gsdclawSpec-first execution workflow for OpenClaw that turns large, vague, or messy project requests into phased, verifiable implementation plans. Helps build, resc...
Install via ClawdBot CLI:
clawdbot install cirokk/gsdclawGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/gsd-build/get-shit-doneAudited Apr 18, 2026 · audit v1.0
Generated Oct 6, 2026
A solo founder has a messy codebase with duplicated entrypoints, truncated files, and no clear build path. GSD-Claw maps the current state, identifies the canonical entrypoint, restores a minimal working baseline, and defines phased acceptance criteria. The founder gets a stable demo path in days instead of a full rewrite.
A product manager passes down a broad request like 'add team workspaces with billing and permissions.' GSD-Claw converts it into an execution spec with objectives, quality bar, exclusions, and a practical v1. Phases separate data model, UI/config capture, persistence, and connection/runtime integration so scope does not drift.
An operations team is stuck on a tangled admin dashboard with inconsistent UI and duplicate components. GSD-Claw stabilizes the current project, consolidates architecture, prioritizes information architecture and usability before visual polish, and verifies each phase with build and rendering checks.
A developer tool needs a settings area for AI, messaging, and payment providers. GSD-Claw models the feature as provider selector, credential fields, help instructions, save state, connection test, then runtime usage. It clearly distinguishes simulated integration from real integration in validation notes.
A freelance developer inherited a half-built app from another contractor with broken paths and unclear status. GSD-Claw enters rescue mode, chooses what to keep, removes dead paths, and reports real status with done/in-progress/blocked/next. The client receives an honest completion plan instead of optimistic claims.
Offer fixed-scope rescue engagements where messy, stalled, or broken codebases are stabilized using the GSD-Claw workflow. Package discovery, baseline restoration, and phased completion as clearly priced tiers with acceptance criteria. Differentiates from hourly consulting by promising verifiable working baselines.
Build a hosted tool that embeds GSD-Claw-style execution templates, phase tracking, acceptance checklists, and verification logs. Teams use it to convert vague requests into build specs and track done/in-progress/blocked/next status across projects. Monetize via seat-based subscriptions with workflow automation.
Sell courses, playbooks, and reusable reference templates that teach teams the GSD-Claw spec-first workflow for scoping, phasing, and verifying medium-to-large projects. Include downloadable execution templates, acceptance checklists, and case studies from rescues and redesigns. Monetize through one-time purchases and cohort-based workshops.
💬 Integration Tip
Keep GSD-Claw as an instruction-only layer that reads project files and produces specs and checklists without requiring credentials or external APIs. When adding provider or API integrations, enforce the workflow order of UI/config capture, persistence, connection test, then runtime usage, and clearly label simulated versus real integrations in your reports.
Scored Oct 6, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.