Jesse Vincent's skills help AI agents enforce disciplined engineering habits, such as checking for relevant skills before starting a task, finding the root cause of a bug through reproduction and hypothesis testing, and writing step-by-step implementation plans before coding. His library also covers searching archived Claude Code conversations for past decisions and fixes, executing plans in reviewed batches, and running parallel agents on independent problems. What stands out is the emphasis on process, with structured checkpoints that keep an agent's work reviewable from start to finish.
Superpowers
15 skills · 313,533 stars · MIT
Brainstorming You MUST use this before any creative work - creating features, building components, adding funct…
Diagnosing Superpowers Use when a superpowers session went wrong and your human partner wants to know why — repeated wor…
Dispatching Parallel Agents Use when facing 2+ independent tasks that can be worked on without shared state or sequential dep…
Executing Plans Use when executing an implementation plan in the current session as the implementer yourself — yo…
Finishing A Development Branch Use when implementation is complete, all tests pass, and you need to decide how to integrate the…
Receiving Code Review Use when receiving code review feedback, before implementing suggestions, especially if feedback…
Requesting Code Review Use when completing tasks, implementing major features, or before merging to verify work meets re…
Subagent Driven Development Use when executing implementation plans with independent tasks in the current session
Systematic Debugging Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Test Driven Development Use when implementing any feature or bugfix, before writing implementation code
Using Git Worktrees Use when starting feature work that needs isolation from current workspace or before executing im…
Using Superpowers Use when starting any conversation - establishes how to find and use skills, requiring skill invo…
Verification Before Completion Use when about to claim work is complete, fixed, or passing, before committing or creating PRs -…
Writing Plans Use when you have a spec or requirements for a multi-step task, before touching code
Writing Skills Use when creating new skills, editing existing skills, or verifying skills work before deployment
Superpowers Skills
31 skills · 759 stars · MIT
Verification Before Completion Run verification commands and confirm output before claiming success
Brainstorming Ideas Into Designs Interactive idea refinement using Socratic method to develop fully-formed designs
Code Review Reception Receive and act on code review feedback with technical rigor, not performative agreement or blind…
Collision Zone Thinking Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?"
Condition Based Waiting Replace arbitrary timeouts with condition polling for reliable async tests
Defense In Depth Validation Validate at every layer data passes through to make bugs impossible
Dispatching Parallel Agents Use multiple Claude agents to investigate and fix independent problems concurrently
Executing Plans Execute detailed plans in batches with review checkpoints
Finishing A Development Branch Complete feature development with structured options for merge, PR, or cleanup
Gardening Skills Wiki Maintain skills wiki health - check links, naming, cross-references, and coverage
Inversion Exercise Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the oppo…
Make sure AI agents find and use the right skills before every task Mandatory workflow rules for reading, announcing and following skills before starting work.
Meta Pattern Recognition Spot patterns appearing in 3+ domains to find universal principles
Preserving Productive Tensions Recognize when disagreements reveal valuable context, preserve multiple valid approaches instead…
Pulling Updates From Skills Repository Sync local skills repository with upstream changes from obra/superpowers-skills
Requesting Code Review Dispatch code-reviewer subagent to review implementation against plan or requirements before proc…
Root Cause Tracing Systematically trace bugs backward through call stack to find original trigger
Scale Game Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at…
Search past Claude Code conversations for decisions and fixes Find earlier discussions, decisions and error fixes by meaning or exact text.
Sharing Skills Contribute skills back to upstream via branch and PR
Simplification Cascades Find one insight that eliminates multiple components - "if this is true, we don't need X, Y, or Z"
Subagent Driven Development Execute implementation plan by dispatching fresh subagent for each task, with code review between…
Systematic Debugging Four-phase debugging framework that ensures root cause investigation before attempting fixes.
Test Driven Development (Tdd) Write the test first, watch it fail, write minimal code to pass
Testing Anti Patterns Never test mock behavior.
Testing Skills With Subagents RED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures,…
Tracing Knowledge Lineages Understand how ideas evolved over time to find old solutions for new problems and avoid repeating…
Using Git Worktrees Create isolated git worktrees with smart directory selection and safety verification
When Stuck Problem Solving Dispatch Dispatch to the right problem-solving technique based on how you're stuck
Writing Plans Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context
Writing Skills TDD for process documentation - test with subagents before writing, iterate until bulletproof
The Elements Of Style
1 skills · 616 stars
Writing Clearly And Concisely Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit message…
Episodic Memory
1 skills · 499 stars · MIT
Remembering Conversations You MUST invoke this skill before saying "I don't know," guessing, or treating any topic as new,…
Superpowers Lab
4 skills · 437 stars · MIT
Finding Duplicate Functions Use when auditing a codebase for semantic duplication - functions that do the same thing but have…
Mcp Cli Use MCP servers on-demand via the mcp CLI tool - discover tools, resources, and prompts without p…
Using Tmux For Interactive Commands Use when you need to run interactive CLI tools (vim, git rebase -i, Python REPL, etc.) that requi…
Windows Vm Create, manage, or connect to a headless Windows 11 VM running in Docker with SSH access.
Other skills
2 skills
Find the root cause of a bug step by step, not by guessing A repeatable method to trace a bug from symptom to root cause and verify the fix.
Write a step-by-step implementation plan before coding A structured plan with file paths, steps and checkpoints, ready for review before any code changes.