Jesse Vincent (obra)
- 72 skills
- 0 followers
- 247k repo stars
- 1 verified
- last week last updated
- ▌
- ▌ Using Git Worktrees 3 · obraCreate isolated git worktrees with smart directory selection and safety verification
- ▌ Verification Before Completion 3 · obraRun verification commands and confirm output before claiming success
- ▌ Dispatching Parallel Agents 2 · obraUse multiple Claude agents to investigate and fix independent problems concurrently
- ▌ Subagent Driven Development 3 · obraExecute implementation plan by dispatching fresh subagent for each task, with code review between tasks
- ▌ Finishing A Development Branch 3 · obraComplete feature development with structured options for merge, PR, or cleanup
- ▌ Writing Plans 2 · obraCreate detailed implementation plans with bite-sized tasks for engineers with zero codebase context
- ▌ Systematic Debugging 2 · obra bundleFour-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.
- ▌ Requesting Code Review 2 · obra bundleDispatch code-reviewer subagent to review implementation against plan or requirements before proceeding
- ▌ Remembering Conversations 2 · obra bundleSearch previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
- ▌
- ▌ Testing Skills With Subagents · obra bundleRED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes
- ▌ Code Review Reception · obraReceive and act on code review feedback with technical rigor, not performative agreement or blind implementation
- ▌ Roborev Fix 2 · obraUse when the user asks to fix open failing reviews, invokes /roborev-fix, or provides job IDs; do not use when the user only pastes review findings with no request to discover or close reviews
- ▌ Roborev Refine 2 · obraIterative review-fix loop for the current branch — reviews via daemon, fixes inline, re-reviews until passing or max iterations reached
- ▌
- ▌
- ▌
- ▌ Roborev Review Branch 2 · obraRequest a code review for all commits on the current branch and present the results
- ▌ Roborev Design Review Branch 2 · obraRequest a design review for all commits on the current branch and present the results
- ▌ Refactoring Safely · obraRefactor with tests first, one change at a time, never mix refactoring with bug fixes or new features
- ▌ Defense In Depth Validation · obraValidate at every layer data passes through to make bugs impossible
- ▌ Brainstorming Ideas Into Designs · obraInteractive idea refinement using Socratic method to develop fully-formed designs
- ▌ Testing Anti Patterns · obraNever test mock behavior. Never add test-only methods to production classes. Understand dependencies before mocking.
- ▌ Condition Based Waiting · obra bundleReplace arbitrary timeouts with condition polling for reliable async tests
- ▌ Managing Homedir · obraUse when adding, changing, deploying, onboarding, or auditing homedir-manager content repos — the marker-based symlink deployment system that manages dotfiles and config across your machines. Covers the update workflow, the manifest, OS-splitting, secrets, new-machine onboarding, and the audit process.
- ▌ Maintaining Macos Defaults · obraUse on demand to reconcile a Mac's GUI-changed settings into version control — when the user says "reconcile my mac defaults", "capture my macOS settings", or after they've changed System Settings and want the keepers tracked. Drives homedir-manager's `defaults` verb (capture/drift/apply) against a versioned desired-state file.
- ▌ Developing Claude Code Plugins · obra bundleUse when working on Claude Code plugins (creating, modifying, testing, releasing, or maintaining) - provides streamlined workflows, patterns, and examples for the complete plugin lifecycle
- ▌
- ▌ Chronicle · obraAllows you to view the user's screen as well as several hours of history. Use when the user makes a reference to their recent work, for which it'd be helpful to see the screen. This skill MUST be used whenever you need to resolve ambiguity in a user request, where the user hasn't specified enough context to do the task. Examples include disambiguating the specific user/app/document/error the user is referring to. You must also use this skill if the user asks about any question regarding Chronicle or asks what you can see from the screen.
- ▌ Roborev Fix · obraUse when the user asks to fix open failing reviews, invokes $roborev-fix, or provides job IDs; do not use when the user only pastes review findings with no request to discover or close reviews
- ▌ Roborev Refine · obraIterative review-fix loop for the current branch — reviews via daemon, fixes inline, re-reviews until passing or max iterations reached
- ▌
- ▌
- ▌ Syncing Obsidian · obraUse when reading or writing files in an Obsidian vault that is synced with obsync. Ensures changes are pulled before reading and pushed after writing. Also covers sync status, file history, version restore, and diagnosing sync issues.
- ▌ E2e Scenario Testing · obraUse when verifying a running application end-to-end through its real interface — a web UI, a CLI, or a TUI — by writing and executing agent-run "scenario cards" against a freshly built instance with falsifiable assertions. Trigger on "test it end to end", "prove the UI actually works", "write/run a scenario", or after a change touches a user-facing surface that unit tests can't fully cover. Not for unit tests, pure code review, or API-only checks.
