A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
GSD (Get Shit Done) is a meta-prompting, context engineering, and spec-driven development system built specifically for Claude Code. It provides a structured workflow where developers define specifications and context before coding begins, letting Claude Code operate with clearer intent and fewer correction cycles. The system uses prompt engineering techniques to shape how Claude interprets tasks, manages project context, and follows development specifications throughout a session. It targets developers who work regularly with Claude Code and want more consistent, directed output without manually re-explaining project constraints each time. The repository itself is now archived and redirects to the active successor project, GSD Core, hosted at the Open GSD organization on GitHub, where ongoing development, issue tracking, and releases continue. Anyone looking to use or contribute to the tool should work from that new location rather than this original repository.
Meta-prompting and spec-driven development system for Claude Code with multiple agent CLIs.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
git clone https://github.com/gsd-build/get-shit-doneTools overview
<!-- GSD 2 - Archived repository redirect --> # GSD Has Moved This repository is no longer the active home for GSD development. The project now continues as **GSD Core** in the Open GSD repository: https://github.com/open-gsd/gsd-core Use the new repository for current source code, issues, releases, and contribution work.
What people ask about get-shit-done
What is gsd-build/get-shit-done?
+
gsd-build/get-shit-done is tools for the Claude AI ecosystem. A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES. It has 64.2k GitHub stars and was last updated 12d ago.
How do I install get-shit-done?
+
You can install get-shit-done by cloning the repository (https://github.com/gsd-build/get-shit-done) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is gsd-build/get-shit-done safe to use?
+
Our security agent has analyzed gsd-build/get-shit-done and assigned a Trust Score of 73/100 (tier: OK). See the full breakdown of passed checks and flags on this page.
Who maintains gsd-build/get-shit-done?
+
gsd-build/get-shit-done is maintained by gsd-build. The last recorded GitHub activity is from 12d ago, with 7 open issues.
Are there alternatives to get-shit-done?
+
Yes. On ClaudeWave you can browse similar tools at /categories/tools, sorted by popularity or recent activity.
Deploy get-shit-done to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/gsd-build-get-shit-done)<a href="https://claudewave.com/repo/gsd-build-get-shit-done"><img src="https://claudewave.com/api/badge/gsd-build-get-shit-done" alt="Featured on ClaudeWave: gsd-build/get-shit-done" width="320" height="64" /></a>More Tools
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]