Agent skill

Gsd

by allgpt-co in allgpt-co/QuickVoice

Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents

MITAuto-check passedProduct & Project Management

Install Gsd

skills CLI
$ npx skills add allgpt-co/QuickVoice --skill gsd -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install allgpt-co/QuickVoice gsd --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/allgpt-co/QuickVoice.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/gsd .claude/skills/gsd && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gsd
GitHub stars
488
Token cost
~2k tokens
SKILL.md length
694 words
Files
5
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents

  • Works in 7 steps: Deep questioning - Extract user vision… → Domain research - Discover standard… → Roadmap creation - Break requirements… → …
  • Tasks that involve Project management
  • SKILL.md covers Overview, Core Philosophy, When to Use GSD and Quick Start Commands, plus 9 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gsd is an agent skill from allgpt-co/QuickVoice. Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files.

It sits in Product & Project Management, covering Project management. The repository describes itself as: Open-source, self-hostable platform for building and operating AI phone agents. The licence is MIT.

When your agent uses it

  • Tasks that involve Project management

Example prompts

  • “/gsd”

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  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

What it can do on your machine

Read from SKILL.md and the folder at commit 89fa8ff. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gsd loads about 2k tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 694 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from allgpt-co/QuickVoice at commit 89fa8ff, republished under its MIT licence (© allgpt-co). 694 words, ~1,951 tokens.

Download SKILL.mdSave it as .claude/skills/gsd/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
gsd
description
Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents
version
1.0.0
author
GSD Project
tags
project-management, agents, workflows, planning, execution
triggers
new project, plan phase, execute phase, map codebase, debug, verify
tools
Read, Write, Edit, Bash, Glob, Grep, Task, AskUserQuestion

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
bash
/gsd:new-project

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

Plan a Phase
bash
/gsd:plan-phase [phase-number]

Creates detailed execution plans with research and verification.

Execute a Phase
bash
/gsd:execute-phase [phase-number]

Executes all plans in a phase with parallel execution support.

Map Codebase
bash
/gsd:map-codebase [optional-focus-area]

Analyzes existing codebase with parallel mapper agents.

Debug Issues
bash
/gsd:debug [issue-description]

Systematic debugging using scientific method and hypothesis testing.

Verify Phase
bash
/gsd:verify-work [phase-number]

Goal-backward verification of phase completion.

Check Progress
bash
/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
Show full SKILL.md (280 more words)Show less

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:

bash
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

© allgpt-co, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in .claude/skills/gsd of allgpt-co/QuickVoice.

  • SKILL.md
  • agents
  • commands
  • references
  • workflows

Open the folder on GitHubat commit 89fa8ff

Compare with similar skills

Gsd next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gsd compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gsd this skillallgpt-co/QuickVoice488—~2kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Uvastral-sh/claude-code-plugins3132 repos~980Automated safety check: PassApache-2.0
Project Managementkunchenguid/firstmate7.8k—~2.1kAutomated safety check: PassMIT
Hivemind Goalsactiveloopai/hivemind1.6k—~1.7kAutomated safety check: NotesApache-2.0
Ichartjswanghetommy/ichartjs352—~4.3kAutomated safety check: PassApache-2.0

Similar skills

  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Uv

    astral-sh/claude-code-plugins

    Official

    Guide for using uv, the Python package and project manager. An agent skill from astral-sh/claude-code-plugins.

    313 GitHub starsUsed in 2 repos~980 tokens
    Product & Project ManagementAuto-check passed
  • Project Management

    kunchenguid/firstmate

    Agent-only procedure for Firstmate project management. An agent skill from kunchenguid/firstmate.

    7.8k GitHub stars~2.1k tokensUpdated today
    Product & Project ManagementAuto-check passed
  • Hivemind Goals

    activeloopai/hivemind

    Create, track and update team goals via the Deeplake virtual filesystem at memory/goal/.

    1.6k GitHub stars~1.7k tokensUpdated 12 days ago
    Product & Project ManagementAuto-check: notes
  • Ichartjs

    wanghetommy/ichartjs

    Plan, validate, render, explain, and safely edit iChart.js visualizations from tabular, project, or diagram data.

    352 GitHub stars~4.3k tokensUpdated yesterday
    Product & Project ManagementAuto-check passed
  • Hivemind Goals

    activeloopai/hivemind

    Create, track and update team goals in Hivemind via the hivemind CLI.

    1.6k GitHub stars~814 tokensUpdated 12 days ago
    Product & Project ManagementAuto-check passed

More from allgpt-co/QuickVoice

All 12 skills in this repo
  • Livekit Agents

    allgpt-co/QuickVoice

    Build voice AI agents with LiveKit Cloud and the Agents SDK.

    488 GitHub stars~3.3k tokensUpdated 4 days ago
    Auto-check: notes
  • Gsd Codebase Mapper

    allgpt-co/QuickVoice

    Explores codebase and writes structured analysis documents. An agent skill from allgpt-co/QuickVoice.

    488 GitHub stars~3.5k tokensUpdated 4 days ago
    Auto-check: notes
  • Gsd Integration Checker

    allgpt-co/QuickVoice

    Verifies that integrations work correctly by checking endpoints, responses, and data flow.

    488 GitHub stars~2.8k tokensUpdated 4 days ago
    Auto-check passed
  • Gsd Phase Researcher

    allgpt-co/QuickVoice

    Researches phase implementation for planning. An agent skill from allgpt-co/QuickVoice.

    488 GitHub stars~1.9k tokensUpdated 4 days ago
    Auto-check passed
  • Gsd Plan Checker

    allgpt-co/QuickVoice

    Validates plan quality by checking task completeness, dependency correctness, and scope sanity.

    488 GitHub stars~2.5k tokensUpdated 4 days ago
    Auto-check passed
  • Gsd Executor

    allgpt-co/QuickVoice

    Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management.

    488 GitHub stars~4.7k tokensUpdated 4 days ago
    Auto-check: warnings

Questions about Gsd

What does Gsd do?

Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents. Gsd is an agent skill from allgpt-co/QuickVoice.

When should I use Gsd?

Gsd fits situations like: tasks that involve Project management.

How do I install Gsd in Claude Code?

Run `npx skills add allgpt-co/QuickVoice --skill gsd -a claude-code`. Or copy the skill folder (.claude/skills/gsd in allgpt-co/QuickVoice) into .claude/skills/gsd in your project. Claude Code loads it when a task matches its description.

How do I install Gsd in Codex?

Run `npx skills add allgpt-co/QuickVoice --skill gsd -a codex`. Or copy the skill folder (.claude/skills/gsd in allgpt-co/QuickVoice) into .agents/skills/gsd in your project. Codex loads it when a task matches its description.

Can I use Gsd in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add allgpt-co/QuickVoice --skill gsd -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gsd, .gemini/skills/gsd, .github/skills/gsd and .opencode/skills/gsd in your project.

What does Gsd need to run?

SKILL.md names no scripts, command-line tools or credentials: Gsd is instructions for the agent only.

Does Gsd access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Gsd safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gsd use?

Gsd is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gsd use?

About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gsd?

Skills that share tags, products or a category with Gsd: CCPM Project Management (automazeio/ccpm, 8.4k stars), Uv (astral-sh/claude-code-plugins, 313 stars), Project Management (kunchenguid/firstmate, 7.8k stars) and Hivemind Goals (activeloopai/hivemind, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gsd?

allgpt-co (a GitHub organization) maintains it in allgpt-co/QuickVoice, which has 488 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 5, 2026.

Source: allgpt-co/QuickVoice on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.