GSD Core
Provides a structured, spec-driven methodology for Claude Code interactions that reduces ambiguity and iteration cycles.
Community-run successor to the abandoned Get Shit Done (GSD) meta-prompting / spec-driven development system for Claude Code. Fork rescued by top contributors after the original author vanished; crypto token explicitly disavowed. Actively maintained.
- Ask Claude to generate structured task specifications from vague project requirements using GSD templates.
- Automate code generation workflows by feeding Claude detailed specs with built-in quality checks and validation.
- Break down complex engineering projects into executable steps with clear acceptance criteria for team handoff.
Provides a structured, spec-driven methodology for Claude Code interactions that reduces ambiguity and iteration cycles. Community maintenance ensures ongoing compatibility and reduces dependency risk from abandoned projects.
Engineering teams using Claude Code for feature development or refactoring who need repeatable, specification-first workflows.
How to Get It
This is a methodology or approach — no installation needed. See the Source link above for the full steps, or paste the source URL into Claude and ask it to summarise the recipe and help you apply it.
After installing, paste this into Claude:
Generate structured task specifications from vague project requirements using GSD templates
Trust Signals Auto-scanned
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 6,358 GitHub stars; contributors unknown; last commit 0d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 6,358 GitHub stars; contributors unknown; last commit 0d ago; license MIT.