By emilelemoine
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Senior developer agent that reviews all changes on a feature branch before merge. Focuses on refactoring opportunities, efficiency improvements, design quality, and bug detection. Dispatched by the finishing-a-development-branch skill.
Use this agent to write implementation plans from a design doc. It explores the codebase with fresh context (no brainstorming history), produces a DAG roadmap with self-contained step files, and runs plan review on each chunk. This agent is typically spawned after brainstorming completes, receiving only the design doc path. <example> Context: Brainstorming produced a design doc and the main session spawns this agent. prompt: "Write an implementation plan from the design doc at docs/specs/2026-03-04-auth-design.md. Worktree: /path/to/worktree" <commentary> The agent starts with fresh context, reads only the design doc, explores the codebase independently, and writes the plan. </commentary> </example>
Search and retrieve notes from the user's org-roam knowledge base. Use when the user asks about their personal notes, wants to reference prior thinking, or needs context from their knowledge graph. Examples: <example>Context: User wants to check their notes before implementing something. user: "Check my org-roam notes on authentication patterns before we start" assistant: "Let me search your org-roam knowledge base for authentication-related notes." <commentary>The user wants to pull in context from their personal knowledge base before coding.</commentary></example> <example>Context: User references something they've written about before. user: "I wrote some notes about this API design a while back" assistant: "Let me search your org-roam for API design notes." <commentary>The user is referencing prior work in their knowledge base.</commentary></example>
Use this agent to set up a git worktree for isolated feature work. Handles directory detection, gitignore verification, worktree creation, dependency installation, and test baseline verification. Returns a structured report. <example> Context: Starting feature work that needs an isolated workspace. prompt: "Set up a worktree for branch feature/auth in repo /Users/me/myproject" <commentary> The agent detects the worktree directory, verifies gitignore, creates the worktree, installs deps, runs tests, and reports back. </commentary> </example>
Use when working on any project that runs on NYU's BigPurple Slurm cluster — job submission, GPU debugging, env setup, scratch vs data paths, node exclusions, GPFS quirks, or cluster shell configuration
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when you have a written implementation plan to execute — follows TDD loop for each task
Use when implementation is complete, all tests pass, and you need to integrate the work - defaults to local merge unless the project CLAUDE.md specifies otherwise
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Superpowers is a complete software development workflow for your coding agents, built on top of a set of composable "skills" and some initial instructions that make sure your agent uses them.
It starts from the moment you fire up your coding agent. As soon as it sees that you're building something, it doesn't just jump into trying to write code. Instead, it steps back and asks you what you're really trying to do.
Once it's teased a spec out of the conversation, it shows it to you in chunks short enough to actually read and digest.
After you've signed off on the design, your agent puts together an implementation plan that's clear enough for an enthusiastic junior engineer with poor taste, no judgement, no project context, and an aversion to testing to follow. It emphasizes true red/green TDD, YAGNI (You Aren't Gonna Need It), and DRY.
Next up, once you say "go", it executes the plan using a TDD loop — red, green, refactor — with a lightweight review after each task. It's not uncommon for Claude to be able to work autonomously for a couple hours at a time without deviating from the plan you put together.
There's a bunch more to it, but that's the core of the system. And because the skills trigger automatically, you don't need to do anything special. Your coding agent just has Superpowers.
If Superpowers has helped you do stuff that makes money and you are so inclined, I'd greatly appreciate it if you'd consider sponsoring my opensource work.
Thanks!
Note: Installation differs by platform. Claude Code or Cursor have built-in plugin marketplaces. Codex and OpenCode require manual setup.
Superpowers is available via the official Claude plugin marketplace
Install the plugin from Claude marketplace:
/plugin install superpowers@claude-plugins-official
In Claude Code, register the marketplace first:
/plugin marketplace add obra/superpowers-marketplace
Then install the plugin from this marketplace:
/plugin install superpowers@superpowers-marketplace
In Cursor Agent chat, install from marketplace:
/add-plugin superpowers
or search for "superpowers" in the plugin marketplace.
Tell Codex:
Fetch and follow instructions from https://raw.githubusercontent.com/obra/superpowers/refs/heads/main/.codex/INSTALL.md
Detailed docs: docs/README.codex.md
Tell OpenCode:
Fetch and follow instructions from https://raw.githubusercontent.com/obra/superpowers/refs/heads/main/.opencode/INSTALL.md
Detailed docs: docs/README.opencode.md
gemini extensions install https://github.com/obra/superpowers
To update:
gemini extensions update superpowers
Start a new session in your chosen platform and ask for something that should trigger a skill (for example, "help me plan this feature" or "let's debug this issue"). The agent should automatically invoke the relevant superpowers skill.
brainstorming - Activates before writing code. Refines rough ideas through questions, explores alternatives, presents design in sections for validation. Saves design document.
using-git-worktrees - Activates after design approval. Creates isolated workspace on new branch, runs project setup, verifies clean test baseline.
writing-plans - Activates with approved design. Breaks work into bite-sized tasks (2-5 minutes each). Every task has exact file paths, complete code, verification steps.
executing-plans - Activates with plan. Follows TDD loop (red-green-refactor) for each task with lightweight refactor review after each green phase.
test-driven-development - Activates during implementation. Enforces RED-GREEN-REFACTOR: write failing test, watch it fail, write minimal code, watch it pass, commit. Deletes code written before tests.
requesting-code-review - Activates between tasks. Reviews against plan, reports issues by severity. Critical issues block progress.
finishing-a-development-branch - Activates when tasks complete. Verifies tests, presents options (merge/PR/keep/discard), cleans up worktree.
The agent checks for relevant skills before any task. Mandatory workflows, not suggestions.
Testing
Debugging
npx claudepluginhub emilelemoine/superpowersCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
v9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Matt Pocock's agent skills for real engineering — grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.