.claude/skills/docs/SKILL.md
Project documentation structure and configured paths. Use when creating or updating docs, locating where plans/reports/issues/architecture docs live, or understanding the documentation layout configured in .cursor/config.json. Do NOT use for code implementation or code review.
npx skillsauth add softmg/product-tracker docsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
IMPORTANT: Documentation paths are configured in .cursor/config.json. Never hardcode ai_docs/ or any specific paths.
Always read documentation paths from config:
config = readJSON(".cursor/config.json")
paths = config.documentation.paths
// paths.root = "ai_docs" (or user's custom path)
// paths.plans = "ai_docs/develop/plans"
// paths.reports = "ai_docs/develop/reports"
// etc.
This is the default structure when using ai_docs/ as root (users can customize all paths):
{configured-root}/ # From config: paths.root
├── design/ # From config: paths.design
├── develop/
│ ├── api/ # From config: paths.api
│ ├── architecture/ # From config: paths.architecture
│ ├── components/ # From config: paths.components
│ ├── features/ # From config: paths.features
│ ├── plans/ # From config: paths.plans
│ ├── reports/ # From config: paths.reports
│ └── issues/ # From config: paths.issues
└── changelog/ # From config: paths.changelog
plans/ - High-level: What to build (created by planner) reports/ - Summary: What was built (created by documenter) issues/ - Tech debt: What to fix later (created by any agent) features/ - Feature descriptions and implementation details api/ - API endpoints documentation components/ - Component documentation architecture/ - Architecture decisions and patterns design/ - UI/UX designs, style guides changelog/ - Version history
/documenter update docs for [feature]Read documentation files directly using the configured paths from config.json.
To access specific docs (replace {root} with your configured path):
{root}/develop/features/authentication.md
{root}/develop/api/endpoints.md
/documenter - Update documentation for recent changesfeature-name.md (kebab-case)ComponentName.md (PascalCase)issue-123.md or descriptive nametask-description.mdExample .cursor/config.json:
{
"documentation": {
"paths": {
"root": "ai_docs",
"plans": "ai_docs/develop/plans",
"reports": "ai_docs/develop/reports",
"issues": "ai_docs/develop/issues",
"architecture": "ai_docs/develop/architecture",
"features": "ai_docs/develop/features",
"api": "ai_docs/develop/api",
"components": "ai_docs/develop/components",
"design": "ai_docs/design",
"changelog": "ai_docs/changelog"
},
"enabled": {
"plans": true,
"reports": true,
"issues": true,
"architecture": true,
"features": true,
"api": true,
"components": true,
"design": true,
"changelog": true
}
}
}
Users can customize all paths to match their project structure (e.g., docs/, documentation/, etc.)
documentation
Task tracking and plan management. Used by planner to create plans and persist tasks, by orchestrator to read tasks and update progress, by documenter to create completion reports, and by any agent to log non-critical issues.
development
Create, edit, evaluate, and package agent skills. Use when building a new skill from scratch, improving an existing skill, running evals to test a skill, benchmarking skill performance, optimizing a skill's description for better triggering, reviewing third-party skills for quality, or packaging skills for distribution. Not for using skills or general coding tasks.
development
Simple implementation workflow - code, test, document. Use when user invokes /implement, wants to create code with automatic testing and documentation, or for simple single-purpose tasks that don't need planning.
development
Security best practices covering authentication, input validation, API security, secrets management, data protection, and OWASP Top 10. Use when implementing auth flows, API endpoints, file uploads, or any feature touching passwords, tokens, PII, or sensitive data. Do NOT use for code style reviews or architecture decisions.