding firewall to hold; the anal
- When to use this
- What it produces — and its honest bounds (read this before you trust it)
- The pipeline it flies (compose, never copy)
- The one gate (and the bounded escape hatch)
- Receipt discipline (the verification currency)
- resume — a first-class one-word verb
- Pitfalls to avoid
- Scale heuristics
What does the audit-and-fix skill do?
Audit an existing codebase, then autonomously implement the fixes it judges worth making against your next goal — composing deep-dive → triage → prompt-pack → build-loop to turn "here's what's wrong" into verified, receipted local commits + an honest ledger. ALWAYS invoke when the user says any of "audit this repo and fix what you find", "audit and edit", "deep dive then fix the bugs", "implement the audit's recommendations", "plan and execute these fixes", or "autopilot this repo but skip the ideation". It composes those skills, never reimplementing them. Honest bounds: a receipt records what
How do I install it?
Run `npx skills add nelsonwerd/idea-to-ship-skills --skill audit-and-fix --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From nelsonwerd/idea-to-ship-skills, a repository with 78 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.