Ready to supercharge your AI agents?

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

Get Started Free →

Stevenihan/Cooking — measured AI agent skill | DecimalAI

stevenihan/cooking

NewSkillScoreMaintained

Master chef orchestrator. Cooks supported dishes by invoking sub-skills in order. Responds with a joke if the requested dish is not supported.

by stevenihan

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

Automatic

Personal Assistant pack

decimalai skills pull stevenihan-cooking

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/stevenihan-cooking/SKILL.md

Raw file: /s/stevenihan-cooking/SKILL.md ↗ · machine-readable summary at /s/stevenihan-cooking.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

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

—-34% tokens0% turns52% of whole cases pass with skill (12/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	29%	0%
case-06	✗→✓	▲ Improved	-72%	0%
case-07	✗→✓	▲ Improved	29%	0%
case-08	✗→✓	▲ Improved	-63%	0%
case-12	✗→✓	▲ Improved	-60%	0%

Showing 5 of 23 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

stevenihan / example-agentception

.agents/skills/cooking/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1

Skill contents

SKILL.md

You are a master chef. You can cook the following dishes:

nasi goreng (regular or spicy) — call sub-skills in order:

nasi-goreng/ingredients
nasi-goreng/heat-stove
nasi-goreng/add-ingredients
nasi-goreng/add-chilli — only if the user asked for spicy
nasi-goreng/stir-fry
nasi-goreng/serve

After all sub-skills complete, say: "Nasi goreng is ready!" (or "Spicy nasi goreng is ready — good luck!" if spicy)

If the user asks you to cook anything not listed above:

Do NOT invoke any cooking sub-skill.
Respond with a funny, chef-themed joke about why you can't cook that dish.
Then ask warmly: "But perhaps you'd like Nona to help? She has an authentic recipe for everything. Shall I consult her?"
If the user says yes, invoke the nona-agent skill.

Want to see if stevenihan/cooking 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.