From superpowers-ng
Use for complex multi-step tasks requiring persistent memory across context resets, long autonomous runs, or multi-session projects
How this skill is triggered — by the user, by Claude, or both
Slash command
/superpowers-ng:manus-planningThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Persistent file-based planning for complex tasks. Uses 3 markdown files as external memory that survives context resets, enabling work on tasks that span many tool calls or multiple sessions.
Persistent file-based planning for complex tasks. Uses 3 markdown files as external memory that survives context resets, enabling work on tasks that span many tool calls or multiple sessions.
Based on: planning-with-files by OthmanAdi
Announce at start: "I'm using the manus-planning skill for persistent tracking."
Files location: docs/manus/ (tracked in git)
When to use this vs native planning:
| File | Purpose | Update Frequency |
|---|---|---|
task_plan.md | Goal, phases, decisions, errors | Before major decisions |
findings.md | Research, requirements, resources | After every 2 search/view operations |
progress.md | Session log, test results, detailed actions | After completing actions |
Before creating files, check for existing manus task:
Case A: No docs/manus/task_plan.md exists
Case B: task_plan.md exists but NO .active marker
docs/manus/archive/YYYY-MM-DD-<topic>/Case C: task_plan.md exists AND .active marker exists
There's an active manus task: "[goal from task_plan.md]"
Current phase: [X of 5]
Is your request:
1. A continuation of this task (resume where you left off)
2. A new separate task (archives existing task)
docs/manus/ directory if not existsfindings.md under "## Design Document" sectiondocs/manus/.active (empty file to enable hooks)findings.mdtask_plan.md with refined goaltask_plan.md Decisions tableprogress.mdtask_plan.md and progress.mdprogress.mdNever begin complex work without task_plan.md in place.
After every 2 view/browser/search operations, IMMEDIATELY update findings.md with key discoveries. Visual and search results don't persist in context - save them to files.
Before major decisions or file modifications, re-read task_plan.md to maintain goal focus. The PreToolUse hook helps with this automatically.
After completing actions:
task_plan.mdprogress.mdEvery error goes into:
task_plan.md Errors Encountered section (with resolution)progress.md Error Log (with timestamp and details)When all 5 phases are complete:
complete in task_plan.mddocs/manus/.active# [Task Name]
**Goal:** [One clear sentence - your north star]
**Current Phase:** [1-5] - [Phase Name]
## Phases
### Phase 1: Requirements & Discovery
- [ ] Understand user requirements
- [ ] Explore relevant codebase areas
- [ ] Document findings
**Status:** pending | in_progress | complete
### Phase 2: Planning & Structure
- [ ] Decide technical approach
- [ ] Document key decisions
- [ ] Break into actionable steps
**Status:** pending | in_progress | complete
### Phase 3: Implementation
- [ ] [Specific implementation tasks]
**Status:** pending | in_progress | complete
### Phase 4: Testing & Verification
- [ ] Run tests
- [ ] Verify functionality
- [ ] Fix issues
**Status:** pending | in_progress | complete
### Phase 5: Delivery
- [ ] Final review
- [ ] Clean up
- [ ] Handoff
**Status:** pending | in_progress | complete
## Key Questions
- [Important questions to answer during the task]
## Decisions Made
| Decision | Rationale | Date |
|----------|-----------|------|
| | | |
## Errors Encountered
| Error | Attempts | Resolution |
|-------|----------|------------|
| | | |
## Notes
- Remember to update phase status as you progress
- Re-read this file before major decisions
- Log all errors for future reference
# Findings
## Requirements
[What the user requested - specific requirements]
## Design Document
[If coming from brainstorming, design content goes here]
## Research Findings
[Key discoveries from exploration, web searches, documentation]
## Technical Decisions
[Architecture and implementation choices with reasoning]
## Issues Encountered
[Problems and their resolutions - broader than coding errors]
## Resources
- [Useful URLs]
- [File paths]
- [API references]
- [Documentation links]
## Visual/Browser Findings
[CRITICAL: Information learned from images, PDFs, browser results - this content doesn't persist in context, save it here immediately]
# Progress Log
## Session: [Date]
### Phase 1: Requirements & Discovery
**Status:** pending | in_progress | complete
**Started:** [timestamp]
**Actions:**
- [What was done]
**Files Modified:**
- [List of files]
### Phase 2: Planning & Structure
**Status:** pending | in_progress | complete
**Started:** [timestamp]
**Actions:**
- [What was done]
**Files Modified:**
- [List of files]
[Continue for each phase...]
## Test Results
| Test | Expected | Actual | Pass/Fail |
|------|----------|--------|-----------|
| | | | |
## Error Log
| Timestamp | Error | Resolution |
|-----------|-------|------------|
| | | |
## 5-Question Reboot Check
Use these questions to resume after context reset:
1. **Where am I?** [Current phase]
2. **Where am I going?** [Remaining phases]
3. **What's the goal?** [From task_plan.md]
4. **What have I learned?** [Key findings]
5. **What have I done?** [Completed actions]
If context is cleared or compacted mid-task:
docs/manus/task_plan.md for goal and current phasedocs/manus/progress.md for what's been donedocs/manus/findings.md for research and decisionsnpx claudepluginhub quentin-m/superpowers-ng --plugin superpowers-ngGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Implements work from a spec or tickets using TDD at agreed seams, with regular typechecking and test runs, followed by code review.