Ready to supercharge your AI agents?

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

Get Started Free →

WS-SK-001 Test Fixture — measured AI agent skill | DecimalAI

agent-sh/test-skill

SkillScore100Maintained

Use when testing per-client skill rules

by agent-sh

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

Automatic

QA & Test Engineering pack

decimalai skills pull agent-sh-test-skill

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/agent-sh-test-skill/SKILL.md

Raw file: /s/agent-sh-test-skill/SKILL.md ↗ · machine-readable summary at /s/agent-sh-test-skill.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 — +64% lift-69% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-09	✗→✓	▲ Improved	-89%	0%
case-01	✗→✓	▲ Improved	67%	0%
case-02	✗→✓	▲ Improved	23%	0%
case-03	✗→✓	▲ Improved	-43%	0%
case-06	✗→✓	▲ Improved	-63%	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

agent-sh / agnix

tests/fixtures/per_client_skills/.agents/skills/test-skill/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/1/2026Version v8

Skill contents

SKILL.md

WS-SK-001 Test Fixture

This skill has a field unsupported by Windsurf (user-invocable). The WS-SK-001 rule should flag this field.

Want to see if agent-sh/test-skill 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.