Production Audit
Multi-angle production-readiness audit with file:line evidence and no hedging
Test report
- Verdict
- Tested · Works
- Score
- Tested
- Jul 30, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Jul 30, 2026 · 62aee33
⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 30, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.
Audited a real 1000-line Python toolchain (the design-harness scripts) twice: once as a plain read-through, once following the skill's lens catalog and its rule that a finding is verified by running the code before it is reported. The skill run produced nine located rows and I reproduced eight of them at the shell — a validator that reports "ok: no dangling links" for a link split across two lines, a CRLF card that parses to an empty frontmatter so a valid idea card is rejected as missing its id, an IndexError when -o is the last argument, an unknown flag silently redirecting output to a hardcoded /tmp path, a UnicodeDecodeError on a non-UTF-8 file, and a RecursionError on a 1200-card reference chain. The baseline read-through listed five candidates, four of which survived verification and one of which needed correcting, and it missed the silent-flag, encoding and CRLF defects entirely. Worth knowing before you run it: the full protocol converges only after two consecutive quiet passes with fixes gated on build plus typecheck plus lint plus tests, so on a real product this is a long, expensive session, and the "a short list means you did not look hard enough" framing pushes toward padding on small targets.
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 5/5
- Triggers reliably 4/5
- Output vs. baseline 8/10
- Docs & honesty 4/5
What Production Audit does
Runs repeated audit passes over a codebase, each from a different lens in its bundled catalog (attack-class, claim-vs-code, data-shape, failure-mode, config, concurrency and more), verifies every candidate finding against the real code before it is reported, and emits one flat severity-tagged list where each row carries a file:line and a one-line fix. Use it for pre-launch reviews, whole-product audits, or checking whether README and landing-page claims match the implementation; an optional scope argument narrows it to one subsystem or lens family.
How to install Production Audit
Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.
Commands — how to trigger Production Audit
-
/production-auditMulti-angle production-readiness audit with file:line evidence and no hedging
It also activates on plain-language prompts like these:
-
Audit this codebase before we launch, find everything wrong with file:line -
Check whether our README and landing page claims match the implementation -
Run a pre-launch production readiness review of the billing subsystem
Frequently asked questions
- Is the Production Audit skill free?
- Yes. The skill itself is free from apoorvjain25/production-audit. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Production Audit work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 30, 2026. Verdict: Tested · Works. Audited a real 1000-line Python toolchain (the design-harness scripts) twice: once as a plain read-through, once following the skill's lens catalog and its rule that a finding is verified by running the code before it is reported. The skill run produced nine located rows and I reproduced eight of them at the shell — a validator that reports "ok: no dangling links" for a link split across two lines, a CRLF card that parses to an empty frontmatter so a valid idea card is rejected as missing its id, an IndexError when -o is the last argument, an unknown flag silently redirecting output to a hardcoded /tmp path, a UnicodeDecodeError on a non-UTF-8 file, and a RecursionError on a 1200-card reference chain. The baseline read-through listed five candidates, four of which survived verification and one of which needed correcting, and it missed the silent-flag, encoding and CRLF defects entirely. Worth knowing before you run it: the full protocol converges only after two consecutive quiet passes with fixes gated on build plus typecheck plus lint plus tests, so on a real product this is a long, expensive session, and the "a short list means you did not look hard enough" framing pushes toward padding on small targets.
- What is the Production Audit SkillProof Score?
- 8.4/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 8/10, docs & honesty 4/5.
- How do I install Production Audit?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Production Audit with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.