No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by gsd-build · Claude Skill · ★ 64.5k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is get-shit-done safe to install? View the security audit →
GET SHIT DONE A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code, OpenCode, Gemini CLI, and Codex. Solves context rot — the quality degradation that happens as Claude fills its context window. [](https://de
| Stars | 64,514 |
| Forks | 5,452 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 68.7874760276591/100 |
| Last Updated | 2026-05-31 |
| Created | 2025-12-14 |
| Platforms | claude-code, node |
| Est. Tokens | ~1284k |
Looking for a get-shit-done alternative? If you're comparing get-shit-done with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
from vibe coding to agentic engineering - practice makes claude perfect
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answer
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, sessio
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your a
程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Pr
Explore other popular claude skill tools:
get-shit-done is A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.. It is categorized as a Claude Skill with 64.5k GitHub stars.
get-shit-done is primarily written in JavaScript. It covers topics such as claude-code, context-engineering, meta-prompting.
You can find installation instructions and usage details in the get-shit-done GitHub repository at github.com/gsd-build/get-shit-done. The project has 64.5k stars and 5452 forks, indicating an active community.
get-shit-done is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to get-shit-done on Agent Skills Hub include claude-code-best-practice, headroom, planning-with-files. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: