Ready to supercharge your AI agents?

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

Get Started Free →

Agent Sh/With Model — measured AI agent skill | DecimalAI

agent-sh/with-model

SkillScore95Maintained

Use when testing valid model configuration

by agent-sh

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

Automatic

AI Engineer pack

decimalai skills pull agent-sh-with-model

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/agent-sh-with-model/SKILL.md

Raw file: /s/agent-sh-with-model/SKILL.md ↗ · machine-readable summary at /s/agent-sh-with-model.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-62% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	-61%	0%
case-16	✗→✓	▲ Improved	-18%	0%
case-03	✗→✓	▲ Improved	-64%	0%
case-06	✗→✓	▲ Improved	-77%	0%
case-07	✗→✓	▲ Improved	-86%	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/valid/skills/with-model/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/1/2026Version v1

Skill contents

SKILL.md

This skill has a valid model value. Valid models are: sonnet, opus, haiku, inherit.

Want to see if agent-sh/with-model 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.