Ready to supercharge your AI agents?

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

Get Started Free →

skillit · pradeepmouli | DecimalAI

agent toolingby pradeepmouli

skillit

pradeepmouli/skillit

Source pradeepmouli/skillit ↗License MIT

Generate structured AI agent skills (SKILL.md) and llms.txt from your TypeScript API documentation

SkillScore100Maintained

Automatic

AI Engineer pack

Last verified 8/3/2026

What it changes

Passed 22 of 22 test cases with the skill, and 5 of 22 without it.

Without skill23%

With skill100%

Checks it passed that the model alone missed

Uses introspectCommander for Commander programs.
Invokes extractCliSkill in the extraction script.
Uses parseHelpOutput to parse raw help text dumps.

and 21 more in the full report

17 fixed5 passed either way0 still failing0 broke

Pass-rate lift: +77 pp
Tokens: -45%
Agent turns: 0%
Response time: -70%

Model gemini-3.6-flashMeasured 8/3/2026v122 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/pradeepmouli-skillit/SKILL.md https://app.decimal.ai/s/pradeepmouli-skillit/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add pradeepmouli-skillit, 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/pradeepmouli-skillit/ and pins it in .decimal/skills.lock

decimalai skills add pradeepmouli-skillit

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

curl -fsSL --create-dirs -o .claude/skills/pradeepmouli-skillit/SKILL.md https://app.decimal.ai/s/pradeepmouli-skillit/SKILL.md

Raw file: /s/pradeepmouli-skillit/SKILL.md ↗ · machine-readable summary at /s/pradeepmouli-skillit.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 17

Prompt

What TypeScript type name defines the parameter shape containing optional program, helpTexts, metadata, and configSurfaces fields?

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies CliExtractionOptions as the interface name.	Missed	Passed

case-17 · 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.md47 lines4 files

skillit

Generate structured AI agent skills (SKILL.md) and llms.txt from your TypeScript API documentation

When to Use

You have a Commander program and want structured option/argument extraction with full fidelity
Runtime introspection is unavailable (no access to the program object)
The CLI uses a framework other than Commander (yargs, oclif, custom)
You have both CLI surfaces (from introspection/help) and typed config interfaces (from TypeDoc)
You want JSDoc @useWhen/@avoidWhen/@never tags to appear on CLI options in the generated skill
You have a Commander program and want to generate a skill from its command structure
You have raw --help output and no runtime access to the program object

Avoid when:

Your CLI uses yargs, oclif, or another framework — use parseHelpOutput as a fallback instead
Your CLI is built with a framework other than Commander — use parseHelpOutput directly instead
API surface: 4 functions

NEVER

NEVER pass both program and helpTexts — program takes precedence and helpTexts is silently ignored
NEVER forget to pass configSurfaces when you have typed option interfaces — JSDoc metadata won't be correlated

Configuration

CliExtractionOptions

Key	Type	Required	Default	Description
`program`	`any`	no	—	Commander program object (preferred)
`helpTexts`	`Record<string, string>`	no	—	Help text per command (fallback)
`metadata`	`{ name?: string; description?: string; keywords?: string[]; repository?: string; author?: string }`	no	—	Package metadata
`configSurfaces`	`ExtractedConfigSurface[]`	no	—	Config surfaces from TypeDoc for JSDoc correlation

Quick Reference

Commander: introspectCommander Fallback: parseHelpOutput

Track record

Benchmark

22 / 22

test cases passed, vs 5 / 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

pradeepmouli / skillit

skills/skillit/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version v1Bundled 3 files

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

pradeepmouli/skillit-cliExtract CLI command structure from commander/yargs for AI agent skill generation Use when working with agent-skills, cli, commander, documentation, skill-generation, yargs.Close match+74 pp pass-rate lift

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

Ready to supercharge your AI agents?

See it in action

What's inside

skillit

When to Use

NEVER

Configuration

CliExtractionOptions

Quick Reference

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills