Token导航 LogoToken导航

Agent Skill · 开发

gsdl-create-plan(gsdl 创建计划)

gsdl-create-plan 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。

gsdl-create-plan 是开发类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 13,855。

总安装 808周安装 33GitHub Stars 3下载 259核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

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:gsdl-create-plan(gsdl 创建计划)
来源仓库:https://github.com/nsantini/gsdl
仓库路径:skills/gsdl-create-plan
安装命令:
npx skills add https://github.com/nsantini/gsdl --skill gsdl-create-plan
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/nsantini/gsdl --skill gsdl-create-plan

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

gsdl-create-plan 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时使用。

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。

来源仓库内路径:skills/gsdl-create-plan

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/nsantini/gsdl --skill gsdl-create-plan;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

gsdl-create-plan 怎么安装?

在终端执行 npx skills add https://github.com/nsantini/gsdl --skill gsdl-create-plan。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

gsdl-create-plan 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

gsdl-create-plan 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

gsdl-create-plan 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

gsdl-create-plan 用的人多吗?

公开数据是累计安装 808 次,近一周安装 33 次,下载 259 次,GitHub 3 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

gsdl-create-plan 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
gsdl-create-plan

gsdl 创建计划 · 本页

8083接触敏感数据未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Generate Task List from PRD

Generates a detailed, step-by-step task list in Markdown format based on an existing Product Requirements Document (PRD). The task list guides a developer through implementation with parent tasks and detailed sub-tasks.

Prerequisites

Before generating a task list:

  1. Project exists: The project should have its own folder at .planning/[project-name]/
  2. PRD exists: Ensure the PRD file exists at .planning/[project-name]/prd-[feature-name].md

Output

The task list will be saved as:

  • Format: Markdown (.md)
  • Location: .planning/[project-name]/
  • Filename: tasks-[prd-file-name].md (e.g., tasks-prd-user-profile-editing.md)
  • Full Path Example: .planning/my-cool-project/tasks-prd-user-authentication.md

Two-Phase Process

This skill follows a two-phase workflow to ensure alignment before diving into details.

Phase 1: Generate Parent Tasks

  1. Receive PRD Reference: The user points to a specific PRD file
  2. Read PRD from disk: Read the PRD file directly from disk at its path — do not rely on any in-context version. The user may have edited the file since it was generated.
  3. Analyze PRD: Analyze the functional requirements, user stories, and other sections from the file just read
  4. Create Parent Tasks: Generate 5-7 high-level tasks required to implement the feature
  5. Present to User: Show the parent tasks in the specified format (without sub-tasks yet)
  6. Pause for Confirmation: Inform the user: "I have generated the high-level tasks based on the PRD. Review the tasks above — feel free to edit the PRD or suggest changes before we continue. Respond with 'Go' to generate the sub-tasks."

Phase 2: Generate Sub-Tasks

  1. Wait for "Go": Only proceed after the user confirms with "Go"
  2. Re-read PRD from disk: Before generating sub-tasks, read the PRD file from disk again to pick up any edits the user may have made since Phase 1
  3. Break Down Tasks: For each parent task, create smaller, actionable sub-tasks based on the current PRD content
  4. Identify Files: List potential files that will need to be created or modified
  5. Generate Final Output: Combine everything into the complete task list structure
  6. Save Task List: Save to the project's tasks directory

Task List Structure

The generated task list must follow this exact format:

## Relevant Files

- `src/path/to/potential/file1.ts` - Brief description of why this file is relevant (e.g., Contains the main component for this feature).
- `src/path/to/file1.test.ts` - Unit tests for `file1.ts`.
- `src/path/to/another/file.tsx` - Brief description (e.g., API route handler for data submission).
- `src/path/to/another/file.test.tsx` - Unit tests for `another/file.tsx`.
- `lib/utils/helpers.ts` - Brief description (e.g., Utility functions needed for calculations).
- `lib/utils/helpers.test.ts` - Unit tests for `helpers.ts`.

### Notes

- Implementation file paths are relative to the workspace root (e.g., `src/components/MyComponent.tsx`). Planning files (PRDs, task lists) live under `.planning/[project-name]/`.
- Unit tests should typically be placed alongside the code files they are testing (e.g., `MyComponent.tsx` and `MyComponent.test.tsx` in the same directory).
- Use `npx jest [optional/path/to/test/file]` to run tests. Running without a path executes all tests found by the Jest configuration.

## Tasks

- [ ] 1.0 Parent Task Title
  - [ ] 1.1 [Sub-task description 1.1]
  - [ ] 1.2 [Sub-task description 1.2]
- [ ] 2.0 Parent Task Title
  - [ ] 2.1 [Sub-task description 2.1]
- [ ] 3.0 Parent Task Title (may not require sub-tasks if purely structural or configuration)

Task Breakdown Guidelines

Parent Tasks

  • Create 5-7 high-level tasks that represent major implementation phases
  • Use numbered format: 1.0, 2.0, 3.0, etc.
  • Each parent task should represent a significant milestone
  • Examples: "Set up project structure", "Implement core functionality", "Add validation and error handling"

Sub-Tasks

  • Break each parent task into specific, actionable items
  • Use nested numbering: 1.1, 1.2, 1.3 under parent 1.0
  • Each sub-task should be concrete and implementable
  • Sub-tasks should logically follow from the parent task
  • Not all parent tasks require sub-tasks (e.g., simple configuration tasks)

Relevant Files

  • List every file that will be created or modified
  • Include both implementation files and test files
  • Use full paths relative to workspace root
  • Provide a brief description for each file explaining its purpose
  • Group related files together (implementation + tests)

Target Audience

The task list is designed for a junior developer who will implement the feature. Tasks should be:

  • Clear and specific
  • Implementable without extensive guidance
  • Ordered logically to build up the feature step by step

Interaction Model

IMPORTANT: This skill requires user confirmation between phases:

  1. Generate parent tasks → Show to user → Wait for "Go"
  2. User responds with "Go" → Generate sub-tasks and complete the file

Do not proceed to Phase 2 until the user explicitly confirms the parent tasks are correct.

Examples

Phase 1 Output (Parent Tasks Only)

## Tasks

- [ ] 1.0 Set up authentication module structure
- [ ] 2.0 Implement user login functionality
- [ ] 3.0 Implement user registration
- [ ] 4.0 Add session management
- [ ] 5.0 Create authentication UI components
- [ ] 6.0 Add error handling and validation
- [ ] 7.0 Write tests and documentation

Phase 2 Output (Complete with Sub-Tasks)

## Relevant Files

- `src/auth/login.ts` - Login endpoint handler
- `src/auth/login.test.ts` - Tests for login functionality
[... more files ...]

## Tasks

- [ ] 1.0 Set up authentication module structure
  - [ ] 1.1 Create auth directory structure
  - [ ] 1.2 Set up authentication configuration
  - [ ] 1.3 Install required dependencies
- [ ] 2.0 Implement user login functionality
  - [ ] 2.1 Create login endpoint
  - [ ] 2.2 Implement credential validation
  - [ ] 2.3 Generate and return JWT token
[... more tasks ...]

平台分布

Codex

34.63%
按下载量换算90

Claude

30.08%
按下载量换算78

Cursor

19.49%
按下载量换算50

Gemini CLI

9.01%
按下载量换算23

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills