Ready to supercharge your AI agents?

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

Get Started Free →

Unknown Tool Skill · agent-sh | DecimalAI

Registry skillby agent-sh

Unknown Tool Skill

agent-sh/unknown-tool-skill

Source agent-sh/agnix ↗License Apache-2.0

Use when testing unknown tool validation

SkillScore95Maintained

Automatic

Coding pack

Last verified 8/3/2026

What it changes

Passed 21 of 22 test cases with the skill, and 15 of 22 without it.

Without skill68%

With skill95%

Checks it passed that the model alone missed

The response recommends declaring standard tool names Read and Grep.
The response identifies Read as the standard built-in tool for reading file contents.
The response identifies Task as the standard built-in tool for delegating sub-agent tasks.

and 4 more in the full report

7 fixed14 passed either way0 still failing1 broke

Pass-rate lift: +27 pp
Tokens: -51%
Agent turns: 0%
Response time: -51%

Model gemini-3.6-flashMeasured 8/3/2026v121 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/agent-sh-unknown-tool-skill/SKILL.md https://app.decimal.ai/s/agent-sh-unknown-tool-skill/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add agent-sh-unknown-tool-skill, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/agent-sh-unknown-tool-skill/ and pins it in .decimal/skills.lock

decimalai skills add agent-sh-unknown-tool-skill

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/agent-sh-unknown-tool-skill/SKILL.md https://app.decimal.ai/s/agent-sh-unknown-tool-skill/SKILL.md

Raw file: /s/agent-sh-unknown-tool-skill/SKILL.md ↗ · machine-readable summary at /s/agent-sh-unknown-tool-skill.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 7

Prompt

Can you review my agent configuration file to make sure all declared tool references match standard supported built-in actions?

What was checked, without and with the skill
Checked	Without skill	With skill
The response identifies Bash, Edit, Read, Write, Grep, Glob, and Task as standard built-in tool names.	Missed	Passed

case-01 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md2 linessingle file

This skill references unknown tools. Tools must be known Claude Code tools: Bash, Read, Write, Edit, Grep, Glob, Task, etc.

Track record

Benchmark

21 / 22

test cases passed, vs 15 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

View 15 scanner checks

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/invalid/skills/unknown-tool/SKILL.md

View on GitHub ↗

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

More skills from the same source and nearby in the registry, with their headline benchmark lift.