Agent skill
speckit-plan
Execute the implementation planning workflow using the plan template to generate design artifacts.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/speckit-plan-dceoy-speckit-agent-skills-e83e50c9
SKILL.md
Spec-Kit Plan
Generate comprehensive technical implementation plan from feature specification. Second step in spec-kit workflow.
When to Use
- After creating spec.md with
speckit-specify - Need technical architecture and design
- Ready to plan implementation details
Execution Workflow
- Setup: Run
.specify/scripts/bash/setup-plan.sh --jsonto get FEATURE_SPEC, IMPL_PLAN, SPECS_DIR, BRANCH paths - Load context: Read FEATURE_SPEC and
.specify/memory/constitution.md, load IMPL_PLAN template - Execute plan workflow:
- Fill Technical Context (mark unknowns as "NEEDS CLARIFICATION")
- Fill Constitution Check section from constitution
- Evaluate gates (ERROR if violations unjustified)
- Phase 0: Research - Resolve all NEEDS CLARIFICATION before design
- Extract unknowns from Technical Context
- Research best practices for each unknown (web search, documentation)
- Generate research.md with decision rationale and alternatives considered
- MUST complete Phase 0 before Phase 1
- Phase 1: Design - Generate technical artifacts
- data-model.md: Extract entities from spec, define fields/relationships/validation
- contracts/: Generate API contracts (OpenAPI/GraphQL) from functional requirements
- quickstart.md: Create test scenarios and setup instructions
- Update agent context: Run
.specify/scripts/bash/update-agent-context.sh claude- Adds new technology from plan to agent-specific context
- Preserves manual additions between markers
- Re-evaluate Constitution Check post-design (verify no violations introduced)
- Report: Command ends after planning. Report branch, IMPL_PLAN path, and generated artifacts
Key Points
- Research unknowns thoroughly before design
- Document decision rationale (why chosen, alternatives considered)
- Design for testability following project conventions
- Avoid over-engineering - only what's needed
- Follow semantic versioning and architecture patterns
- Constitution check is non-negotiable - must align with principles
- Update agent-specific context files with new technology
Next Steps
After creating plan.md:
- Generate tasks with
speckit-tasks - Analyze for consistency with
speckit-analyze - Create checklist for quality validation
See Also
speckit-specify- Create feature specificationsspeckit-tasks- Break plan into actionable tasksspeckit-analyze- Validate cross-artifact consistencyspeckit-checklist- Generate custom validation checklists
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?