GSD is a comprehensive AI-driven workflow for taking projects from initial concept to verified execution through systematic planning and parallelized research.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install glittercowboy
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install glittercowboy using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
GSD (Get Shit Done) is a sophisticated project management system designed for AI coding agents to handle the entire project lifecycle. It transforms vague ideas into structured reality by employing a multi-agent architecture that covers everything from initial context gathering to final feature verification. As a core part of the Openclaw Skills ecosystem, GSD ensures that developers don't just write code, but build well-researched, architecturally sound, and thoroughly tested software through a disciplined, phased approach.
The skill utilizes an orchestrator-subagent pattern to maintain a lean main context while delegating specialized tasks like domain research, roadmap creation, and parallel execution to focused sub-agents. This ensures high-quality output and prevents the "context drift" often seen in long-running AI development sessions. Whether you are starting a new greenfield project or managing a complex brownfield codebase, GSD provides the framework to maintain momentum and technical integrity.
To use GSD within your environment, ensure the Openclaw Skills framework is active. You can trigger the primary initialization workflow using the following command:
/gsd new-project
For existing projects where you want to check status or resume work, use:
/gsd progress
GSD maintains project state and artifacts within a structured .planning/ directory to ensure transparency and persistence.
| Artifact | Purpose |
|---|---|
PROJECT.md |
The source of truth for project vision and high-level status. |
REQUIREMENTS.md |
Defined scope, feature lists, and v1 must-haves. |
ROADMAP.md |
The phased execution timeline derived from research. |
SUMMARY.md |
Synthesized findings from the parallel research agents. |
plans/ |
A directory containing individual execution plans and task logs. |
Loading
PinchBench is a comprehensive benchmarking suite designed to measure the performance and accuracy of Openclaw Skills across various real-world tasks.

A professional stock valuation framework using ROIC and CAPM to determine intrinsic value and investment risk.

A high-performance NFT minting bot for Ethereum and EVM chains designed for sub-100ms execution and multi-wallet orchestration.

Clawland enables AI agents to play on-chain odd/even games on the Solana devnet by minting GEM tokens from SOL or USDC.

A complete end-to-end AI agent workflow for taking projects from initial idea to verified execution through systematic planning and research.

A comprehensive automation skill for LimeSurvey that enables full lifecycle management of surveys, participants, and data via the RemoteControl 2 API.








































