Agent skill
project-planning
Generate initial project planning documents (PVS, ADR, Tech Spec, Roadmap) from a project concept description. Use when starting a new project, when docs/planning/ contains placeholder files, or when user requests project planning document generation.
Install this agent skill to your Project
npx add-skill https://github.com/aiskillstore/marketplace/tree/main/skills/byronwilliamscpa/project-planning
SKILL.md
Project Planning Skill
Generate four essential planning documents to guide AI-assisted development. These documents maintain context coherence across coding sessions and prevent architectural drift.
When to Use This Skill
- User describes a project concept and asks for planning documents
- Files in
docs/planning/show "Awaiting Generation" status - User invokes
/plancommand with project description - Starting development on a new feature requiring architectural decisions
Output Documents
| Document | Location | Purpose |
|---|---|---|
| Project Vision & Scope | docs/planning/project-vision.md |
What & Why - problem, solution, scope |
| Technical Spec | docs/planning/tech-spec.md |
How - architecture, data model, APIs |
| Development Roadmap | docs/planning/roadmap.md |
When - phased implementation plan |
| Architecture Decision Record | docs/planning/adr/adr-001-*.md |
Key technical decisions with rationale |
Generation Process
Step 1: Gather Project Context
Before generating, collect:
- Project description from user input
- Technical constraints from
pyproject.tomland existing code - Cookiecutter choices reflected in project structure
Step 2: Generate Documents in Order
Generate documents sequentially, as later documents reference earlier ones:
- Project Vision & Scope - Establishes what we're building and why
- Architecture Decision Record - Key technical choices based on PVS
- Technical Implementation Spec - Detailed how-to based on ADRs
- Development Roadmap - Implementation plan based on all above
Step 3: Expert Review via Consensus
After generating each document, use the zen-mcp-server consensus tool to get expert review:
Use mcp__zen__consensus with gemini-3-pro-preview to review:
"Review this [document type] for sufficiency to begin development.
Evaluate:
1. SPECIFICITY: Are requirements concrete enough to implement?
2. COMPLETENESS: Are all critical sections filled with project-specific content?
3. FEASIBILITY: Are timelines and technical choices realistic?
4. CLARITY: Can a developer understand what to build from this?
5. GAPS: What critical information is missing?
Respond with:
- READY: Document is sufficient to begin work
- NEEDS REVISION: [List specific improvements required]
Document content:
[paste document content]"
Review each document in order:
- PVS → Must be READY before generating ADR
- ADR → Must be READY before generating Tech Spec
- Tech Spec → Must be READY before generating Roadmap
- Roadmap → Must be READY before completing
If any document NEEDS REVISION, incorporate feedback and re-review before proceeding.
Step 4: Validate and Cross-Reference
After all documents pass review:
- Ensure documents reference each other correctly
- Verify technical choices are consistent across documents
- Flag any assumptions needing user validation
- Run validation script if available
Document Generation Guidelines
All Documents
- Be specific: Use concrete technologies, versions, and measurable criteria
- No boilerplate: Every section must contain project-specific information
- Under 1000 words: Dense information, minimal prose
- Markdown format: Use headers, bullets, tables for structure
- Include TL;DR: 2-3 sentence summary at top of each document
Project Vision & Scope (PVS)
Use template: templates/pvs-template.md
Focus on:
- Problem being solved and user impact
- Core capabilities (3-5 max for MVP)
- Explicit scope boundaries (in vs out)
- Measurable success metrics
Architecture Decision Record (ADR)
Use template: templates/adr-template.md
Create ADR for:
- Database/storage choice
- Authentication strategy
- API design approach
- Key framework decisions
- Any choice expensive to reverse
Format: adr-001-{decision-slug}.md
Technical Implementation Spec
Use template: templates/tech-spec-template.md
Include:
- Complete tech stack with versions
- Component architecture diagram (ASCII)
- Data model with schemas
- API endpoints specification
- Security requirements
- Error handling approach
Development Roadmap
Use template: templates/roadmap-template.md
Structure as:
- Phase 0: Foundation (environment, CI/CD)
- Phase 1: MVP Core (essential features)
- Phase 2: Enhancement (additional features)
- Phase 3: Polish (testing, documentation)
Each phase needs:
- Clear deliverables
- Success criteria (testable)
- Estimated duration
- Dependencies
Pre-Filling from Project Context
When generating, incorporate known information:
# From pyproject.toml / cookiecutter context
python_version = "3.12"
project_name = "Fragrance Rater"
project_slug = "fragrance_rater"
cli_framework = "Click"
containerization = "Docker"
Quality Checklist
Before completing generation:
- All four documents created in
docs/planning/ - Each document has TL;DR section
- No "[TODO]" or "[TBD]" placeholders remain
- Documents cross-reference each other
- Technical choices are consistent
- Success criteria are measurable
- Scope boundaries are explicit
- At least one ADR created
Templates Reference
Templates are in templates/ directory:
pvs-template.md- Project Vision & Scope structureadr-template.md- Architecture Decision Record structuretech-spec-template.md- Technical Spec structureroadmap-template.md- Development Roadmap structure
Detailed Guidance
For comprehensive documentation on each document type, see reference/ directory:
reference/document-guide.md- Full guidance for all document typesreference/prompting-patterns.md- How to use documents during development
After Generation
Instruct user to:
- Review each document for accuracy
- Validate assumptions marked with
[ ] - Adjust timelines in roadmap if needed
- Commit documents to version control
- Reference documents in future development sessions
Example Usage
When user says: "I want to build a CLI tool for managing personal finances..."
