Plan writing skill
Structured task planning with clear breakdowns, dependencies, and verification criteria.
by davila7·MIT license·★ 32,299 Stars on the repo·GitHub ↗
Use now
npx degit davila7/claude-code-templates/cli-tool/components/skills/productivity/plan-writing#main ~/.claude/skills/plan-writingChecked ·commit main
Files of Plan writing
SKILL.md
Show the full text153 lines
Plan Writing
Source: obra/superpowers
Overview
This skill provides a framework for breaking down work into clear, actionable tasks with verification criteria.
Task Breakdown Principles
1. Small, Focused Tasks
- Each task should take 2-5 minutes
- One clear outcome per task
- Independently verifiable
2. Clear Verification
- How do you know it's done?
- What can you check/test?
- What's the expected output?
3. Logical Ordering
- Dependencies identified
- Parallel work where possible
- Critical path highlighted
- Phase X: Verification is always LAST
4. Dynamic Naming in Project Root
- Plan files are saved as
{task-slug}.mdin the PROJECT ROOT - Name derived from task (e.g., "add auth" →
auth-feature.md) - NEVER inside
.claude/,docs/, or temp folders
Planning Principles (NOT Templates!)
🔴 NO fixed templates. Each plan is UNIQUE to the task.
Principle 1: Keep It SHORT
| ❌ Wrong | ✅ Right |
|---|---|
| 50 tasks with sub-sub-tasks | 5-10 clear tasks max |
| Every micro-step listed | Only actionable items |
| Verbose descriptions | One-line per task |
Rule: If plan is longer than 1 page, it's too long. Simplify.
Principle 2: Be SPECIFIC, Not Generic
| ❌ Wrong | ✅ Right |
|---|---|
| "Set up project" | "Run npx create-next-app" |
| "Add authentication" | "Install next-auth, create /api/auth/[...nextauth].ts" |
| "Style the UI" | "Add Tailwind classes to Header.tsx" |
Rule: Each task should have a clear, verifiable outcome.
Principle 3: Dynamic Content Based on Project Type
For NEW PROJECT:
- What tech stack? (decide first)
- What's the MVP? (minimal features)
- What's the file structure?
For FEATURE ADDITION:
- Which files are affected?
- What dependencies needed?
- How to verify it works?
For BUG FIX:
- What's the root cause?
- What file/line to change?
- How to test the fix?
Principle 4: Scripts Are Project-Specific
🔴 DO NOT copy-paste script commands. Choose based on project type.
| Project Type | Relevant Scripts |
|---|---|
| Frontend/React | ux_audit.py, accessibility_checker.py |
| Backend/API | api_validator.py, security_scan.py |
| Mobile | mobile_audit.py |
| Database | schema_validator.py |
| Full-stack | Mix of above based on what you touched |
Wrong: Adding all scripts to every plan Right: Only scripts relevant to THIS task
Principle 5: Verification is Simple
| ❌ Wrong | ✅ Right |
|---|---|
| "Verify the component works correctly" | "Run npm run dev, click button, see toast" |
| "Test the API" | "curl localhost:3000/api/users returns 200" |
| "Check styles" | "Open browser, verify dark mode toggle works" |
Plan Structure (Flexible, Not Fixed!)
# [Task Name]
## Goal
One sentence: What are we building/fixing?
## Tasks
- [ ] Task 1: [Specific action] → Verify: [How to check]
- [ ] Task 2: [Specific action] → Verify: [How to check]
- [ ] Task 3: [Specific action] → Verify: [How to check]
## Done When
- [ ] [Main success criteria]
That's it. No phases, no sub-sections unless truly needed. Keep it minimal. Add complexity only when required.
Notes
[Any important considerations]
---
## Best Practices (Quick Reference)
1. **Start with goal** - What are we building/fixing?
