superpowers plugin
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
How to install the superpowers plugin
Run both commands inside Claude Code. The first adds the marketplace once; the second installs the plugin.
/plugin marketplace add pickleshell/next-level-agent
/plugin install superpowers@superpowers-devWhat's inside superpowers
19 parts read from the plugin's own files.
Skills 18
Claude loads it when the task matches- assistant-notebook
Consult and maintain the user's persistent Assistant Notebook in ChatGPT Library or on the local filesystem as a secondary recall aid and index. The current conversation and other available context are primary and usually more complete. Consult it once when starting a substantive working context or restoring continuity, then reuse the recovered context without rereading the notebook on every request. Reconsult only when needed for a missing fact, older decision, project switch, or context loss. Update it after meaningful progress with verified outcomes, decisions, files, blockers, and next steps.
- brainstorming
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.
- dispatching-parallel-agents
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
- executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints
- finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
- mem0-memory
Use optional Mem0 memory tools for focused cross-session recall and short verified durable facts. Use when the user asks to remember or forget something, when resuming work that may need prior context, or after verified progress creates a stable fact worth retaining.
- next-level-agent
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
- planning-parallel-work
Use when a substantial software task needs decomposition into dependency-aware, independently verifiable work items and safe parallel execution groups before implementation begins.
- receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
- requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
- 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 implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
- verification-before-completion
Use 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 before assertions always
- writing-acceptance-tests
Use when independent tests must be derived from a specification, public interface, or acceptance criteria before implementation, without writing or relying on production code.
- 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
Hooks 1
Runs on these events- SessionStartcommand
startup|clear|compact
Using superpowers in Claude Code
Skills need no command. Claude reads them when your request matches what they describe.
Update, turn off or remove
- Update the plugin (shell)
- claude plugin update superpowers@superpowers-dev
- Refresh the marketplace
- /plugin marketplace update superpowers-dev
- Turn it off for now
- /plugin disable superpowers@superpowers-dev
- Remove it
- /plugin uninstall superpowers@superpowers-dev
Skills in superpowers
- assistant-notebookpickleshell/next-level-agent
Consult and maintain the user's persistent Assistant Notebook in ChatGPT Library or on the local filesystem as a secondary recall aid and index. The current conversation and other available context are primary and usually more complete. Consult it once when starting a substantive working context or restoring continuity, then reuse the recovered context without rereading the notebook on every request. Reconsult only when needed for a missing fact, older decision, project switch, or context loss. Update it after meaningful progress with verified outcomes, decisions, files, blockers, and next steps.
4 files7stars - brainstormingpickleshell/next-level-agent
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.
8 files7stars - next-level-agentpickleshell/next-level-agent
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
6 files7stars - requesting-code-reviewpickleshell/next-level-agent
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
2 files7stars - subagent-driven-developmentpickleshell/next-level-agent
Use when executing implementation plans with independent tasks in the current session
7 files7stars - systematic-debuggingpickleshell/next-level-agent
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
11 files7stars - test-driven-developmentpickleshell/next-level-agent
Use when implementing any feature or bugfix, before writing implementation code
2 files7stars - writing-planspickleshell/next-level-agent
Use when you have a spec or requirements for a multi-step task, before touching code
2 files7stars - writing-skillspickleshell/next-level-agent
Use when creating new skills, editing existing skills, or verifying skills work before deployment
7 files7stars - dispatching-parallel-agentspickleshell/next-level-agent
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
7stars - executing-planspickleshell/next-level-agent
Use when you have a written implementation plan to execute in a separate session with review checkpoints
7stars - finishing-a-development-branchpickleshell/next-level-agent
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
7stars - mem0-memorypickleshell/next-level-agent
Use optional Mem0 memory tools for focused cross-session recall and short verified durable facts. Use when the user asks to remember or forget something, when resuming work that may need prior context, or after verified progress creates a stable fact worth retaining.
7stars - planning-parallel-workpickleshell/next-level-agent
Use when a substantial software task needs decomposition into dependency-aware, independently verifiable work items and safe parallel execution groups before implementation begins.
7stars - receiving-code-reviewpickleshell/next-level-agent
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
7stars - using-git-worktreespickleshell/next-level-agent
Use 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
7stars - verification-before-completionpickleshell/next-level-agent
Use 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 before assertions always
7stars - writing-acceptance-testspickleshell/next-level-agent
Use when independent tests must be derived from a specification, public interface, or acceptance criteria before implementation, without writing or relying on production code.
7stars
superpowers plugin questions
How do I install the superpowers plugin?
In Claude Code run /plugin marketplace add pickleshell/next-level-agent, then /plugin install superpowers@superpowers-dev.
What does the superpowers plugin include?
superpowers bundles 18 skills, hooks.
How do I update or remove the superpowers plugin?
Update it with claude plugin update superpowers@superpowers-dev in your shell, or from the Installed tab of /plugin. Remove it with /plugin uninstall superpowers@superpowers-dev.
What license is the superpowers plugin under?
MIT, as stated in the plugin's manifest.