Token导航 LogoToken导航TokenDH.com
研究检索需要联网github未标认证来源可访问clear审计异常

gsdGSD 搜索

Agent Skill

gsd 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

33,936

周安装

1,355

GitHub Stars

6

下载量

11,088
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

3

许可证

MIT

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:gsd(GSD 搜索)
来源仓库:https://github.com/ctsstc/get-shit-done-skills
仓库路径:skills/gsd
安装命令:
npx skills add https://github.com/ctsstc/get-shit-done-skills --skill gsd
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。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/ctsstc/get-shit-done-skills --skill gsd

简介

面向独立开发人员的结构化项目管理系统,使用 Claude 代理来规划、执行和交付软件。

  • 提供 19 多个命令,涵盖项目初始化、阶段规划/执行、代码库映射、调试和验证工作流程
  • 通过原子提交、并行执行波和上下文预算将工作组织到目标后向阶段以保持质量
  • 生成.planning/
  • 包含项目上下文、需求、路线图、阶段工件和代码库分析的目录结构
  • 包括 11 个专门代理,用于整个项目生命周期的规划、执行、调试、验证、研究和集成检查

SKILL.md

Get Shit Done (GSD) - Project Management System

A comprehensive project management system designed for solo developers working with Claude AI agents. GSD provides structured workflows for project initialization, planning, execution, verification, and debugging.

Overview

GSD is a modular agent-based system that transforms project ideas into shipped software through:

  1. Deep questioning - Extract user vision and requirements
  2. Domain research - Discover standard stacks and patterns
  3. Roadmap creation - Break requirements into phases
  4. Phase planning - Create executable plans with verification
  5. Execution - Implement plans with atomic commits
  6. Verification - Ensure goals are achieved, not just tasks done
  7. Debugging - Systematic investigation of issues

Core Philosophy

  • Solo Developer + Claude Workflow - No teams, no stakeholders, no ceremonies
  • Plans are Prompts - PLAN.md files ARE the execution prompts, not documents
  • Goal-Backward Planning - Start from what must be TRUE, derive what to build
  • Atomic Commits - Each task commits independently for clean history
  • Quality Over Speed - Stop before context degrades (~50% usage)
  • Ship Fast - Plan → Execute → Ship → Learn → Repeat

When to Use GSD

Use GSD when you need to:

  • Initialize a new software project
  • Plan and execute development phases
  • Map an existing codebase
  • Debug issues systematically
  • Verify phase completion
  • Track project progress and state

Quick Start Commands

New Project

/gsd:new-project

Initializes a new project with questioning → research → requirements → roadmap flow.

Plan a Phase

/gsd:plan-phase [phase-number]

Creates detailed execution plans with research and verification.

Execute a Phase

/gsd:execute-phase [phase-number]

Executes all plans in a phase with parallel execution support.

Map Codebase

/gsd:map-codebase [optional-focus-area]

Analyzes existing codebase with parallel mapper agents.

Debug Issues

/gsd:debug [issue-description]

Systematic debugging using scientific method and hypothesis testing.

Verify Phase

/gsd:verify-work [phase-number]

Goal-backward verification of phase completion.

Check Progress

/gsd:progress

Shows current project position, completed phases, and next steps.

Agent Skills

GSD includes specialized agents for different tasks:

  • gsd-codebase-mapper - Explores and documents codebase structure
  • gsd-planner - Creates executable phase plans
  • gsd-executor - Executes plans with atomic commits
  • gsd-debugger - Investigates bugs systematically
  • gsd-verifier - Verifies goal achievement
  • gsd-research-synthesizer - Synthesizes research outputs
  • gsd-roadmapper - Creates project roadmaps
  • gsd-phase-researcher - Researches phase implementation
  • gsd-project-researcher - Researches domain ecosystem
  • gsd-integration-checker - Verifies integrations work
  • gsd-plan-checker - Validates plan quality

Command Skills

GSD provides commands for orchestrating the entire project lifecycle:

  • gsd:new-project - Initialize new project
  • gsd:map-codebase - Map existing codebase
  • gsd:plan-phase - Plan a phase
  • gsd:execute-phase - Execute a phase
  • gsd:verify-work - Verify phase completion
  • gsd:debug - Debug issues
  • gsd:discuss-phase - Gather phase context
  • gsd:research-phase - Research phase implementation
  • gsd:complete-milestone - Complete milestone
  • gsd:audit-milestone - Audit milestone
  • gsd:add-phase - Add new phase
  • gsd:insert-phase - Insert phase
  • gsd:remove-phase - Remove phase
  • gsd:add-todo - Add todo item
  • gsd:check-todos - Check todos
  • gsd:plan-milestone-gaps - Plan milestone gaps
  • gsd:pause-work - Pause work
  • gsd:resume-work - Resume work
  • gsd:update - Update project state
  • gsd:whats-new - Show what's new

Workflow Skills

Detailed workflow definitions for complex operations:

  • discovery-phase - Phase discovery workflow
  • execute-phase - Phase execution workflow
  • diagnose-issues - Parallel UAT diagnosis
  • map-codebase - Codebase mapping workflow
  • discuss-phase - Phase discussion workflow
  • verify-phase - Phase verification workflow
  • verify-work - Work verification workflow
  • transition - Phase transition workflow
  • resume-project - Project resumption workflow

Reference Skills

Reference documents for best practices and guidelines:

  • questioning - Deep questioning techniques
  • tdd - Test-driven development patterns
  • ui-brand - UI/UX guidelines
  • verification-patterns - Verification methodologies
  • git-integration - Git workflow patterns
  • checkpoints - Checkpoint handling
  • continuation-format - Continuation format specification

Project Structure

GSD creates a .planning/ directory with:

.planning/
├── PROJECT.md           # Project context and vision
├── config.json          # Workflow preferences
├── REQUIREMENTS.md      # Scoped requirements
├── ROADMAP.md          # Phase structure
├── STATE.md            # Project memory and state
├── research/            # Domain research outputs
├── phases/              # Phase-specific artifacts
│   ├── XX-name/
│   │   ├── XX-PLAN.md
│   │   ├── XX-SUMMARY.md
│   │   ├── XX-CONTEXT.md
│   │   ├── XX-RESEARCH.md
│   │   ├── XX-VERIFICATION.md
│   │   └── XX-UAT.md
└── codebase/            # Codebase analysis
    ├── STACK.md
    ├── ARCHITECTURE.md
    ├── STRUCTURE.md
    ├── CONVENTIONS.md
    ├── TESTING.md
    ├── INTEGRATIONS.md
    └── CONCERNS.md

Key Concepts

Goal-Backward Planning

Instead of asking "what should we build?", ask "what must be TRUE for the goal to be achieved?"

Forward: "Build authentication system" → task list Goal-Backward: "Users can securely access accounts" → derive what must exist

Atomic Commits

Each task commits independently with descriptive messages:

feat(01-01): implement user login
fix(01-02): fix password validation
test(01-03): add login tests

Context Budgeting

Plans complete within ~50% context usage to maintain quality:

  • 0-30%: PEAK quality
  • 30-50%: GOOD quality
  • 50-70%: DEGRADING quality
  • 70%+: POOR quality (avoid)

Wave-Based Execution

Plans are grouped into waves for parallel execution:

  • Wave 1: Independent plans (no dependencies)
  • Wave 2: Plans depending only on Wave 1
  • Wave 3: Plans depending on Wave 2, etc.

Anti-Patterns to Avoid

  • Enterprise PM Theater - No RACI matrices, sprint ceremonies, stakeholder management
  • Horizontal Layers - Don't group by "all models, then all APIs" - group by features
  • Vague Success Criteria - "Authentication works" → "User can log in with email/password"
  • Time Estimates - Never estimate in hours/days/weeks
  • Task Completion ≠ Goal Achievement - Verify outcomes, not just task completion

Getting Help

Each agent, command, and workflow has its own SKILL.md with detailed instructions. Use:

  • @skills/gsd/agents/ for agent-specific help
  • @skills/gsd/commands/ for command-specific help
  • @skills/gsd/workflows/ for workflow-specific help
  • @skills/gsd/references/ for reference documentation

Version

GSD Version: 1.0.0 Last Updated: 2026-01-19

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

Claude Code

26.91%
按下载量换算2,984

Codex

22.64%
按下载量换算2,510

OpenCode

15.45%
按下载量换算1,713

Antigravity

12.65%
按下载量换算1,403

Gemini CLI

7.59%
按下载量换算842

Cursor

3.23%
按下载量换算358

安全审计

Gen Agent Trust Hub

未通过

Socket

通过

Snyk

可疑

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。

来源信息

继续浏览同类 Skills