All authors
Claude Skills by georgesmomo
github.com/georgesmomo16 skills0 installs17 views
- Analyze RequirementsTurn a need into testable acceptance criteria in Given/When/Then, with edge cases enumerated.Votes: 0GitHub stars: 2
- Audit SourceAudit spec ↔ code ↔ tests alignment; surface drift as advisory findings, never auto-fix.Votes: 0GitHub stars: 2
- BrainstormFrame a need — problem, users, scope, risks, success metric — before committing to a spec.Votes: 0GitHub stars: 2
- ClarifyWhen a request is ambiguous, act as an analyst — reflect it back and ask one targeted question at a time (each with a recommendation) until the need is crisp, then execute.Votes: 0GitHub stars: 2
- Code ReviewReview a deliverable against its requirements, findings graded by severity.Votes: 0GitHub stars: 2
- Generate AgentTurn a description (or an auto-analysis) into a new agent persona, grounded in real named methods and matching the framework's gold-standard shape.Votes: 0GitHub stars: 2
- Generate DashboardTurn a description (or an auto-analysis) into a new custom dashboard page, as a declarative block spec that automatically matches every design the dashboard ships.Votes: 0GitHub stars: 2
- Generate SkillTurn a description (or an auto-analysis) into a new skill file, grounded in a real, cited domain standard and matching the framework's gold-standard shape.Votes: 0GitHub stars: 2
- ImplementImplement a plan task as small, conventional commits — red-green when a test exists, boy-scout cleanup on touched code, no scope creep.Votes: 0GitHub stars: 2
- Propose CustomizationsThe "Auto" mode — analyze the project and propose concrete, justified dashboard/skill/agent candidates instead of requiring a description upfront.Votes: 0GitHub stars: 2
- Security ReviewReview a change for secrets, authorization and attack surface against OWASP ASVS + Top 10.Votes: 0GitHub stars: 2
- Write AdrRecord an architecturally significant decision as a short, durable ADR.Votes: 0GitHub stars: 2
- Write E2e TestsAuthor durable, CI-runnable Playwright end-to-end tests — run headed, directly in the browser, by default; falls back to MCP, native browser tooling or headless, always telling the user why.Votes: 0GitHub stars: 2
- Write PlanBreak an approved, designed spec into small, dependency-ordered, checkbox tasks.Votes: 0GitHub stars: 2
- Write SpecProduce a clear, reviewable specification in markdown, signed off before design/code starts.Votes: 0GitHub stars: 2
- Write TestsWrite unit/integration tests test-first, one behaviour per test, red-green-refactor.Votes: 0GitHub stars: 2