Skills

Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't…

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool…

Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of…

UI/UX design intelligence for web, mobile, and desktop.

Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation.

Interactively create, install, activate, and verify custom claude-mem modes, including domain-specific observation types, concept tags, optional Telegram…

Documentation reference for writing Python code using the browser-use open-source library.

Map what the owner wants from the prompts they typed themselves (prompts an agent wrote are left out), then put their top priorities and open asks, each with…

QA-test a website or web app and return a 1-5 quality score (5 = flawless, 1 = broken) with evidence.

Group recent conversations into overall requests, review each one's progress from memory, link each to the owner goals it serves, and write the build story…

Automated semantic versioning and release workflow for Claude Code plugins.

Optimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence.

Audit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency…

Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup.

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting.

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo.

Read-only review of Caveman Cloud evidence: cost, Cave Score, workflows, traces, latency, errors, routing, savings.

Act on a Caveman learn report - review the ranked token sinks, apply cost-lowering fixes with per-edit consent, and report what those fixes returned.

Inspect Caveman Cloud's experiment lifecycle and block unsafe execution.

Turn a Caveman optimization observation into an operator-chosen candidate with a paired baseline evaluation.

Operate a Dify server through difyctl: find and run any operation, and build, test, publish and change Workflow and Chatflow apps.

Use when writing, changing, or reviewing Cucumber and Playwright tests under `e2e/`, including feature files, step definitions, support code, scenario tags…

Review frontend code under `web/` or `packages/dify-ui/` when the user explicitly requests a review or audit.

Use when implementing or refactoring React/TypeScript components and the task requires decisions about component ownership, feature boundaries, state, data…