- ▌
- ▌ Roborev Review Branch · obraRequest a code review for all commits on the current branch and present the results
- ▌ Maintaining Documentation · obra bundleUse when documentation needs creating, checking, or maintaining — docs may have drifted from code, pre-release doc verification, updating docs after finishing code work, adding or enforcing project terminology, deciding where a new doc should live, or a routine re-audit of previously verified docs.
- ▌ Roborev Design Review Branch · obraRequest a design review for all commits on the current branch and present the results
- ▌ Creating Skills · obra bundleTDD for process documentation - test with subagents before writing, iterate until bulletproof
- ▌
- ▌ Gardening Skills Wiki · obra bundleMaintain skills wiki health - check links, naming, cross-references, and coverage
- ▌ Root Cause Tracing · obra bundleSystematically trace bugs backward through call stack to find original trigger
- ▌ Codex Subagents · obra bundleSpawn background subagents for parallel or long-running tasks. Use when you need research threads, context isolation, or detached execution.
- ▌ Prove Claim · obraUse when asked to prove, disprove, investigate, or find evidence for a claim about people, concepts, ideas, or their relationships. Also use when asked to explore connections, find who influenced what, trace how ideas developed, or answer questions that require reasoning over multiple linked notes.
- ▌ Driving Claude Code Sessions · obra bundleUse when acting as a project manager that delegates tasks to other coding-agent sessions (Claude Code, Codex, or Pi) - launch workers, assign them work, monitor progress, review their tool calls, and collect results
- ▌ Browsing · obra bundleUse when you need direct browser control - teaches Chrome DevTools Protocol for controlling existing browser sessions, multi-tab management, form automation, and content extraction via use_browser MCP tool
- ▌ Windows Vm · obraCreate, manage, or connect to a headless Windows 11 VM running in Docker with SSH access. Use when the user wants to spin up, stop, restart, or SSH into a Windows VM.
- ▌ Remembering Conversations · obra bundleYou MUST invoke this skill before saying "I don't know," guessing, or treating any topic as new, no matter how trivial the question seems. It supplements other memory systems, which only hold partial records. Searching past conversations is the only way to recover what was actually said.
- ▌ Test Driven Development 2 · obra bundleUse when implementing any feature or bugfix, before writing implementation code
- ▌ Brainstorming 2 · obraYou MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
- ▌ Executing Plans 2 · obraUse when you have a written implementation plan to execute in a separate session with review checkpoints
- ▌ Using Git Worktrees 2 · obraUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
- ▌ Subagent Driven Development 2 · obraUse when executing implementation plans with independent tasks in the current session
- ▌ Finishing A Development Branch 2 · obraUse when implementation is complete, all tests pass, and you need to decide how to integrate the work
- ▌ Verification Before Completion 2 · obraUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence
- ▌
- ▌ Using Superpowers · obra bundleEnsures skills are invoked before any response, including clarifying questions, and establishes how to find and use skills.
- ▌ Brainstorming · obra bundleGuides collaborative dialogue to turn ideas into fully formed designs and specs before any implementation begins.
- ▌ Writing Plans · obra bundleCreates detailed, step-by-step implementation plans from specs or requirements, with task decomposition, file structure, and test-driven development instructions.
- ▌ Writing Skills · obra bundleCreate, edit, and verify agent skills using test-driven development to ensure agents follow documented procedures correctly.
- ▌ Executing Plans · obraLoad a written implementation plan, execute each task with verification checkpoints, and complete development using a structured workflow.
- ▌ Using Git Worktrees · obraSets up an isolated Git worktree for feature development, preferring native tools and falling back to manual git worktrees when needed.
- ▌ Systematic Debugging · obra bundleFind root causes of bugs, test failures, or unexpected behavior before proposing any fixes.
- ▌ Receiving Code Review · obraProvides a structured protocol for receiving and evaluating code review feedback, emphasizing technical verification over performative agreement.
- ▌ Requesting Code Review · obra bundleDispatch a code reviewer subagent to catch issues before they cascade, with precisely crafted context for evaluation.
- ▌ Test Driven Development · obra bundleWrite tests before implementation code for new features, bug fixes, and refactoring, following the red-green-refactor cycle.
- ▌ Dispatching Parallel Agents · obraDispatch multiple independent tasks to parallel agents for faster debugging and problem-solving.
- ▌ Subagent Driven Development · obra bundleExecute implementation plans by dispatching a fresh subagent per task, with task review after each and a whole-branch review at the end.
- ▌ Finishing A Development Branch · obraGuides completion of development work by verifying tests, detecting the environment, and presenting structured options for merging, creating a PR, or discarding changes.
- ▌ Verification Before Completion · obraEnforces running verification commands and confirming output before claiming work is complete, fixed, or passing, to prevent false success claims.