Ready to supercharge your AI agents?

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

MCP Documentation Conventions — measured AI agent skill | DecimalAI

pradeepmouli/skillit-mcp-docs

SkillScore91Maintained

MCP server documentation conventions for high-quality generated skills. Use when writing tool descriptions, `_meta` annotations, or input schemas for MCP extraction.

by pradeepmouli

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

Automatic

Doc Ops pack

decimalai skills pull pradeepmouli-skillit-mcp-docs

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/pradeepmouli-skillit-mcp-docs/SKILL.md

Raw file: /s/pradeepmouli-skillit-mcp-docs/SKILL.md ↗ · machine-readable summary at /s/pradeepmouli-skillit-mcp-docs.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 — +55% lift-15% tokens0% turns91% of whole cases pass with skill (20/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-03	✗→✓	▲ Improved	122%	0%
case-04	✗→✓	▲ Improved	-22%	0%
case-01	✗→✓	▲ Improved	5%	0%
case-02	✗→✓	▲ Improved	-33%	0%
case-06	✗→✓	▲ Improved	-64%	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

pradeepmouli / skillit

packages/mcp/skills/skillit-mcp-docs/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1

Skill contents

SKILL.md

MCP Documentation Conventions

Use this skill when documenting MCP servers for @skillit/mcp.

Focus Areas

Tool descriptions that explain purpose and invocation scenarios
Flat _meta string fields — useWhen, avoidWhen, never, remarks, example
Parameter and schema descriptions that explain valid inputs and effects
Stable, specific tool names instead of generic verbs

Fix Patterns

Add one-sentence tool descriptions with when-to-call guidance
Set _meta.useWhen = "[scenario]" directly on the tool's _meta — not nested under a toSkills key, and not an array
Document each schema property with the effect on server behavior
Prefer names like read_project_file over get

Want to see if pradeepmouli/skillit-mcp-docs 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.