Generation Flow with Consensus Review
-
Generate PVS
- Read
templates/pvs-template.md - Generate
docs/planning/project-vision.mdwith finance CLI specifics - Review:
mcp__zen__consensuswith gemini-3-pro-preview → READY or revise
- Read
-
Generate ADR
- Read
templates/adr-template.md - Generate
docs/planning/adr/adr-001-database-choice.mdfor SQLite decision - Review:
mcp__zen__consensuswith gemini-3-pro-preview → READY or revise
- Read
-
Generate Tech Spec
- Read
templates/tech-spec-template.md - Generate
docs/planning/tech-spec.mdwith Python/Click/SQLite stack - Review:
mcp__zen__consensuswith gemini-3-pro-preview → READY or revise
- Read
-
Generate Roadmap
- Read
templates/roadmap-template.md - Generate
docs/planning/roadmap.mdwith phased implementation - Review:
mcp__zen__consensuswith gemini-3-pro-preview → READY or revise
- Read
-
Final Validation
- Run
scripts/validate-planning-docs.py - Summarize what was created and review outcomes
- List next steps for beginning development
- Run
Consensus Review Prompt Template
mcp__zen__consensus with gemini-3-pro-preview:
Review this Project Vision & Scope document for Fragrance Rater.
EVALUATION CRITERIA:
1. SPECIFICITY - Can a developer implement from these requirements?
2. COMPLETENESS - All sections filled with project-specific content?
3. FEASIBILITY - Realistic scope for the described constraints?
4. CLARITY - Unambiguous success criteria and scope boundaries?
5. GAPS - Any critical missing information?
RESPOND:
- READY: Sufficient to proceed to next document
- NEEDS REVISION: [Specific improvements with examples]
DOCUMENT:
[Full document content here]
MCP Server Requirement
This skill requires the zen-mcp-server for consensus review. If not available, skip Step 3 and proceed with manual review.
Configuration: Ensure mcp__zen__consensus tool is accessible.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
perigon-backend
Perigon ASP.NET Core + EF Core + Aspire conventions
perigon-agent
Pointers for Copilot/agents to apply Perigon conventions
perigon-angular
Angular 21+ standalone/Material/signal conventions for Perigon WebApp
fastapi-mastery
Comprehensive FastAPI development skill covering REST API creation, routing, request/response handling, validation, authentication, database integration, middleware, and deployment. Use when working with FastAPI projects, building APIs, implementing CRUD operations, setting up authentication/authorization, integrating databases (SQL/NoSQL), adding middleware, handling WebSockets, or deploying FastAPI applications. Triggered by requests involving .py files with FastAPI code, API endpoint creation, Pydantic models, or FastAPI-specific features.
context7-efficient
Token-efficient library documentation fetcher using Context7 MCP with 86.8% token savings through intelligent shell pipeline filtering. Fetches code examples, API references, and best practices for JavaScript, Python, Go, Rust, and other libraries. Use when users ask about library documentation, need code examples, want API usage patterns, are learning a new framework, need syntax reference, or troubleshooting with library-specific information. Triggers include questions like "Show me React hooks", "How do I use Prisma", "What's the Next.js routing syntax", or any request for library/framework documentation.
browser-use
Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction.
Didn't find tool you were looking for?