Ready to supercharge your AI agents?

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

Get Started Free →

Review — measured AI agent skill | DecimalAI

hmbown/review

NewSkillScoreMaintained

Read-only correctness review with actionable findings first, tight file/line evidence, severity, and a concise residual-risk summary.

by hmbown

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

Automatic

Coding pack

decimalai skills pull hmbown-review

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/hmbown-review/SKILL.md

Raw file: /s/hmbown-review/SKILL.md ↗ · machine-readable summary at /s/hmbown-review.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 22h ago

Yes — +5% lift-3% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	27%	0%
case-01	✓→✓	＝ Same ✓	36%	0%
case-02	✓→✓	＝ Same ✓	97%	0%
case-03	✓→✓	＝ Same ✓	-23%	0%
case-05	✓→✓	＝ Same ✓	-17%	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

hmbown / codewhale

crates/tui/assets/skills/review/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Review

When to use

Use for correctness review of a diff, PR, or named change set.

Non-goals

Read-only by default. Do not edit unless asked.
Do not bury findings under style nits.

Workflow

Establish the change scope.
List findings by severity with file/line evidence.
Call out residual risk and missing tests.
End with a short merge/risk summary.

Want to see if hmbown/review 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.