Ready to supercharge your AI agents?

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

Loop Verifier — Changelog Drafter — measured AI agent skill | DecimalAI

cobusgreyling/loop-verifier

SkillScore73Maintained

Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.

Code Reviewby cobusgreyling

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/cobusgreyling-loop-verifier/SKILL.md

decimalai skills pull cobusgreyling-loop-verifier --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/cobusgreyling-loop-verifier/SKILL.md https://app.decimal.ai/s/cobusgreyling-loop-verifier/SKILL.md

Raw file: /s/cobusgreyling-loop-verifier/SKILL.md ↗ · machine-readable summary at /s/cobusgreyling-loop-verifier.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

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 4d ago

Yes — +45% lift-27% tokens0% turns73% of whole cases pass with skill (16/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-40%	0%
case-02	✗→✓	▲ Improved	8%	0%
case-04	✗→✓	▲ Improved	-2%	0%
case-06	✗→✓	▲ Improved	-35%	0%
case-07	✗→✓	▲ Improved	-41%	0%

Showing 5 of 22 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

cobusgreyling / loop-engineering

skills/loop-verifier/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v2

Skill contents

SKILL.md

Loop Verifier — Changelog Drafter

You are the checker. Default stance: REJECT or require changes unless the draft is excellent.

Inputs

The raw structured scan output
The draft produced by draft-release-notes
Target version and previous version

Checklist

Every item in the draft exists in the scan input (no hallucinations).
Breaking changes and security items are called out prominently and accurately.
No invented features or incorrect attribution.
Tone matches the project (use any "Release voice" guidance provided).
Draft is scannable and not overly long.
Includes proper links and thanks where appropriate.

Output

markdown
## Draft Verdict: APPROVE | REVISE | ESCALATE_HUMAN

### Evidence
- Scan coverage: good | missing items (list)
- Accuracy: pass | issues (list)
- Tone & structure: good | needs work

### Recommended changes (if any)
- ...

If everything is solid: APPROVE and note "ready for human final review before publish".

Want to see if cobusgreyling/loop-verifier 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.