Spec-driven development with built-in verification for substantial projects. Use when user wants to plan a project, scope a feature, build something with structure, or says "GSD mode", "let's plan", "scope out", "spec-driven". Workflow is Discuss → Plan → Execute → Verify. Based on glittercowboy's GSD system (MIT license). NOT for quick questions or simple tasks.
Security Analysis
high confidenceThe skill is an instruction-only implementation of a spec-driven development workflow (GSD); its requested actions and files are coherent with that purpose and it does not ask for credentials or perform any suspicious network or install actions.
Name/description match the provided instructions and file templates. The SKILL.md and assets define a project planning → execution → verification workflow; all required artifacts (plans, context, summaries) are present. There are no declared environment variables, binaries, or installs that contradict the stated purpose.
Instructions direct the agent to create and write files under {project}/.gsd/, spawn sub-agents for research and execution, run 'verify' commands, and commit changes 'if applicable'. These actions are expected for an execution-capable project workflow but do give the agent discretionary access to the workspace and to run commands. The SKILL.md does not attempt to read secrets or unusual system paths, nor does it specify external endpoints. Users should be aware the skill intends to modify project files and may run commands (e.g., tests, verification scripts).
Instruction-only skill with no install spec and no code files to execute. This minimizes install-time risk; nothing is downloaded or written by an installer.
The skill requests no environment variables, no credentials, and no config paths. This is proportionate for a local project planning/execution tool. Note: the instructions implicitly assume common developer tooling (git, test runners) may be available but none are required as declared environment items.
always is false and the skill does not request persistent elevated privileges or modification of other skills. It intends to create a .gsd directory inside project workspaces (normal for a project-oriented skill). Autonomous invocation is allowed by default but not excessive here.
Guidance
This skill is an instruction-only manifest of the GSD workflow and appears internally consistent. Before installing or enabling it, be aware: (1) it will create and modify files under your project (a {.gsd} directory) and may commit changes — ensure the agent has only the repository/workspace access you intend; (2) it can spawn sub-agents and run verification commands (tests, file checks), so make sure your environment's test/CI tooling and any commands the skill runs are safe and do not have access to secrets; (3) the SKILL.md assumes typical developer tools (git, test runners) but does not declare them — verify those tools are present and that you consent to commits or other side effects; (4) because it requests no credentials and has no install step, there's no obvious network/data-exfiltration vector in the provided files, but review generated .gsd outputs and verification commands before accepting automated commits or deployments. If you want lower risk, run this skill in an isolated workspace or require manual approval before any commit or external action.
Latest Release
v1.0.2
Fixed display name to GSD Claw
More by @RubenAQuispe
Published by @RubenAQuispe on ClawHub
