Skip to main content
ClaudeWave
Skill4.3k estrellas del repoactualizado 8d ago

planning-with-files

The planning-with-files skill provides a structured system for managing complex multi-step tasks by creating and maintaining three persistent markdown files: task_plan.md for tracking phases, notes.md for research findings, and a deliverable file for final output. Use this approach by default when work spans multiple tool calls, requires progress tracking across phases, involves research or verification loops, or may pause and resume later, since persistent disk-based notes prevent context fragmentation and enable more reliable task completion than relying solely on chat memory.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/Galaxy-Dawn/claude-scholar /tmp/planning-with-files && cp -r /tmp/planning-with-files/skills/planning-with-files ~/.claude/skills/planning-with-files
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# Planning with Files

Work like Manus: use persistent markdown files as your working memory on disk.

This is not just an optional planning style. It should be the default persistence layer for complex Codex work.

Use it proactively when:

- the task will likely take more than a few tool calls
- progress needs to be tracked across phases
- findings or evidence must be preserved while working
- the task may branch, pause, or resume later
- relying on chat context alone would be fragile

## Quick Start

Before ANY complex task:

1. **Create `task_plan.md`** in the working directory
2. **Define phases** with checkboxes
3. **Update after each phase** - mark [x] and change status
4. **Read before deciding** - refresh goals in attention window

## The 3-File Pattern

For every non-trivial task, create THREE files:

| File | Purpose | When to Update |
|------|---------|----------------|
| `task_plan.md` | Track phases and progress | After each phase |
| `notes.md` | Store findings and research | During research |
| `[deliverable].md` | Final output | At completion |

## Core Workflow

```
Loop 1: Create task_plan.md with goal and phases
Loop 2: Research → save to notes.md → update task_plan.md
Loop 3: Read notes.md → create deliverable → update task_plan.md
Loop 4: Deliver final output
```

### The Loop in Detail

**Before each major action:**
```bash
Read task_plan.md  # Refresh goals in attention window
```

**After each phase:**
```bash
Edit task_plan.md  # Mark [x], update status
```

**When storing information:**
```bash
Write notes.md     # Don't stuff context, store in file
```

## task_plan.md Template

Create this file FIRST for any complex task:

```markdown
# Task Plan: [Brief Description]

## Goal
[One sentence describing the end state]

## Phases
- [ ] Phase 1: Plan and setup
- [ ] Phase 2: Research/gather information
- [ ] Phase 3: Execute/build
- [ ] Phase 4: Review and deliver

## Key Questions
1. [Question to answer]
2. [Question to answer]

## Decisions Made
- [Decision]: [Rationale]

## Errors Encountered
- [Error]: [Resolution]

## Status
**Currently in Phase X** - [What I'm doing now]
```

## notes.md Template

For research and findings:

```markdown
# Notes: [Topic]

## Sources

### Source 1: [Name]
- URL: [link]
- Key points:
  - [Finding]
  - [Finding]

## Synthesized Findings

### [Category]
- [Finding]
- [Finding]
```

## Critical Rules

### 1. ALWAYS Create Plan First
Never start a complex task without `task_plan.md`. This is non-negotiable.

### 2. Read Before Decide
Before any major decision, read the plan file. This keeps goals in your attention window.

### 3. Update After Act
After completing any phase, immediately update the plan file:
- Mark completed phases with [x]
- Update the Status section
- Log any errors encountered

### 4. Store, Don't Stuff
Large outputs go to files, not context. Keep only paths in working memory.

### 5. Log All Errors
Every error goes in the "Errors Encountered" section. This builds knowledge for future tasks.

## When to Use This Pattern

**Use 3-file pattern for:**
- Multi-step tasks (3+ steps)
- Research tasks
- Building/creating something
- Tasks spanning multiple tool calls
- Anything requiring organization

**Skip for:**
- Simple questions
- Single-file edits
- Quick lookups

## Anti-Patterns to Avoid

| Don't | Do Instead |
|-------|------------|
| Use TodoWrite for persistence | Create `task_plan.md` file |
| State goals once and forget | Re-read plan before each decision |
| Hide errors and retry | Log errors to plan file |
| Stuff everything in context | Store large content in files |
| Start executing immediately | Create plan file FIRST |

## Advanced Patterns

See [reference.md](reference.md) for:
- Attention manipulation techniques
- Error recovery patterns
- Context optimization from Manus

See [examples.md](examples.md) for:
- Real task examples
- Complex workflow patterns
code-reviewerSubagent

Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code. MUST BE USED for all code changes.

kaggle-minerSubagent

Use this agent when the user provides a Kaggle competition URL or asks to learn from Kaggle winning solutions. Examples:

literature-reviewerSubagent

Use this agent when the user asks to "conduct literature review", "search for papers", "analyze research papers", "identify research gaps", "review related work", or mentions starting a research project. This agent integrates with Zotero for automated paper collection, organization, and full-text analysis. Examples:

paper-minerSubagent

Use this agent when the user provides a research paper (PDF/DOCX/arXiv link) or asks to learn writing patterns from papers, extract venue-specific writing signals, study paper structure, or mine rebuttal strategies. The agent writes extracted knowledge into the active installed paper-miner writing memory for ml-paper-writing. It does not maintain project-specific writing memory.

rebuttal-writerSubagent

Use this agent when the user asks to "write rebuttal", "respond to reviewers", "analyze review comments", or needs help with academic paper review response. This agent specializes in systematic rebuttal writing with professional tone and structured responses.

tdd-guideSubagent

Test-driven development guide for writing tests first, implementing the smallest passing change, and keeping verification tight. Use when the user explicitly wants TDD or when a task should be driven by failing tests before code.

analyze-resultsSlash Command

Run a blocker-first post-experiment workflow: validate evidence, produce strict statistical analysis when possible, and generate a decision-oriented results report only when the analysis bundle is sufficient. Uses results-analysis + results-report as a gated two-stage workflow.

commitSlash Command

Commit changes following Conventional Commits format (local only, no push).