Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

README Audit — measured AI agent skill | DecimalAI

archive228/readme-audit

SkillScore96Maintained

Check whether a README actually lets a stranger run the project. Use on any repo's README before publishing.

Documentationby archive228

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Doc Ops pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/archive228-readme-audit/SKILL.md

decimalai skills pull archive228-readme-audit --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/archive228-readme-audit/SKILL.md https://app.decimal.ai/s/archive228-readme-audit/SKILL.md

Raw file: /s/archive228-readme-audit/SKILL.md ↗ · machine-readable summary at /s/archive228-readme-audit.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 6h ago

Yes — +17% lift-24% tokens0% turns96% of whole cases pass with skill (22/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	55%	0%
case-03	✗→✓	▲ Improved	13%	0%
case-04	✗→✓	▲ Improved	-39%	0%
case-19	✗→✓	▲ Improved	-18%	0%
case-05	✓→✓	＝ Same ✓	-25%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

archive228 / loopkit

skills/readme-audit/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

README Audit

A README's only job: a stranger clones it and gets to "it works" without asking you. Check, in order:

One sentence on what it is and who it's for — above the fold.
Install — copy-paste commands that actually work on a clean machine. Test them mentally step by step.
Run / quickstart — the smallest end-to-end example.
Config — required env vars, where secrets go.
No rot — does it reference files/commands/flags that still exist? Stale README is worse than none.

Cut: long philosophy, badges nobody reads, TODO sections. Output: the specific gaps + the fix.

Want to see if archive228/readme-audit would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.