Bootstraps documentation structure for projects. Creates initial README, architecture docs, and API documentation with project-aware templates.
Creates initial documentation structure with project-aware templates for README, architecture, and API documentation.
/plugin marketplace add datamaker-kr/synapse-claude-marketplace/plugin install platform-dev-team-common@synapse-marketplaceThis skill is limited to using the following tools:
README.mdtemplates/README.template.mdtemplates/api.template.mdtemplates/architecture.template.mdThis skill creates initial documentation structure for projects that lack proper documentation. It detects project type and generates appropriate documentation templates, including README, architecture overview, and API documentation.
Use this skill when:
Before bootstrapping, verify what documentation already exists:
Check for:
Decision:
Analyze the codebase to determine project type and technology stack.
Django:
manage.py, settings.py, requirements.txt with DjangoFastAPI:
main.py, requirements.txt with fastapiExpress:
package.json with express, app.js or server.jsNestJS:
nest-cli.json, package.json with @nestjsFlask:
app.py, requirements.txt with flaskSpring Boot:
pom.xml or build.gradle, Application.javaReact:
package.json with react, .jsx or .tsx filesVue:
package.json with vue, vue.config.js, .vue filesAngular:
angular.json, package.json with @angularNext.js:
next.config.js, pages/ directorySvelte:
svelte.config.js, .svelte filesIndicators:
apps/, packages/, workspaces)Terraform:
.tf filesKubernetes:
.yaml files with kind:, apiVersion:Docker:
Dockerfile, docker-compose.ymlAnsible:
playbook.yml, ansible.cfgPython Package:
setup.py, pyproject.toml without web frameworkJavaScript/TypeScript Library:
package.json with "main" field, no web frameworkRust Crate:
Cargo.toml, src/lib.rsGo Package:
go.mod, package structureDetection Method:
# Use Glob to find indicator files
Glob: "manage.py" # Django
Glob: "main.py" # FastAPI
Glob: "package.json" # Node.js
# Use Read to check file contents
Read: "package.json" # Check dependencies
# Use Grep to find specific patterns
Grep: pattern="from django" glob="*.py" # Django imports
Grep: pattern="from fastapi" glob="*.py" # FastAPI imports
Create comprehensive README based on project type using template.
README Sections (adapt based on project type):
Project Header
Overview
Installation
Usage
Project Structure
Development
API Documentation (for backend projects)
Deployment (if applicable)
Contributing
License
Use template: templates/README.template.md with placeholders replaced
Generate standard documentation directory:
docs/
├── architecture.md
├── api.md (for backend/full-stack)
└── .gitkeep (if empty)
Create architecture documentation using template.
Architecture Sections (adapt based on project type):
System Overview
Architecture Diagram (Mermaid placeholder)
Components
Data Flow
Technology Stack
Design Decisions
Use template: templates/architecture.template.md
Create API documentation template.
API Documentation Sections:
Overview
Authentication
Endpoints
Error Handling
Rate Limiting (if applicable)
Use template: templates/api.template.md
Generate directory tree for README using Bash:
# Generate tree (if tree command available)
tree -L 3 -I 'node_modules|__pycache__|*.pyc|.git'
# Or use find
find . -type d -maxdepth 3 | grep -v node_modules | grep -v __pycache__
Insert into README.md
Replace template placeholders with detected values:
Replacements:
{{PROJECT_NAME}}: From directory name, package.json, setup.py{{DESCRIPTION}}: Placeholder or from package.json{{FRAMEWORK}}: Detected framework (Django, React, etc.){{LANGUAGE}}: Detected language (Python, JavaScript, etc.){{INSTALL_COMMAND}}: Framework-specific (pip install, npm install){{RUN_COMMAND}}: Framework-specific (python manage.py runserver, npm start){{TEST_COMMAND}}: Framework-specific (pytest, npm test)After creating files, report to user:
# Documentation Bootstrap Complete ✅
## Created Files
- README.md (X lines)
- docs/architecture.md (Y lines)
- docs/api.md (Z lines) [if applicable]
## Project Type Detected
- Type: [Django Backend / React Frontend / etc.]
- Framework: [framework name]
- Language: [language]
## Next Steps
1. Review generated documentation
2. Fill in placeholders marked with [PLACEHOLDER] or {{VARIABLE}}
3. Add project-specific details
4. Update Mermaid diagrams with actual architecture
5. Add real API endpoint examples
## Customization Needed
- [ ] Add project description in README.md
- [ ] Fill technology stack details
- [ ] Add real API endpoints in docs/api.md
- [ ] Update architecture diagram
- [ ] Add deployment instructions
- [ ] Update environment variables
Templates are located in skills/docs-bootstrapper/templates/:
Templates use placeholders:
{{VARIABLE}}: Auto-replaced with detected values[PLACEHOLDER]: User must fill in[OPTIONAL]: Optional section, can be removedScenario 1: New Django Project
User: /docs-bootstrapper
docs-bootstrapper:
Checking existing documentation...
No comprehensive docs found.
Detecting project type...
✓ Detected: Django Backend
✓ Framework: Django 4.2 + DRF
✓ Database: PostgreSQL (from settings)
Creating documentation...
✓ README.md created (180 lines)
✓ docs/architecture.md created (120 lines)
✓ docs/api.md created (90 lines)
Bootstrap complete! Review and customize generated docs.
Scenario 2: React Project
User: Bootstrap documentation for this React app
docs-bootstrapper:
Detecting project type...
✓ Detected: React Frontend
✓ Framework: React 18 + TypeScript
✓ State: Redux Toolkit
Creating documentation...
✓ README.md created (160 lines)
✓ docs/architecture.md created (100 lines)
Bootstrap complete! Frontend project detected, no API docs generated.
Can be invoked directly when starting new projects:
User: /docs-bootstrapper
Skill: Detects project, creates comprehensive documentation structure
Or called by docs-manager when gap analysis shows no docs exist.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Search, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.