一键导入
planning-with-files
// Use when user explicitly requests planning with files, or asks for persistent tracking of a complex task.
// Use when user explicitly requests planning with files, or asks for persistent tracking of a complex task.
| name | planning-with-files |
| description | Use when user explicitly requests planning with files, or asks for persistent tracking of a complex task. |
Use persistent markdown files as external memory for complex tasks. Files survive context limits and session boundaries.
Use TodoWrite to decompose phases into executable tasks. Before closing session, use Question to confirm findings, decisions, and deliverables are satisfactory.
All planning files go in _plans/ with date-prefixed task folders:
_plans/
2026-01-08-dark-mode-toggle/
plan.md
research.md
decisions.md
2026-01-09-api-auth-refactor/
plan.md
scratch.md
Naming: YYYY-MM-DD-task-name (kebab-case, concise description)
Create files based on what the task needs, not a fixed pattern:
| Type | When to Create | Content |
|---|---|---|
plan.md | Always | Goal, phases, status, errors encountered |
research.md | Research-heavy tasks | Sources, findings, synthesized data |
decisions.md | Tradeoff decisions | ADRs, options considered, rationale |
scratch.md | Complex reasoning | Drafts, working notes, exploratory code |
[deliverable].md | Final outputs | Reports, summaries, documentation |
# Plan: [Brief Description]
## Goal
[One sentence describing the end state]
## Phases
- [ ] Phase 1: [Description]
- [ ] Phase 2: [Description]
- [ ] Phase 3: [Description]
## Status
**Current:** [What's happening now]
## Decisions
- [Decision]: [Rationale]
## Errors Encountered
- [Error]: [Resolution]
# Research: [Topic]
## Sources
- [Source]: [Key findings]
## Findings
### [Category]
- [Finding]
# Decisions: [Task]
## [Decision Title]
**Status:** Decided | Pending
**Options:**
1. [Option A] - [Pros/Cons]
2. [Option B] - [Pros/Cons]
**Choice:** [Selected option]
**Rationale:** [Why]
Planning files are for investigation; TodoWrite tasks are for execution.
Workflow:
_plans/ directory and plan.md| Tool | When to Use |
|---|---|
| Explore subagent | Search codebase, find patterns, understand existing structure before planning |
| Question | Clarify requirements, validate assumptions, confirm decisions before proceeding |
Use these proactively during investigation to avoid wrong assumptions and wasted effort.
Planning is complete when:
plan.md exists with clear goal and phasesQuestionAfter many tool calls (~20+), re-read plan.md before major decisions. This brings goals back into the attention window.
Large outputs go to files, not context. Keep paths in working memory, content in files.
Every error goes in plan.md under "Errors Encountered". This builds knowledge and shows recovery.
Don't just record what you decided - record WHY. Future-you needs this context.
Mark phases complete as soon as they're done. Don't batch status updates.
| Don't | Do Instead |
|---|---|
| Create files in project root | Use _plans/YYYY-MM-DD-name/ |
| State goals once and forget | Re-read plan.md when context is long |
| Hide errors and retry silently | Log errors with resolution |
| Stuff everything in context | Store large content in files |
| Start executing immediately | Create plan.md first for complex tasks |
This skill should be used when investigating .NET project dependencies, understanding why packages are included, listing references, or auditing for outdated/vulnerable packages.
This skill should be used when running .NET tests selectively with a build-first, test-targeted workflow. Use it for running tests with xUnit focus.