Agent Skillsvudovn/ag-kit › plan-writing

plan-writing

GitHub

提供结构化任务规划框架,将工作分解为清晰、可验证的小任务,识别依赖关系并优化执行顺序,适用于功能实现、重构及多步骤复杂工作。

.agents/skills/plan-writing/SKILL.md vudovn/ag-kit

Trigger Scenarios

需要拆解复杂任务 实施新功能开发 进行代码重构 多步骤工作流程规划

Install

npx skills add vudovn/ag-kit --skill plan-writing -g -y
More Options

Non-standard path

npx skills add https://github.com/vudovn/ag-kit/tree/main/.agents/skills/plan-writing -g -y

Use without installing

npx skills use vudovn/ag-kit@plan-writing

指定 Agent (Claude Code)

npx skills add vudovn/ag-kit --skill plan-writing -a claude-code -g -y

安装 repo 全部 skill

npx skills add vudovn/ag-kit --all -g -y

预览 repo 内 skill

npx skills add vudovn/ag-kit --list

SKILL.md

Frontmatter
{
    "name": "plan-writing",
    "version": "1.0.0",
    "description": "Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.",
    "when_to_use": "When creating structured task plans, breaking down features into tasks, or defining verification criteria. Use with \/plan workflow.",
    "allowed-tools": "Read, Glob, Grep"
}

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}.md in the PROJECT ROOT
  • Name derived from task (e.g., "add auth" → auth-feature.md)
  • NEVER inside .agents/, 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]

## Notes
[Any important considerations]

That's it. No phases, no sub-sections unless truly needed. Keep it minimal. Add complexity only when required.


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

Version History

  • 211561c Current 2026-08-20 11:39

Same Skill Collection

.agents/skills/api-patterns/SKILL.md
.agents/skills/app-builder/SKILL.md
.agents/skills/app-builder/templates/SKILL.md
.agents/skills/architecture/SKILL.md
.agents/skills/bash-linux/SKILL.md
.agents/skills/batch-operations/SKILL.md
.agents/skills/behavioral-modes/SKILL.md
.agents/skills/brainstorming/SKILL.md
.agents/skills/clean-code/SKILL.md
.agents/skills/code-review-checklist/SKILL.md
.agents/skills/code-review-graph/SKILL.md
.agents/skills/context-compression/SKILL.md
.agents/skills/coordinator-mode/SKILL.md
.agents/skills/database-design/SKILL.md
.agents/skills/deployment-procedures/SKILL.md
.agents/skills/design-spec/SKILL.md
.agents/skills/documentation-templates/SKILL.md
.agents/skills/frontend-architecture/SKILL.md
.agents/skills/frontend-design/SKILL.md
.agents/skills/game-development/2d-games/SKILL.md
.agents/skills/game-development/3d-games/SKILL.md
.agents/skills/game-development/game-art/SKILL.md
.agents/skills/game-development/game-audio/SKILL.md
.agents/skills/game-development/game-design/SKILL.md
.agents/skills/game-development/mobile-games/SKILL.md
.agents/skills/game-development/multiplayer/SKILL.md
.agents/skills/game-development/pc-games/SKILL.md
.agents/skills/game-development/SKILL.md
.agents/skills/game-development/vr-ar/SKILL.md
.agents/skills/game-development/web-games/SKILL.md
.agents/skills/geo-fundamentals/SKILL.md
.agents/skills/i18n-localization/SKILL.md
.agents/skills/intelligent-routing/SKILL.md
.agents/skills/lint-and-validate/SKILL.md
.agents/skills/mcp-builder/SKILL.md
.agents/skills/memory-system/SKILL.md
.agents/skills/mobile-design/SKILL.md
.agents/skills/nextjs-react-expert/SKILL.md
.agents/skills/nodejs-best-practices/SKILL.md
.agents/skills/parallel-agents/SKILL.md
.agents/skills/performance-profiling/SKILL.md
.agents/skills/powershell-windows/SKILL.md
.agents/skills/python-patterns/SKILL.md
.agents/skills/red-team-tactics/SKILL.md
.agents/skills/rust-pro/SKILL.md
.agents/skills/seo-fundamentals/SKILL.md
.agents/skills/server-management/SKILL.md
.agents/skills/simplify-code/SKILL.md
.agents/skills/skillify/SKILL.md

Metadata

Files
0
Version
211561c
Hash
2698f0dc
Indexed
2026-08-20 11:39

- 위키
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-26 02:12
浙ICP备14020137号-1 $방문자$