Token导航 LogoToken导航TokenDH.com
开发只读github未标认证来源可访问许可证需确认审计通过

task-generation任务生成

Agent Skill

task-generation 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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

225

周安装

9

GitHub Stars

10

下载量

73
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:task-generation(任务生成)
来源仓库:https://github.com/aspiers/ai-config
仓库路径:skills/task-generation
安装命令:
npx skills add https://github.com/aspiers/ai-config --skill task-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/aspiers/ai-config --skill task-generation

简介

task-generation 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息。

  • 适合在 Codex、Claude、Cursor、Gemini CLI 中围绕仓库状态、代码变更或协作事项进行整理。
  • 通过 npx skills add 命令从指定 GitHub 仓库安装,需结合原始 README 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操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Task Generation

Generate a detailed, step-by-step task list in Markdown format based on an existing Product Requirements Prompt (PRP).

When to Use This Skill

Use this skill when:

  • A PRP exists at .ai/[feature-name]/prp.md
  • You need to break down the feature into implementable tasks
  • Planning how a junior developer will implement the feature

Input

  • feature_name - Locates the PRP at .ai/[feature-name]/prp.md

Process

  1. Receive PRP Reference: The user points to a specific PRP file
  2. Analyze PRP: Read and analyze the functional requirements, user stories, and other sections
  3. Clarify Open Questions: If there are still any open questions, ask the user for clarification and amend the PRP accordingly before proceeding
  4. Phase 1: Generate Parent Tasks: Based on the PRP analysis, create the main high-level tasks (3-8 parent tasks). Present these to the user in the specified format (without sub-tasks yet). Inform: "I have generated the high-level tasks. Ready to generate sub-tasks? Respond with 'go' to proceed."
  5. Wait for Confirmation: Pause and wait for the user to respond with "go"
  6. Phase 2: Generate Sub-Tasks: Once confirmed, break down each parent task into smaller, actionable sub-tasks
  7. Identify Relevant Files: Based on tasks and PRP, identify potential files that need creation or modification
  8. Generate Final Output: Combine parent tasks, sub-tasks, relevant files, and notes
  9. Save Task List: Save to .ai/[feature-name]/tasks.md
  10. Commit Task List: Stage and commit the new task list

Commit Message Template

feat: add .ai/[feature-name]/tasks.md

Generate tasks according to .ai/[feature-name]/prp.md

Output Format

The tasks.md file *must* follow this structure:

# Context

See [prp.md][./prp.md] for the corresponding Product Requirements Prompt.

# Relevant Files

- `path/to/file1.ts` - Brief description of why this file is relevant
- `path/to/file1.test.ts` - Unit tests for `file1.ts`
- `path/to/another/file.tsx` - Brief description
- `path/to/another/file.test.tsx` - Unit tests for `another/file.tsx`
- `lib/utils/helpers.ts` - Utility functions needed for calculations
- `lib/utils/helpers.test.ts` - Unit tests for helpers.ts

# Tasks

- [ ] 1. Parent Task Title
  - [ ] 1.1. Sub-task description 1.1
  - [ ] 1.2. Sub-task description 1.2

- [ ] 2. Parent Task Title
  - [ ] 2.1. Sub-task description 2.1

- [ ] 3. Parent Task Title (may not require sub-tasks)

Target Audience

Assume the primary reader is a junior developer who will implement the feature. Tasks should be clear, actionable, and provide enough context for someone less familiar with the codebase to complete them.

Interaction Model

The process explicitly requires a pause after generating parent tasks to get user confirmation ("Go") before proceeding to generate detailed sub-tasks. This ensures the high-level plan aligns with user expectations.

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

37.49%
按下载量换算27

Claude

26.77%
按下载量换算20

Cursor

17.74%
按下载量换算13

Gemini CLI

8.34%
按下载量换算6

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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