speckit-plan-zh

User Input

$ARGUMENTS

Outline

1. Setup: Run

   .specify/scripts/powershell/setup-plan.ps1 -Json

   from the root directory of the repository and parse the JSON to obtain FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in parameters, such as "I'm Groot", use escape syntax: e.g., 'I'''m Groot' (or use double quotes if possible: "I'm Groot").
2. Load Context: Read FEATURE_SPEC and

   .specify/memory/constitution.md

   . Load the copied IMPL_PLAN template.
3. Execute Plan Workflow: Follow the structure in the IMPL_PLAN template to:
   • Fill in technical context (mark unknown items as "Needs Clarification")
   • Fill in the constitution check section from the constitution
   • Evaluate gateways (report ERROR if there are unjustified violations)
   • Phase 0: Generate research.md (resolve all "Needs Clarification" items)
   • Phase 1: Generate data-model.md, contracts/, quickstart.md
   • Phase 1: Update agent context by running agent scripts
   • Re-evaluate constitution check after design
4. Stop and Report: The command ends after Phase 2 planning. Report the branch, IMPL_PLAN path, and generated artifacts.

Phases

Phase 0: Outline & Research

1. Extract unknown items from the above technical context:
   • For each "Needs Clarification" → Research task
   • For each dependency → Best practice task
   • For each integration → Pattern task
2. Generate and distribute research agents:
   text

   For each unknown item in the technical context:
     Task: "Research {unknown item} for {feature context}"
   For each technical choice:
     Task: "Find best practices for {technology} in {domain}"

3. Integrate findings in

   research.md

   using the format:
   • Decision: [What was chosen]
   • Rationale: [Why it was chosen]
   • Alternatives Considered: [What else was evaluated]

Phase 1: Design & Contracts

research.md

1. Extract entities from feature specification →

   data-model.md

   :
   • Entity names, fields, relationships
   • Validation rules from requirements
   • State transitions if applicable
2. Generate API contracts from functional requirements:
   • For each user action → Endpoint
   • Use standard REST/GraphQL schema
   • Output OpenAPI/GraphQL schema to

     /contracts/

3. Agent Context Update:
   • Run

     .specify/scripts/powershell/update-agent-context.ps1 -AgentType claude

   • These scripts detect the AI agent being used
   • Update the corresponding agent-specific context files
   • Only add new technologies from the current plan
   • Keep manually added content between markers

Key Rules

• Use absolute paths
• Report ERROR if checkpoint fails or there are unresolved clarification items