2. **Max 10 tasks** - If more, break into multiple plans
3. **Each task verifiable** - Clear "done" criteria
4. **Project-specific** - No copy-paste templates
5. **Update as you go** - Mark `[x]` when complete
---
## When to Use
- New project from scratch
- Adding a feature
- Fixing a bug (if complex)
- Refactoring multiple files
| 1 | |
| 2 | name plan-writing |
| 3 | description Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work. |
| 4 | allowed-tools Read, Glob, Grep |
| 5 | |
| 6 | |
| 7 | # Plan Writing |
| 8 | |
| 9 | > Source: obra/superpowers |
| 10 | |
| 11 | ## Overview |
| 12 | This skill provides a framework for breaking down work into clear, actionable tasks with verification criteria. |
| 13 | |
| 14 | ## Task Breakdown Principles |
| 15 | |
| 16 | ### 1. Small, Focused Tasks |
| 17 | Each task should take 2-5 minutes |
| 18 | One clear outcome per task |
| 19 | Independently verifiable |
| 20 | |
| 21 | ### 2. Clear Verification |
| 22 | How do you know it's done? |
| 23 | What can you check/test? |
| 24 | What's the expected output? |
| 25 | |
| 26 | ### 3. Logical Ordering |
| 27 | Dependencies identified |
| 28 | Parallel work where possible |
| 29 | Critical path highlighted |
| 30 | **Phase X: Verification is always LAST** |
| 31 | |
| 32 | ### 4. Dynamic Naming in Project Root |
| 33 | Plan files are saved as `{task-slug}.md` in the PROJECT ROOT |
| 34 | Name derived from task (e.g., "add auth" → `auth-feature.md`) |
| 35 | **NEVER** inside `.claude/`, `docs/`, or temp folders |
| 36 | |
| 37 | ## Planning Principles (NOT Templates!) |
| 38 | |
| 39 | > 🔴 **NO fixed templates. Each plan is UNIQUE to the task.** |
| 40 | |
| 41 | ### Principle 1: Keep It SHORT |
| 42 | |
| 43 | | ❌ Wrong | ✅ Right | |
| 44 | |----------|----------| |
| 45 | | 50 tasks with sub-sub-tasks | 5-10 clear tasks max | |
| 46 | | Every micro-step listed | Only actionable items | |
| 47 | | Verbose descriptions | One-line per task | |
| 48 | |
| 49 | > **Rule:** If plan is longer than 1 page, it's too long. Simplify. |
| 50 | |
| 51 | |
| 52 | |
| 53 | ### Principle 2: Be SPECIFIC, Not Generic |
| 54 | |
| 55 | | ❌ Wrong | ✅ Right | |
| 56 | |----------|----------| |
| 57 | | "Set up project" | "Run `npx create-next-app`" | |
| 58 | | "Add authentication" | "Install next-auth, create `/api/auth/[...nextauth].ts`" | |
| 59 | | "Style the UI" | "Add Tailwind classes to `Header.tsx`" | |
| 60 | |
| 61 | > **Rule:** Each task should have a clear, verifiable outcome. |
| 62 | |
| 63 | |
| 64 | |
| 65 | ### Principle 3: Dynamic Content Based on Project Type |
| 66 | |
| 67 | **For NEW PROJECT:** |
| 68 | What tech stack? (decide first) |
| 69 | What's the MVP? (minimal features) |
| 70 | What's the file structure? |
| 71 | |
| 72 | **For FEATURE ADDITION:** |
| 73 | Which files are affected? |
| 74 | What dependencies needed? |
| 75 | How to verify it works? |
| 76 | |
| 77 | **For BUG FIX:** |
| 78 | What's the root cause? |
| 79 | What file/line to change? |
| 80 | How to test the fix? |
| 81 | |
| 82 | |
| 83 | |
| 84 | ### Principle 4: Scripts Are Project-Specific |
| 85 | |
| 86 | > 🔴 **DO NOT copy-paste script commands. Choose based on project type.** |
| 87 | |
| 88 | | Project Type | Relevant Scripts | |
| 89 | |--------------|------------------| |
| 90 | | Frontend/React | `ux_audit.py`, `accessibility_checker.py` | |
| 91 | | Backend/API | `api_validator.py`, `security_scan.py` | |
| 92 | | Mobile | `mobile_audit.py` | |
| 93 | | Database | `schema_validator.py` | |
| 94 | | Full-stack | Mix of above based on what you touched | |
| 95 | |
| 96 | **Wrong:** Adding all scripts to every plan |
| 97 | **Right:** Only scripts relevant to THIS task |
| 98 | |
| 99 | |
| 100 | |
| 101 | ### Principle 5: Verification is Simple |
| 102 | |
| 103 | | ❌ Wrong | ✅ Right | |
| 104 | |----------|----------| |
| 105 | | "Verify the component works correctly" | "Run `npm run dev`, click button, see toast" | |
| 106 | | "Test the API" | "curl localhost:3000/api/users returns 200" | |
| 107 | | "Check styles" | "Open browser, verify dark mode toggle works" | |
| 108 | |
| 109 | |
| 110 | |
| 111 | ## Plan Structure (Flexible, Not Fixed!) |
| 112 | |
| 113 | |
| 114 | # [Task Name] |
| 115 | |
| 116 | ## Goal |
| 117 | One sentence: What are we building/fixing? |
| 118 | |
| 119 | ## Tasks |
| 120 | - [ ] Task 1: [Specific action] → Verify: [How to check] |
| 121 | - [ ] Task 2: [Specific action] → Verify: [How to check] |
| 122 | - [ ] Task 3: [Specific action] → Verify: [How to check] |
| 123 | |
| 124 | ## Done When |
| 125 | - [ ] [Main success criteria] |
| 126 | |
| 127 | |
| 128 | > **That's it.** No phases, no sub-sections unless truly needed. |
| 129 | > Keep it minimal. Add complexity only when required. |
| 130 | |
| 131 | ## Notes |
| 132 | [Any important considerations] |
| 133 | |
| 134 | |
| 135 | |
| 136 | |
| 137 | ## Best Practices (Quick Reference) |
| 138 | |
| 139 | 1. **Start with goal** - What are we building/fixing? |
| 140 | 2. **Max 10 tasks** - If more, break into multiple plans |
| 141 | 3. **Each task verifiable** - Clear "done" criteria |
| 142 | 4. **Project-specific** - No copy-paste templates |
| 143 | 5. **Update as you go** - Mark `[x]` when complete |
| 144 | |
| 145 | |
| 146 | |
| 147 | ## When to Use |
| 148 | |
| 149 | - New project from scratch |
| 150 | - Adding a feature |
| 151 | - Fixing a bug (if complex) |
| 152 | - Refactoring multiple files |
| 153 |
Discussion
Browse more free Claude skills.