speckit-plan-zh

User input

$ARGUMENTS

Before continuing, youmustconsider the user input (if it is not empty).

Outline

1. Setup: Run from the repository root .specify/scripts/powershell/setup-plan.ps1 -Json and parse the JSON to obtain FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH. For single quotes in arguments, such as "I'm Groot", use the escape syntax: for example 'I'''m Groot' (or if possible use double quotes: "I'm Groot").

2. Load context: Read FEATURE_SPEC and .specify/memory/constitution.md. Load the IMPL_PLAN template (already copied).

1. Execute the planning workflow: Follow the structure in the IMPL_PLAN template to:

   • Fill in the technical context (mark unknown items as "NEEDS CLARIFICATION")
   • Fill in the charter check section from the charter
   • Evaluate gates (error if there are unjustified violations)
   • Phase 0: Generate research.md (resolve all "NEEDS CLARIFICATION")
   • Phase 1: Generate data-model.md, contracts/, quickstart.md
   • Phase 1: Update agent context by running the agent script
   • Re-evaluate charter check after design

2. Stop and report: The command ends after Phase 2 planning. Report the branch, IMPL_PLAN path, and generated artifacts.

Phase

Phase 0: Outline & Research

1. Extract unknown items from the above technical context:

   • For each "NEEDS CLARIFICATION" → research task
   • For each dependency → best practices task
   • For each integration → patterns task

2. Generate and dispatch research agents:

   对于技术上下文中的每个未知项:
     任务: "研究 {未知项} 用于 {功能上下文}"
   对于每个技术选择:
     任务: "查找 {技术} 在 {领域} 中的最佳实践"
   

3. In research.md consolidate findings, using the format:

   • Decision: [what was chosen]
   • Rationale: [why it was chosen]
   • Alternatives considered: [what else was evaluated]

Output: research.md with all "NEEDS CLARIFICATION" resolved

Phase 1: Design & Contracts

Prerequisites: research.md complete

1. Extract entities from the 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 patterns
   • Output OpenAPI/GraphQL schemas 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 file
   • Only add new technologies from the current plan
   • Preserve manual additions between the markers

Output: data-model.md, /contracts/*, quickstart.md, agent-specific files

Key rules

• Use absolute paths
• If a checkpoint fails or there are unresolved clarification items, report ERROR