Ready to supercharge your AI agents?

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

Get Started Free →

warn-only — measured AI agent skill | DecimalAI

ai-creed/warn-only

SkillScore100Maintained

Use when testing warning-only exit code behavior.

by ai-creed

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

Automatic

QA & Test Engineering pack

decimalai skills pull ai-creed-warn-only

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/ai-creed-warn-only/SKILL.md

Raw file: /s/ai-creed-warn-only/SKILL.md ↗ · machine-readable summary at /s/ai-creed-warn-only.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 6d ago

Yes — +50% lift-64% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	15%	0%
case-02	✗→✓	▲ Improved	28%	0%
case-03	✗→✓	▲ Improved	-24%	0%
case-07	✗→✓	▲ Improved	-80%	0%
case-11	✗→✓	▲ Improved	-83%	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 — 8/1/2026

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

ai-creed / ai-shakespii

tests/fixtures/warn-only/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

warn-only

Intent

Control fixture: exactly one warning (FM01 unknown field), exit 0.

Inputs

None — the fixture is static.

Preconditions

None — no external dependencies.

Procedure

Lint this directory and expect one warning.

Output

A findings list with a single FM01 warning.

Examples

Given the input shakespii lint tests/fixtures/warn-only, the expected output is one warning and exit code 0.

Anti-patterns

Adding a second unknown field — the CLI test locks the count at one.

Want to see if ai-creed/warn-only 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.