planner/SKILL.md
Create step-by-step plans for solving problems, debugging issues, building features, or architecting complex solutions. Always includes pros/cons analysis and risk consideration. Use when the user asks to plan, create a roadmap, break down a task, design an approach, outline steps, or needs a structured path forward.
npx skillsauth add tim-hub/role-based-skills plannerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create clear, actionable step-by-step plans. Every plan considers trade-offs, risks, and alternatives so you make informed decisions before writing a single line of code.
When the user asks to plan:
Select the appropriate planning mode based on the user's goal:
Break a well-defined problem into steps toward a solution.
Systematically narrow down the source of a bug or unexpected behavior.
Plan the implementation of a new feature within an existing codebase.
Design a system or application from scratch or plan a major restructuring.
Plan a safe transition from current state to desired state.
# Plan: [Goal in one sentence]
## Context
[Brief summary of current state, constraints, and relevant findings from codebase exploration]
## Approach
### Option A: [Name]
[One-paragraph description]
| Pros | Cons |
|------|------|
| ... | ... |
| ... | ... |
### Option B: [Name]
[One-paragraph description]
| Pros | Cons |
|------|------|
| ... | ... |
| ... | ... |
**Recommended**: Option [X] — [One-sentence justification]
## Steps
### Phase 1: [Phase Name]
- [ ] **Step 1**: [Action] — [Why this step matters]
- [ ] **Step 2**: [Action] — [Why this step matters]
- Verify: [How to confirm this step succeeded]
### Phase 2: [Phase Name]
- [ ] **Step 3**: [Action] — [Why this step matters]
- [ ] **Step 4**: [Action] — [Why this step matters]
- Verify: [How to confirm this step succeeded]
## Risks & Mitigations
| Risk | Likelihood | Impact | Mitigation |
|------|-----------|--------|------------|
| ... | Low/Med/High | Low/Med/High | ... |
| ... | Low/Med/High | Low/Med/High | ... |
## Out of Scope
- [Items explicitly excluded and why]
## Definition of Done
- [Criteria that confirm the plan is fully executed]
For debugging/investigation, use this specialized format instead:
# Investigation: [Symptom / Issue]
## Observed Behavior
[What is happening]
## Expected Behavior
[What should happen]
## Hypotheses
| # | Hypothesis | Likelihood | Evidence Needed |
|---|-----------|-----------|-----------------|
| 1 | ... | High/Med/Low | ... |
| 2 | ... | High/Med/Low | ... |
## Investigation Steps
- [ ] **Step 1**: [Check/test] — Tests hypothesis #[N]
- If confirmed: [Next action]
- If ruled out: Proceed to step [N]
- [ ] **Step 2**: [Check/test] — Tests hypothesis #[N]
- If confirmed: [Next action]
- If ruled out: Proceed to step [N]
## Resolution
[To be filled after investigation — root cause + fix]
The planner works well in combination with other skills:
/brainstormer) - Use before planning to generate diverse solution options when the path forward is unclear. Feed the top picks into the planner's "Approach" section./challenger) - Use after planning to stress-test the plan. Feed the challenge report back to refine risks, mitigations, and step ordering./brainstormer — Generate options/planner — Structure the best options into a concrete plan/challenger — Poke holes in the plantesting
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
development
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and verification steps assuming engineer has minimal domain knowledge
data-ai
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
tools
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification