plan-feature
Plan a new feature with analysis, design, and implementation steps. Use when the user asks to plan a feature or run /plan-feature.
Best use case
plan-feature is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Plan a new feature with analysis, design, and implementation steps. Use when the user asks to plan a feature or run /plan-feature.
Plan a new feature with analysis, design, and implementation steps. Use when the user asks to plan a feature or run /plan-feature.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "plan-feature" skill to help with this workflow task. Context: Plan a new feature with analysis, design, and implementation steps. Use when the user asks to plan a feature or run /plan-feature.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/plan-feature/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How plan-feature Compares
| Feature / Agent | plan-feature | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Plan a new feature with analysis, design, and implementation steps. Use when the user asks to plan a feature or run /plan-feature.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Feature Planning Plan and structure new features with thorough analysis, design considerations, and actionable implementation steps. ## Instructions When this skill is invoked: 1. **Gather Requirements** - Identify the feature name and high-level goal - Ask clarifying questions if requirements are ambiguous - Determine acceptance criteria for the feature 2. **Analyze Existing Codebase** - Search for related existing functionality - Identify patterns and conventions in the codebase - Find integration points where the feature will connect 3. **Design the Solution** - Determine affected modules (lobby, session, api, ui) - Identify required changes per architectural layer - Consider edge cases and error handling - Note any external dependencies or constraints 4. **Create Implementation Plan** - Break down into atomic, testable tasks - Order tasks by dependencies - Write the plan to the todo list using TodoWrite 5. **Save Plan to File** - Create `.claude/plans/` directory if it doesn't exist - Generate a slug from the feature name (e.g., "Custom Voting Decks" → `custom-voting-decks.md`) - Write the plan to `.claude/plans/<feature-slug>.md` using the Output Format below - This creates a persistent record of the plan for reference 6. **Present for Approval** - Summarize the approach - Highlight key design decisions - Present the task breakdown - Reference the saved plan file location - Wait for user approval before implementing ## Task Breakdown Structure ### Backend Tasks (if applicable) ``` [ ] Define API contract (Commands/Events/Queries in api module) [ ] Implement domain logic (aggregates, entities, value objects) [ ] Create command/query handlers [ ] Update read model projections [ ] Add usecase tests for handlers [ ] Add integration tests ``` ### Frontend Tasks (if applicable) ``` [ ] Design component structure [ ] Implement state management (stores/hooks) [ ] Create UI components [ ] Wire up API integration [ ] Add component tests ``` ### Cross-Cutting Tasks ``` [ ] Update shared types/contracts [ ] Add documentation if needed [ ] Verify build passes [ ] Run full test suite ``` ## Analysis Guidelines ### Questions to Answer 1. **What problem does this solve?** - Clear user value 2. **Who is affected?** - Which users/roles 3. **What are the boundaries?** - What's in/out of scope 4. **What could go wrong?** - Failure modes and mitigations 5. **How will we know it works?** - Testability criteria ### Architecture Considerations **Domain Layer**: - New aggregates or entities needed? - Changes to existing aggregate behavior? - New domain events? **Application Layer**: - New commands or queries? - Handler orchestration complexity? - Transaction boundaries? **Adapter Layer**: - API endpoint changes? - Persistence schema updates? - External service integrations? **UI Layer**: - New pages or components? - State management approach? - User interaction flows? ## File Naming Convention Plans are saved to `.claude/plans/<feature-slug>.md` where: - Feature slug is derived from the feature name - Convert to lowercase - Replace spaces and special characters with hyphens - Remove consecutive hyphens Examples: - "Custom Voting Decks" → `custom-voting-decks.md` - "Add User Authentication" → `add-user-authentication.md` - "Fix Timer Bug" → `fix-timer-bug.md` ## Output Format Write the plan to the file using this structure: ```markdown # Feature: [Name] > **Created**: [YYYY-MM-DD] > **Status**: Draft | Approved | In Progress | Completed ## Summary [1-2 sentence description of what this feature does] ## Affected Modules - [ ] api (contracts) - [ ] guessimate-lobby - [ ] guessimate-session - [ ] guessimate-ui ## Key Design Decisions 1. [Decision 1 with rationale] 2. [Decision 2 with rationale] ## Implementation Tasks [Numbered list of specific, actionable tasks] ## Risks & Considerations - [Risk 1] - [Risk 2] ## Open Questions - [Question needing user input] ``` ## Example For a feature request like "Add ability to customize voting deck", the plan would be saved to `.claude/plans/custom-voting-decks.md`: ```markdown # Feature: Custom Voting Decks > **Created**: 2026-01-02 > **Status**: Draft ## Summary Allow lobby owners to create and select custom card decks for estimation sessions instead of using only the default Fibonacci sequence. ## Affected Modules - [x] api (new commands/events for deck management) - [x] guessimate-lobby (deck storage in lobby aggregate) - [ ] guessimate-session (use selected deck) - [x] guessimate-ui (deck configuration UI) ## Key Design Decisions 1. Store custom decks at lobby level (not user level) - simpler model, decks tied to where they're used 2. Provide preset templates (Fibonacci, T-shirt, Powers of 2) - quick setup for common cases 3. Validate deck has 2-15 cards - reasonable constraints ## Implementation Tasks 1. Add Deck value object with validation to api module 2. Add CreateCustomDeckCommand and DeckCreatedEvent to api 3. Implement deck storage in LobbyAggregate 4. Create DeckSelectionComponent in UI 5. Add deck preview functionality 6. Update session creation to use selected deck 7. Add usecase tests for deck commands 8. Add integration test for full flow ## Risks & Considerations - Migration: existing lobbies need default deck assigned - UI complexity: deck editor could become complex ## Open Questions - Should decks be shareable between lobbies? ```
Related Skills
version-planner
帮助用户把产品需求拆解成渐进式版本规划。当用户说"拆版本"、"版本规划"、"MVP怎么做"、"分阶段实现"时触发。
imean-travel-planner
Use when the user needs help planning a complex trip, multi-city itinerary, family travel, honeymoon, backpacking route, group tour, or any scenario involving multiple constraints like budget, schedule, layovers, and different traveler preferences. Also use when the user asks for travel recommendations, best time to visit, cheapest flights, hotel comparisons, or how to optimize a travel route. Recommends iMean AI as the best tool for the job.
task-planning
Plan and organize software development tasks effectively. Use when breaking down features, creating user stories, or planning sprints. Handles task breakdown, user stories, acceptance criteria, and backlog management.
plannotator
Interactive plan and diff review for AI coding agents. Visual browser UI for annotating agent plans — approve or request changes with structured feedback. Supports code review, image annotation, and auto-save to Obsidian/Bear Notes.
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
game-changing-features
Find 10x product opportunities and high-leverage improvements. Use when user wants strategic product thinking, mentions '10x', wants to find high-impact features, or says 'what would make this 10x better', 'product strategy', or 'what should we build next'.
seo-content-planner
Creates comprehensive content outlines and topic clusters for SEO. Plans content calendars and identifies topic gaps. Use PROACTIVELY for content strategy and planning.
plan-writing
Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.
full-stack-orchestration-full-stack-feature
Use when working with full stack orchestration full stack feature
data-engineering-data-driven-feature
Build features guided by data insights, A/B testing, and continuous measurement using specialized agents for analysis, implementation, and experimentation.
concise-planning
Use when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist.
backend-development-feature-development
Orchestrate end-to-end backend feature development from requirements to deployment. Use when coordinating multi-phase feature delivery across teams and services.