Token导航 LogoToken导航TokenDH.com
研究检索操作浏览器github未标认证来源可访问许可证需确认审计通过

plan-generation计划生成

Agent Skill

plan-generation 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

220

周安装

9

GitHub Stars

61

下载量

71
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:plan-generation(计划生成)
来源仓库:https://github.com/melodic-software/claude-code-plugins
仓库路径:skills/plan-generation
安装命令:
npx skills add https://github.com/melodic-software/claude-code-plugins --skill plan-generation
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/melodic-software/claude-code-plugins --skill plan-generation

简介

用于在任务前查找、检索和筛选相关信息。

  • 适合根据关键词、任务场景或来源线索快速定位候选结果,支持多宿主环境协作。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,使用前需确认权限和维护状态。
  • 建议检查是否会触发联网、命令执行或文件读写操作,确保符合安全策略。
  • 可结合来源仓库和原始 README 进一步核验具体用法和适用边界。

SKILL.md

Plan Generation

Guide for generating high-quality plans from meta-prompt templates.

When to Use

  • Generating plans from /chore, /bug, /feature templates
  • Reviewing generated plans for completeness
  • Ensuring plans follow team standards
  • Improving plan quality and specificity

Plan Generation Process

Step 1: Understand the Request

Parse the high-level description:

Input: "Add user authentication with OAuth"

Extract:
- Domain: Authentication
- Scope: User-facing, OAuth protocol
- Complexity: Medium-high (external integration)

Step 2: Activate Reasoning

Use extended thinking for complex planning:

THINK HARD about:
- What files need to change?
- What are the dependencies?
- What could go wrong?
- How will we verify success?

Step 3: Explore the Codebase

Gather context before planning:

  • Read README for project structure
  • Identify relevant existing patterns
  • Find test examples to follow
  • Locate configuration files

Step 4: Fill the Template

Complete every section with specifics:

## Relevant Files
- src/auth/OAuthProvider.ts (create)
- src/auth/index.ts (modify - add export)
- src/config/oauth.ts (create)
- tests/auth/oauth.test.ts (create)

Step 5: Validate Plan Quality

Check against quality criteria before finalizing.

Quality Criteria

Every plan should meet these standards:

Specificity

Bad: "Update the component" Good: "Update UserProfile.tsx to add loading state on line 45"

Actionability

Bad: "Handle errors appropriately" Good: "Add try/catch in fetchUser(), log errors with console.error, show ErrorBoundary"

Completeness

All template sections filled:

  • Description explains what and why
  • Relevant Files lists all files to touch
  • Tasks are numbered and specific
  • Validation Commands are executable
  • Notes capture edge cases

Testability

Every plan must include validation:

## Validation Commands

- Run `npm test -- auth` to verify unit tests pass
- Run `npm run e2e -- oauth` to verify integration
- Manual: Complete OAuth flow in browser

Plan Types and Focus Areas

Chore Plans

Focus on:

  • Clear scope boundaries
  • Idempotent operations
  • Low-risk execution
  • Quick validation

Bug Plans

Focus on:

  • Root cause analysis
  • Reproduction steps
  • Regression prevention
  • Before/after verification

Feature Plans

Focus on:

  • User story alignment
  • Implementation phases
  • Testing strategy
  • Acceptance criteria

Common Issues and Fixes

Vague Tasks

Problem: "Implement the feature" Fix: Break into specific sub-tasks with file references

## Step by Step Tasks
1. Create AuthContext in src/contexts/AuthContext.tsx
2. Add useAuth hook in src/hooks/useAuth.ts
3. Wrap App component with AuthProvider in src/App.tsx
4. Add login route in src/routes/index.tsx

Missing Files

Problem: Plan doesn't mention test files Fix: Always include test file creation/modification

## Relevant Files
- src/components/Login.tsx (create)
- src/components/Login.test.tsx (create) # Tests!

Unclear Validation

Problem: "Make sure it works" Fix: Specific commands with expected outcomes

## Validation Commands
- Run `npm test` - expect 0 failures
- Run `npm run build` - expect successful build
- Run `npm run lint` - expect 0 errors

Scope Creep

Problem: Plan addresses more than requested Fix: Stay focused on original request, note related work in Notes

## Notes
- Related: Login form could use accessibility improvements (separate chore)
- Related: Password reset flow needs similar OAuth option (separate feature)

Extended Thinking Triggers

Note: Extended thinking is enabled by default in Claude Code (31,999 tokens). Phrases like "think", "think hard", "ultrathink" are prompt instructions that signal your expectations but don't control token allocation. Use Alt+T to toggle thinking or MAX_THINKING_TOKENS to adjust budget.

Use "THINK HARD" in meta-prompts as a prompt instruction to signal the need for careful reasoning:

PhraseWhen to Use
"THINK HARD"Medium-to-high complexity, encourage careful reasoning

Output Guidelines

Naming Convention

specs/[type]-[descriptive-name].md

Examples:
- specs/chore-update-dependencies.md
- specs/bug-fix-login-race-condition.md
- specs/feature-oauth-authentication.md

File Location

Always write plans to specs/ directory (or project-specific equivalent).

Format Consistency

Match the template's Plan Format exactly - don't add or remove sections.

Related Memory Files

  • @template-engineering.md - How templates work
  • @meta-prompt-patterns.md - Prompt hierarchy
  • @plan-format-guide.md - Standard plan structures
  • @fresh-agent-rationale.md - Why plan then implement separately

Version History

  • v1.0.0 (2025-12-26): Initial release

Last Updated

Date: 2025-12-26 Model: claude-opus-4-5-20251101

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.39%
按下载量换算26

Claude

28.48%
按下载量换算20

Cursor

21.74%
按下载量换算15

Gemini CLI

10.97%
按下载量换算8

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills