Skill rating

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative

Use when the user says brain, project knowledge, what do we know about, open tasks, or recent decisions, or runs /brain or /brain-update. SQLite project_brain.db tracker for entities, relationships, t

Use when implementing, reviewing, or debugging Apple Liquid Glass: iOS 26+ adoption, Regular vs Clear variants, tinting, scroll edge effects, or an iOS-native redesign review.

Generate self-contained HTML visual explanations for systems, code changes, plans, data, and technical concepts. Use for diagrams, architecture overviews, diff or plan reviews, project recaps, compari

Use when asked to generate tests for a file, module or component, to raise coverage, or to bootstrap a suite for untested code. Detects the project's test framework and conventions first, then writes

Speech-to-text transcription via OpenAI Whisper. Supports two modes — Local CLI (no API key, runs on-device) and Cloud API (fast, scalable, requires OPENAI_API_KEY). Use when the user needs to transcr

Generate structured meeting notes from transcripts or pasted text. Use when someone says "meeting notes", "process this transcript", "summarize this call", "notes from today's meeting", or pastes/refe

Use when designing, building or reviewing UI/UX for a web or mobile app: picking styles, color palettes, typography, layout, animation or charts, or checking accessibility and touch targets. Priority-

Use when facing architectural decisions, complex trade-offs, strategic technology choices, or scaling and migration questions that deserve more than a quick answer. Lays out options with trade-offs, t

Use when building AI features into a product: LLM integration, RAG pipelines, guardrails, streaming, AI UX, prompt engineering, or AI cost control. Treats prompts as code and validates every model out

Use for authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery.

Creates task-oriented technical documentation with progressive disclosure. Use when writing READMEs, API docs, architecture docs, or markdown documentation. Also use this skill at the END of any compl

Use when the user says 'm0 remember', 'record what we did', 'note for next session' or 'write a checkpoint', or after finishing a step worth handing to the next session. Appends one entry to the M0 th

Use when the user says m0 handoff, before I compact, end of session, save session state, resume where we left off, or continue in Cursor or Claude Code. Writes or reads a compact_checkpoint so a cold

Use when the user asks m0 recall, where were we, what did we do last time, catch me up, what is next, or to resume context from another tool. Reads the recent M0 operational thread per project, newest

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, soc

Use when the agent must open a URL, fill a form, click through a flow, screenshot a page, or extract data from a live page. Covers two providers (agent-browser local CLI, agentic-browser cloud) and th

Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture. Use when building with Tailwind v4 or migrating from v3.

Use when starting any task, before invoking any other skill or GSD command, to route between Superpowers skills and GSD commands from project state and task scope. Fires first when both systems are in

Post-run self-evaluation system that scores agent output on correctness, clarity, actionability, and conciseness. Use after /team runs, skill executions, or when explicitly asked to evaluate output qu

Use when adding server-side API routes to an Expo Router app (+api.ts files) for secrets, database access, third-party proxies, webhooks, CORS, or EAS Hosting deploys. Covers file routing, env vars, a

Audit token consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations. Use when the context window is fi

Clone any website into a pixel-perfect single-file HTML prototype. Extracts design tokens, assets, CSS computed styles, interaction patterns, and content via Playwright. Outputs a self-contained HTML

Build AI applications with OpenAI Agents SDK - text agents, voice agents, multi-agent handoffs, tools with Zod schemas, guardrails, and streaming. Prevents 11 documented errors. Use when: building ag

Use when the user sends or generates an image, screenshot, video, audio or file and wants it saved, or asks to find past media (that diagram, the mockup from last week). Ingests and searches with loca

Use when starting a new project, onboarding to an existing product, or auditing an existing folder structure against the standard. Scaffolds the 16-document set, folder structure, project memory and d

Detailed completeness audit of all project documents. Use when someone asks "are we ready for production", "audit our docs", "readiness check", "nfr tracker", or "what's missing". Do NOT use for a qui

Generate an Architecture Review Board (ARB) presentation in a standard 11-slide format. Use when someone asks to "create an ARB deck", "architecture review presentation", "prepare for architecture rev

Use when finished work needs to reach a coco-managed repository (coco-research/coco or similar) — verifies branch state, commits, pushes through the corporate DLP guard only when actually needed, open

Persistent project goal that survives across sessions and tools, with continuous-execution loop semantics. Use when someone asks to "set a goal", "what is my goal", "goal status", "keep working on X u

Use after a GSD update, when local modifications were backed up to gsd-local-patches/ and must be merged back. Three-way compares the pristine baseline, the backup, and the new install, flagging confl

Use when the user asks for a slideshow, presentation, pitch deck, or interactive deck, or to convert an existing page into a deck. Authors a HyperFrames deck with fragments, branching and presenter mo

Use when executing implementation plans with independent tasks in the current session

Use when the user asks to refresh CLAUDE.local.md, regenerate project context, or after a brain-update session flush. Rewrites only the sentinel-delimited auto-generated section from the brain DB, pre

Use when project files changed since the last brain scan, CLAUDE.local.md was updated, or a periodic refresh is due. Rescans incrementally, writes new entities, decisions, and documents; needs project

End-of-session brain flush. Scans the full conversation, extracts all new entities, decisions, tasks, events, relationships, and updates, presents a summary, and writes to project_brain.db after confi

Use when setting up project memory in a new folder or on the first brain:init in a project. Creates project_brain.db, registers the project, and bootstraps it from CLAUDE.local.md, memory files, docs,

Use when implementing any feature or bugfix, before writing implementation code

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verificat

Train and optimize AI agents using Microsoft's Agent Lightning framework with reinforcement learning. Use when setting up agent training, instrumenting agents with tracing, configuring LightningStore,

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples inclu

Use when you have a spec or requirements for a multi-step task, before touching code

Use when the user says 'm0', 'm0 status', 'start m0', 'cross-tool memory', 'operational thread', or 'where is my memory stored', or when the M0 daemon or MCP wiring needs attention.

Knowledge base from "Solving a Million-Step LLM Task with Zero Errors" (Meyerson, Paolo, Dailey, Shahrzad, Francon, Hayes, Qiu, Hodjat, Miikkulainen — arXiv:2511.09030). Use when designing long-horizo

Use when linked docs drift, when a source file changes and downstream PRDs, decks, or notes must follow, or when a .sync-report.md exists. Diffs the proposed edits, applies them only after approval, a

Use when you want phase research without planning: to investigate before deciding a phase is feasible, or to re-research after a plan already exists. Standalone command; most workflows should use /gsd

Use when the user says 'cognee recall', 'search memory', 'what do we know about', 'find related', or 'graph search'. Runs semantic, graph, and lexical search across the Cognee knowledge graph and inje