superpowers
v1.0.0by Ryfter · author: Jesse Vincent
The Superpowers development methodology by Jesse Vincent and Prime Radiant, repackaged unchanged for Kiro. Superpowers is a complete, opinionated software-development workflow built from composable skills: it starts by teasing a spec out of the conversation, turns it into a clear implementation plan, then drives the work with true red-green-refactor TDD, systematic root-cause debugging, code review between tasks, and subagent-driven development. Strong on the full engineering lifecycle, including git worktrees, parallel-agent orchestration, and clean branch finishing. 14 skills covering brainstorming, writing and executing plans, TDD, systematic debugging, code review (requesting and receiving), verification, and more. 100% the work of Jesse Vincent and Prime Radiant; this power only brings their skills into Kiro. GitHub: https://github.com/obra/superpowers.
What superpowers does, in the publisher's words
> This is 100% the work of Jesse Vincent (and the team at Prime Radiant). > Every skill in this power was written by the Superpowers authors and lives at > github.com/obra/superpowers. > This power does not add, rewrite, or improve any of that work, it only > repackages it, unchanged, so it can be installed as a Kiro power. > All credit goes to the original authors. If you find these skills valuable, > follow and support them.
A Kiro Power that vendors the Superpowers agent skills so Kiro can use them. The skill files are copied verbatim from upstream; attribution and license are preserved.
- License: MIT (see UPSTREAM-LICENSE)
- Synced commit: recorded in UPSTREAM.txt
From the project README, punctuation lightly normalized · Open the README on GitHub
- Skills
- 14
- MCP servers
- 0
- Stars
- 1
- License
- MIT
- Repo created
- 2026-09-01
- Last pushed
- 2026-10-19
- Publisher type
- User
- Version
- 1.0.0
Links
Skills · 14
- 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
- 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
- using-superpowers
- Use when starting any conversation: establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
- 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-plans
- writing-skills
Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.
Category
Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.
Keywords
methodology · tdd · brainstorming · systematic-debugging · code-review · subagent-driven-development · superpowers
Related by publisher and keywords
Matt Pocock's engineering and productivity agent skills, from https://www.aihero.dev/skills, repackaged unchanged for Kiro. A battle-tested toolkit for doing real software engineering with an AI agent (not vibe coding): align before you build with grilling/brainstorming, drive features and fixes with true red-green-refactor TDD, run disciplined bug diagnosis, review changes against standards and spec, and actively improve codebase architecture through deep-module design and domain modeling. Also includes productivity tooling: specs, tickets, research, prototypes, handoffs, and teaching. 25 skills across engineering and productivity, kept faithful to the source. 100% Matt Pocock's work; this power only brings his skills into Kiro. Site: https://www.aihero.dev/skills. GitHub: https://github.com/mattpocock/skills. X: https://x.com/mattpocockuk.
Read and search your Google Workspace directly from Kiro through a self-hosted, local MCP server. Search and browse Google Drive, read Google Docs (exported cleanly to markdown), pull Google Sheets cell values, and read Google Slides text and layout. It leans toward lightweight text formats over binary: Docs become.md, Sheets become.csv, Slides become a markdown outline, so you spend fewer tokens and get diff-friendly output; binary is used only when no text form exists or you ask for the original. Can also locate and download Google Vids files (Vids has no content API, so deeper Vid contents are not extractable). Runs the @piotr-agier/google-drive-mcp server locally over stdio; your Google identity, OAuth credentials, and token stay on your machine. Prefers read-only scopes by default.
Fetch YouTube video transcripts as plain text from Kiro, so the agent can read, summarize, quote, or research spoken video content it otherwise cannot see. Bundles a small Python script that wraps the youtube-transcript-api library: pass one or more video URLs or IDs and it writes one UTF-8.txt per video, reporting word counts and skipping videos with no captions. Handles full watch URLs, youtu.be short links, /shorts/ and /embed/ forms, and bare 11-character IDs, and works across both the modern (>=1.0) and legacy youtube-transcript-api interfaces. Use when the user shares YouTube links and wants the words, not the video. No API key required; transcripts are pulled from YouTube's public caption tracks.
An agentic skills framework & software development methodology that works: planning, TDD, debugging, and collaboration workflows.
The Moe skill library: brainstorming, planning, TDD, systematic debugging, code review, worktrees, parallel dispatch, plugin authoring, and more.
Composable AI skills framework covering the full software delivery lifecycle, design, architecture, implementation, testing, and review.
[](https://agentpluginsdirectory.com/plugins/superpowers)✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.