跳到正文
cccskills
免费在 GitHub 公开

concise-planning

Use when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Concise Planning

Generate focused, actionable implementation plans that eliminate ambiguity and prevent scope creep.

When to Use

  • User asks "how should I approach this?" or "can you make a plan for X?"
  • Task involves multiple files or components
  • Work spans more than ~3 logical steps
  • You need to communicate a proposed sequence before executing

When NOT to Use

  • Task is a single-step operation (just do it)
  • User gave an explicit command with clear intent (just execute)
  • During /plan-phase or /implement-slice (those have their own planning structure)

Workflow

1. Scan Context (30 seconds, not 5 minutes)

Read only what's necessary:

  • Project structure — ls the relevant directories
  • Existing patterns — check one similar file for conventions
  • Constraints — look for test frameworks, linters, type systems in use

Do NOT read every file in the project. Do NOT generate a 500-line analysis. Scan, not study.

2. Ask or Assume

  • 0 questions if the task is clear and you have enough context
  • 1 question max if there's a genuinely blocking ambiguity
  • Never more than 2 — if you need more, you don't understand the codebase well enough. Go read more code instead of asking.

For non-blocking unknowns, state your assumption:

"Assuming we want this as a new utility in lib/ rather than inline — will adjust if you prefer otherwise."

3. Generate Plan

Use this exact structure:

## Approach

[1-3 sentences: what you'll do and why this approach over alternatives]

## Scope

**In:**
- [Specific deliverable 1]
- [Specific deliverable 2]

**Out:**
- [Explicitly excluded item — prevents scope creep]

## Steps

1. [Verb] [specific target] — [why, if non-obvious]
2. [Verb] [specific target]
3. [Verb] [specific target]
4. [Verb] [specific target]
5. Validate: [specific validation command or check]

## Assumptions

- [Assumption 1 — what you decided without asking]

Plan Quality Rules

RuleWhy
6-10 stepsFewer = too vague. More = over-planned.
Verb-first steps"Add", "Create", "Refactor", "Test" — not "The component should..."
Name files and functions"Add validateEmail() to lib/validators.ts" not "add validation"
One validation step minimumEvery plan ends with proof it works
Explicit "Out" scopePrevents the plan from growing mid-execution
No nested sub-plansIf a step needs sub-steps, it's too big — split it

Anti-Patterns

Don'tDo
"Research best practices for X"Just apply the best practice directly in a step
"Consider whether to use A or B"Pick one, state why, move on
"Set up the project structure""Create src/validators/ with index.ts and email.ts"
"Write tests""Add tests for validateEmail: valid input, empty string, missing @, >254 chars"
20-step plan8-step plan with clear scope boundaries
Plan that describes what might happenPlan that describes what WILL happen

Output Format

Always present the plan in a markdown code block or as structured markdown. Never as prose paragraphs.

After presenting the plan, ask one question:

"Ready to execute, or want to adjust anything?"

Then execute on confirmation — don't re-plan.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Audit and improve web accessibility following WCAG 2.1 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

Structured methodology for adversarial thinking — generating attack scenarios, abuse cases, race conditions, and security edge cases against specs and implementations. Produces spec-level gap items, not code-level fixes.

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

Orchestrate multiple Antigravity skills through guided workflows for SaaS MVP delivery, security audits, AI agent builds, and browser QA.

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

Manage API versioning and evolution with URL/header/query strategies, deprecation workflows, breaking change classification, sunset headers, and consumer-driven contract testing. Use when designing versioning strategy, deprecating endpoints, or evolving API contracts.

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

Analyzes codebase structure, data flow, module relationships, and key patterns to generate and maintain a living architecture document (ARCHITECTURE.md).

中文简介正在准备中。当前显示原文说明。

RepairYourTech/cfsa-antigravity62026年8月16日 更新

查看 RepairYourTech 的全部技能

报告此技能的问题