doc — community rs_trader, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Perfect for Developer Agents needing automated documentation generation for specs and codebases. Tarding Platform

pcortellezzi pcortellezzi
[0]
[1]
Updated: 2/21/2026

Agent Capability Analysis

The doc skill by pcortellezzi is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Perfect for Developer Agents needing automated documentation generation for specs and codebases.

Core Value

Empowers agents to regenerate documentation pages based on current specs and codebase, targeting specific sections or entire guides, using arguments like 'user' or 'dev' to specify regeneration scope, and supporting protocols like command-line interfaces.

Capabilities Granted for doc

Regenerating user guide pages for updated features
Updating developer guide pages for new architecture
Automating documentation for specific tools or charts

! Prerequisites & Limits

  • Requires specification of target section or guide via $ARGUMENTS
  • Limited to regeneration of existing documentation structure
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

doc

Install doc, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Documentation Generator

Generates or updates documentation pages based on the current specs and codebase. Can target specific sections or regenerate everything.

Argument

$ARGUMENTS specifies what to generate. Examples:

  • user — regenerate all user guide pages
  • dev — regenerate all developer guide pages
  • user/chart — regenerate chart-related user pages
  • user/tools — regenerate drawing tools pages
  • dev/architecture — regenerate the architecture page
  • all — regenerate everything
  • (empty) — show current doc coverage status

Procedure

1. If no argument: show doc coverage

List all pages in docs/src/SUMMARY.md and check which files exist and which are missing or empty.

Report format:

=== DOCUMENTATION COVERAGE ===

User Guide:
  ✅ user/getting_started.md (exists, 45 lines)
  ✅ user/chart/navigation.md (exists, 62 lines)
  ⚠️  user/chart/multi_pane.md (empty or missing)

Dev Guide:
  ✅ dev/architecture.md (exists, 180 lines)
  ⚠️  dev/plugin_guide.md (empty or missing)

Coverage: 28/35 pages present (80%)

2. If argument provided: generate pages

For each page in scope:

a. Identify the spec source: find the matching spec file(s) in specs/ b. Read the spec: extract behaviors, states, descriptions c. Read the current code: understand what's actually implemented d. Write the doc page:

  • User pages: plain language, no code, explain what and how to use. Add > Spec source: specs/... at the bottom.
  • Dev pages: technical language, code examples, architecture diagrams. Reference actual crate names and trait names. e. Verify: run mdbook build docs to check for broken links or formatting errors

3. Update SUMMARY.md if needed

If new pages were created that aren't in SUMMARY.md, add them in the appropriate section.

4. Final verification

bash
1mdbook build docs

Report any build errors.

Rules

  • User docs are for non-developers — no Rust code, no technical jargon
  • Dev docs are for Rust developers — include code snippets, API references, trait names
  • Always reference the spec source at the bottom of user pages
  • Language: English only
  • Do not invent features — only document what exists in specs or code
  • Build must pass after changes

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is doc?

Perfect for Developer Agents needing automated documentation generation for specs and codebases. Tarding Platform

How do I install doc?

Run the command: npx killer-skills add pcortellezzi/rs_trader/doc. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for doc?

Key use cases include: Regenerating user guide pages for updated features, Updating developer guide pages for new architecture, Automating documentation for specific tools or charts.

Which IDEs are compatible with doc?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for doc?

Requires specification of target section or guide via $ARGUMENTS. Limited to regeneration of existing documentation structure.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add pcortellezzi/rs_trader/doc. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use doc immediately in the current project.

Related Skills

Looking for an alternative to doc or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI