elements-of-style
Applies the classic writing rules from Strunk's style guide to any prose people will read, such as documentation, commit messages, error messages and reports, so the text comes out clearer and more concise.
Finds functions that do the same job under different names, queries MCP servers only when you ask so they stay out of your context, drives interactive tools like vim or a Python REPL through tmux, and sets up a headless Windows VM you can SSH into.
Claude Code
$ npx -y skills add obra/superpowers-lab --agent claude-code
Codex
$ npx skills add obra/superpowers-lab -a codex
Cursor
$ npx skills add obra/superpowers-lab -a cursor
Gemini CLI
$ npx skills add obra/superpowers-lab -a gemini-cli
GitHub Copilot
$ npx skills add obra/superpowers-lab -a github-copilot
OpenCode
$ npx skills add obra/superpowers-lab -a opencode
Windsurf
$ npx skills add obra/superpowers-lab -a windsurf
Experimental skills for Claude Code Superpowers - new techniques and tools under active development.
This plugin contains experimental skills that extend Claude Code's capabilities with new techniques that are still being refined and tested. These skills are functional but may evolve based on real-world usage and feedback.
Detect semantic code duplication in LLM-generated codebases. Unlike traditional copy-paste detectors that find syntactic duplicates, this skill identifies functions with the same intent but different implementations.
Use cases:
How it works: Two-phase approach using classical function extraction followed by LLM-powered intent clustering. Haiku categorizes functions by domain, then Opus analyzes each category to find semantic duplicates.
See skills/finding-duplicate-functions/SKILL.md for full documentation.
Use MCP servers on-demand via the mcp CLI tool. Discover and invoke tools, resources, and prompts without polluting context with pre-loaded MCP integrations.
Use cases:
See skills/mcp-cli/SKILL.md for full documentation.
Enables Claude Code to control interactive CLI tools (vim, git rebase -i, menuconfig, REPLs, etc.) through tmux sessions.
Use cases:
How it works: Creates detached tmux sessions, sends keystrokes programmatically, and captures terminal output to enable automation of traditionally manual workflows.
See skills/using-tmux-for-interactive-commands/SKILL.md for full documentation.
Create, manage, or connect to a headless Windows 11 VM running in Docker with KVM acceleration and SSH access โ no RDP or GUI required.
Use cases:
How it works: Uses dockur/windows to run Windows 11 in a Docker container with KVM acceleration. Manages the full lifecycle: create, start, stop, restart, SSH, and status checks. Includes automated setup of OpenSSH Server, Node.js, and Claude Code inside the VM.
See skills/windows-vm/SKILL.md for full documentation.
# Install the plugin
claude-code plugin install https://github.com/obra/superpowers-lab
# Or add to your claude.json
{
"plugins": [
"https://github.com/obra/superpowers-lab"
]
}
Skills in this plugin are:
Found a bug or have an improvement? Please open an issue or PR!
MIT License - see LICENSE for details
Applies the classic writing rules from Strunk's style guide to any prose people will read, such as documentation, commit messages, error messages and reports, so the text comes out clearer and more concise.
Semantic search over past Claude Code conversations, so a session can recall earlier discussions, decisions, and patterns. It adds a remembering-conversations skill that checks prior sessions before the assistant says it doesn't know.
Turn one coding-agent session into a project manager that delegates tasks to other coding-agent sessions, Claude Code, Codex, or Pi.
Skills for working on Playwright itself, covering development of new APIs and CLI commands, CI failure analysis, cherry-picking to release branches, triaging bug reports, and querying test results. Aimed at Playwright contributors and maintainers.
The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.
Skills for evaluating and red-teaming LLM apps with Promptfoo. Covers writing and running eval suites, connecting Promptfoo to models and APIs, and running and rerunning redteam security scans.
Skills for evaluating AI agents, RAG pipelines and LLM apps with DeepEval metrics, and for tracing those apps with OpenTelemetry or DeepEval tracing into Confident AI.
Finds functions that do the same job under different names, queries MCP servers only when you ask so they stay out of your context, drives interactive tools like vim or a Python REPL through tmux, and sets up a headless Windows VM you can SSH into. Install it with the command on its page. It includes finding-duplicate-functions, mcp-cli, using-tmux-for-interactive-commands. Its skills do not fire on their own yet. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it