generate-skill

A command that creates project-specific agent skills from a project's official documentation. Agent skills are reference files that help an AI coding assistant work with a framework or tool.

In plain words
What is it for?
Use it for projects using Vue, Nuxt, Vite, UnoCSS, pnpm, Pinia, Vitest, or VitePress, when you want skills generated from their documentation.
Why use it?
It saves the work of manually reading documentation and turning it into structured skill files. It also records the source and generation details for each set of skills.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/pleaseai/claude-code-plugins/generate-skill
Clone the repo
git clone --depth 1 https://github.com/pleaseai/claude-code-plugins

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 566 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00035 $0.00566
Opus 5 $0.00017 $0.00283
Sonnet 5 $0.00007 $0.00113
Haiku 4.5 $0.00003 $0.00057

Measured 2d ago against content hash 8a68b1ba67cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

generate-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/generate-skill.md · 45 lines

What it actually says

Generate agent skills for the project: $ARGUMENTS

Follow the guidelines in docs/skills-generator.md to generate Type 1 skills.

Steps

  1. Read docs/skills-generator.md for the full generation guidelines
  2. Check vendor/antfu-skills/instructions/$ARGUMENTS.md for project-specific instructions (if it exists)
  3. Read source docs from sources/$ARGUMENTS/docs/
  4. Generate skill files into skills/$ARGUMENTS/:
    • SKILL.md — index with frontmatter (name, description, metadata) and a table of all references
    • GENERATION.md — tracking metadata (source path, git SHA, generation date)
    • references/*.md — one file per concept (prefixed by category, e.g. core-syntax.md, features-plugins.md)
  5. Copy the generated skills into the plugin directory:
    mkdir -p "plugins/$ARGUMENTS/skills/$ARGUMENTS/" && cp -r "skills/$ARGUMENTS/." "plugins/$ARGUMENTS/skills/$ARGUMENTS/"
    

    Note: bun run skills:sync only handles Type 2 (vendor) and Type 3 (manual) skills. Type 1 (generated) skills must be copied manually to the plugin directory.

  6. Commit the generated skills:
    git add skills/$ARGUMENTS/ plugins/$ARGUMENTS/skills/$ARGUMENTS/
    git commit -m "feat($ARGUMENTS): generate skills from official documentation"
    

Output Location

  • Source docs: sources/$ARGUMENTS/ (submodule, run bun scripts/cli.ts init if missing)
  • Generated skills: skills/$ARGUMENTS/ (our own skills directory, never modify vendor/antfu-skills/)
  • Synced to plugin: plugins/$ARGUMENTS/skills/$ARGUMENTS/

Writing Guidelines

  • Rewrite docs for agents — synthesize, don't copy verbatim
  • Focus on practical usage patterns and code examples
  • Omit installation guides, introductions, and content agents already know well
  • One concept per reference file
  • Include working code examples
  • Explain when and why to use each feature, not just how
  • Keep each reference file concise (under 200 lines)
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 45 lines · 35 tokens per session scan A 8a68b1ba67cb

Subscribe to this mod's changes

generate-skill is a command published in the GitHub repository pleaseai/claude-code-plugins (13 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 566 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.