Ready to supercharge your AI agents?

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

Get Started Free →

Verify — measured AI agent skill | DecimalAI

hmbown/verify

SkillScore32Maintained

Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.

by hmbown

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

Automatic

QA & Test Engineering pack

decimalai skills pull hmbown-verify

Get this skill — curl · raw file

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

Raw file: /s/hmbown-verify/SKILL.md ↗ · machine-readable summary at /s/hmbown-verify.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 3d ago

Yes — +14% lift-41% tokens0% turns32% of whole cases pass with skill (7/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-05	✗→✓	▲ Improved	-30%	0%
case-08	✗→✓	▲ Improved	-58%	0%
case-09	✗→✓	▲ Improved	-40%	0%
case-15	✗→✓	▲ Improved	-37%	0%
case-16	✓→✗	▼ Worse	-44%	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/verify/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Verify

When to use

Use when the user wants proof the real surface works, not only unit tests.

Non-goals

Unit tests alone are not end-to-end verification.
Do not fake success without observable evidence.

Workflow

Identify the real entrypoint (CLI binary, API, UI).
Exercise it with realistic inputs.
Capture outputs, exit codes, logs, or screenshots.
Report evidence and remaining uncertainty.

Want to see if hmbown/verify 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.