$ skilldirectory
— zsh — registry.skilldirectory.dev
skill libraryblogguidesabout

home / creators / obra

Jesse Vincent

Jesse Vincent

@obra

Jesse Vincent builds open-source agent skills for AI agents focused on Testing & QA, Coding and Writing, shared openly under the MIT licence. Their work includes Using Superpowers, Verification Before Completion and Dispatching Parallel Agents.

14 skills listed6 categories

# skills by Jesse Vincent

Coding · ★ 2,89,989 · MITReceiving Code ReviewUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical…Coding · ★ 2,89,989 · MITRequesting Code ReviewUse when completing tasks, implementing major features, or before merging to verify work meets requirements.Writing · ★ 2,89,989 · MITWriting PlansUse when you have a spec or requirements for a multi-step task, before touching code.Testing & QA · ★ 2,89,989 · MITTest Driven DevelopmentUse when implementing any feature or bugfix, before writing implementation code.Productivity · ★ 2,89,989 · MITBrainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.Testing & QA · ★ 2,89,989 · MITSystematic DebuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes.Testing & QA · ★ 2,89,989 · MITFinishing A Development BranchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work.Coding · ★ 2,90,001 · MITUsing Git WorktreesUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via…Writing · ★ 2,90,001 · MITWriting SkillsUse when creating new skills, editing existing skills, or verifying skills work before deployment.AI Agents & MCP · ★ 3,07,678 · MITDispatching Parallel AgentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies.AI Agents & MCP · ★ 3,07,678 · MITSubagent Driven DevelopmentUse when executing implementation plans with independent tasks in the current session.Productivity · ★ 3,07,678 · MITExecuting PlansUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution.Agent Skills · ★ 3,13,073 · MITUsing SuperpowersUse when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions.Testing & QA · ★ 3,13,073 · MITVerification Before CompletionUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output…