Ready to supercharge your AI agents?

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

skillit-refine — measured AI agent skill | DecimalAI

pradeepmouli/skillit-refine

SkillScore100Maintained

Autonomously improve an MCP skill via the skillit audit→draft→review loop (build or runtime mode) Also: skillit, refine, mcp, skill-generation, cli, audit, overlay.

by pradeepmouli

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

Automatic

AI Engineer pack

decimalai skills pull pradeepmouli-skillit-refine

Get this skill — curl · raw file

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

Raw file: /s/pradeepmouli-skillit-refine/SKILL.md ↗ · machine-readable summary at /s/pradeepmouli-skillit-refine.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 7d ago

—-33% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-49%	0%
case-02	✗→✓	▲ Improved	-3%	0%
case-03	✗→✓	▲ Improved	211%	0%
case-08	✗→✓	▲ Improved	-40%	0%
case-07	✗→✓	▲ Improved	-38%	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

skills/skillit-refine/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1Bundled 1 file

Skill contents

references/

SKILL.md

skillit-refine

Autonomously improve an MCP skill via the skillit audit→draft→review loop (build or runtime mode)

Commands

refine

Autonomously improve a skill via the audit→draft→review loop

Usage:

[options]

| Flag | Type | Required | Default | Env | Description | | ------------------ | -------- | -------- | ------- | --- | --------------------------------------------------------- | | --mcp | string | yes | — | — | path to mcp.json or MCP config file | | --server | string | no | — | — | server name within the config (defaults to first enabled) | | --overlay | string | no | — | — | path to overlay JSON file (runtime mode only) | | --mode | string | no | — | — | refine mode: build or runtime (auto-detected if omitted) | | --source-glob | string | no | — | — | glob pattern for TypeScript source files (build mode) | | --max-iterations | string | no | 5 | — | iteration cap (default 5) | | --items | string | no | 5 | — | work items per iteration (default 5) |

References

Load these on demand — do NOT read all at once:

When using CLI commands → read references/commands.md for flags, arguments, and defaults