superpowers
claudecodexCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
14 skills · hooks
Always-on skills: code explanation, conventional commits, codebase visualization, code quality, git, and Vue/TypeScript frontend work
Plugin core from marketplace caderon-pack in brent-hoover/caderon-pack. Commands read from the repo's manifest — today.
agent-busMessage bus between independent Claude Code sessions on this machine (cmux-hosted). Use when the user asks you to register on the bus, message/ask/tell another agent or session, coordinate with an agent in another terminal, or when a prompt beginning with "[agent-bus]" announces a new message for yo
agent-teamsHow to orchestrate Claude Code's experimental Agent Teams — spawning teammates as separate sessions, delegating work to them, and waiting for results instead of doing the work yourself in the main thread. Use whenever a task should run as parallel/independent workstreams: multi-file refactors, revie
bdd-specsBehavior-driven design: write executable specifications BEFORE any implementation code. Integrates with the doc-driven-development workflow — reads feature-work/<slug>/plan.md and problem.md when present, otherwise falls back to /docs/PLAN.md and /docs/STORIES.md. Generates spec files in nested Feat
catch-me-upReconstruct and summarize the state of the current working session — what's been done, what's left, and where things stand right now. Use whenever the user asks to be "caught up", says "catch me up", "where were we", "what have we done so far", "remind me where we are", "status", "recap", "summarize
code-qualityStandards for maintaining high code quality including comments, test coverage, and documentation practices
codebase-visualizerGenerate an interactive collapsible tree visualization of your codebase. Use when exploring a new repo, understanding project structure, or identifying large files.
conventional-commitCreate commit messages following conventional commit conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with issue references.
explain-codeExplains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this
git-masterGit expert for atomic commits, rebasing, and history management with style detection
git-worktreesCreate, list, and remove git worktrees in a consistent, repeatable way. Use when the user asks to work on a branch in an isolated worktree, set up parallel work, spin up a worktree for an agent/PR, or clean up worktrees. Worktrees ALWAYS live in `.worktrees/` at the repository root (git ignored).
markdown-reviewUse when you have authored documents (markdown plans, designs, reports, analyses; Gherkin .feature files; other text files) that the user should read and give feedback on. Serves them to the user's browser — markdown rendered, .feature files as Gherkin, anything else as numbered source — with a mult
retrospectiveAnalyze the current (or a past) working session end-to-end and deliver a retrospective — what went well, what could improve, and what to stop doing — covering both the user and Claude, with concrete follow-ups like CLAUDE.md edits, new skills, or hooks. Use whenever the user asks for a "retro", "ret
user-storiesWrite, split, and refine agile/scrum user stories and acceptance criteria. Produces /docs/STORIES.md as the canonical backlog, formatted to feed directly into the bdd-specs skill (Story → Feature, Given/When/Then acceptance criteria → Scenario/Specification). Use this whenever the user wants to writ
vue-typescriptMaster Vue TypeScript - Type-safe Components, Generics, Type Inference, Advanced Patterns
/core:quick-fixMake a small, obvious fix directly on the current branch. No sprint, no PLAN, no stories.
/core:retrospectiveRetrospective on a working session — what went well, what to improve, what to stop — with concrete follow-ups.
/core:worktreeCreate a git worktree for a feature branch at .worktrees/<slug>.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
14 skills · hooks
BDD-enforced feature lifecycle: problem → Gherkin scenarios → design → plan → close, with mutation testing gate at close; /scaffold-bdd-docs copies the bare templates into a project
4 skills · 3 commands · 4 agents
Read and write your Obsidian vault from Claude Code — daily notes, quick capture, and vault browsing via MCP
1 skill · 8 commands · 1 MCP server
Guides Claude through problem → design → plan documentation workflow for new features; /scaffold-docs copies the bare templates into a project
2 skills · 3 commands · 4 agents
Seven-phase greenfield project planning: vision → stack → architecture → data models → stories → plan → scaffold, ending in a repo with green architecture tests and red BDD specs (Python/Go)
1 skill · 1 command · 7 agents
Kubernetes and Helm skills: manifest generation, security policies, Helm debugging, values management
6 skills · 1 command · 1 agent
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
Claude Code skill for creating and presenting Slidev slidedecks
1 skill
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
AI-supervised issue tracker for coding workflows
1 skill · 1 agent · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.