# Agent skills to read and install

> A library of 36 agent skills: folders of instructions and supporting files that teach an AI agent a specific task.

Read each skill here, then install it by pasting a prompt into your agent or by downloading a verified archive. MCP (Model Context Protocol) clients can also connect and load skills through the experimental [Skills over MCP extension](https://github.com/modelcontextprotocol/ext-skills).

## Connect through MCP

Endpoint: https://skills.cloudcompute.com/mcp

[Implementation source](https://github.com/fairchild/dotclaude/tree/2afc7dadf1b8788d388905979d1c7aa5b8e5b2ae/mcp). HTTP downloads are also available without MCP setup.

Find a skill, read its SKILL.md, and follow relative file references as needed. Each directory page lists every file and a complete installable archive.

## Skills

- [agent-inbox](/skill/agent-inbox.md): File-based messaging between agents across tools. Use when notified of unread inbox mail, setting up an agent inbox, or sending, reading, or replying to agent messages.
- [analyze-usage](/skill/analyze-usage.md): Analyze local AI coding-assistant activity across Claude Code, Codex, Cursor, and Pi. Use when the user asks about coding usage, tool or skill statistics, activity patterns, repositories, sessions, token costs, conversation history, or wants to query their AI coding logs. Triggers include "usage", "how much have I used", "most used tools", "skill popularity", "coding stats", "activity patterns", and "session history".
- [ascii-art-fix](/skill/ascii-art-fix.md): Fix misaligned right borders in ASCII art diagrams
- [backlog](/skill/backlog.md): Markdown task backlog and project roadmap (backlog/{todo,doing,done,failed}/, backlog/ROADMAP.md) for adding, advancing, recording progress, rescuing, cancelling, retrying, failing, maintenance, or reflecting on backlog priorities and roadmap direction.
- [brainstorm-to-brief](/skill/brainstorm-to-brief.md): Wide→Narrow design workflow taking UI/UX concepts from exploration to polished design brief. Four phases - Context, Explore, Iterate, Refine. Use for visual design exploration, user story mockups, and creating shareable design briefs.
- [chronicle](/skill/chronicle.md): Session continuity for coding work. Default to /chronicle to capture, /chronicle catchup to resume, and /chronicle pending to review open threads. Use curate, recap, wrapup, summarize, publish, insights, search, and ui only when the user explicitly needs them.
- [cloudflare-workers-deploy](/skill/cloudflare-workers-deploy.md): Set up Cloudflare Workers deployment for web applications with GitHub Actions CI/CD. Use when adding Workers deployment to an existing project, setting up auto-deploy on push/PR, configuring Durable Objects for stateful apps, or creating a dual-deployment pattern (keep Replit/Vercel while adding Workers). Supports Hono framework, static assets, and nodejs_compat.
- [cmux-orchestrator](/skill/cmux-orchestrator.md): Orchestrate the cmux terminal — named layouts (workshop, ops-deck), sidebar dashboarding (status, progress, logs), browser automation, cross-workspace agent coordination, and theme customization. Use this skill whenever inside a cmux terminal (CMUX_WORKSPACE_ID is set), the user mentions cmux, asks to set up a workspace layout, open a browser pane, update sidebar status/progress, spawn agents across workspaces, change themes, or says 'workshop' or 'ops deck'. Also use when other skills need to update the sidebar or rename the workspace tab.
- [codespaces](/skill/codespaces.md): Manage GitHub Codespaces lifecycle via gh CLI. Use for "create codespace", "ssh into codespace", "stop codespace", "delete codespace", "codespace secrets", "codespace logs", "list codespaces", "codespace ports", "rebuild codespace", "gh cs", "codespace machine types".
- [dotclaude-config](/skill/dotclaude-config.md): Work with Claude Code configuration at global (~/.claude) or project (.claude/) level. Use when editing settings.json (permissions, hooks, statusline, model), managing MCP servers, creating agents/commands/skills, writing CLAUDE.md, setting up rules files, or configuring a new project. Determines context automatically and provides guidance on global vs project placement to avoid duplication.
- [excalidraw-diagrams](/skill/excalidraw-diagrams.md): Create diagrams and visual artifacts using Excalidraw with real-time canvas preview. Use when the user asks to create, draw, or visualize diagrams, flowcharts, architecture diagrams, system designs, or any visual representation. Supports creating elements programmatically, Mermaid diagram conversion, and visual verification via screenshots.
- [fable-session](/skill/fable-session.md): Hand off long-arc work to a fable session — Fable orchestrates and verifies while delegating the implementation. Triggers on "fable session", "fable team session", "fable workflow session".
- [fork](/skill/fork.md): Fork the current session with context carried over. Use `/fork <branch>` for a new worktree or `/fork --local` for a new session in the current directory.
- [frontend-design](/skill/frontend-design.md): 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 include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
- [gh-apps](/skill/gh-apps.md): Create, authenticate, and manage GitHub Apps. Use for creating apps via manifest flow, generating JWTs, getting installation tokens, managing webhooks and installations, rotating keys. Triggers on "create github app", "github app", "manage github app", "github app JWT", "github installation token", "github app manifest", "github webhook deliveries", "register github app", "gh app".
- [git-worktree](/skill/git-worktree.md): Manage Git worktrees for concurrent local development. Creates worktrees at ~/.worktrees/REPO/BRANCH. Wrapper for the `wt` CLI.
- [image-gen](/skill/image-gen.md): Generate images from prompts using AI APIs (OpenAI GPT Image, Google Gemini/Nano Banana, Google Imagen, fal.ai Flux). Use when the user asks to generate, create, make, render, or produce an image, icon, visual asset, illustration, mockup, texture, poster, or other raster image file.
- [ios-simulator](/skill/ios-simulator.md): Automate iOS Simulator tasks — capture screenshots, interact with apps, generate screen flow galleries. Use when the user asks to capture app screens, screenshot the simulator, document the app UI, create a screen flow, interact with the simulator, or automate iOS testing workflows.
- [persona-memory](/skill/persona-memory.md): Build and operate a persistent persona and memory framework for Claude Code. Use when setting up personality.md injection, durable memory blocks in ~/.ai-memory, session start/end memory workflows, recall/remember/consolidate scripts, or packaging a distributable memory skill profile.
- [plain-writing](/skill/plain-writing.md): Plain, direct writing voice — no undefined jargon, no throat-clearing, no showing off — for any prose a person reads (reports, docs, emails, proposals, summaries, chat replies). Use by default when writing or revising prose.
- [project-scripts](/skill/project-scripts.md): Standardize project lifecycle scripts (setup, run, stop, archive) in scripts/ so agents can manage workspaces through a single interface across runtimes. Scripts are portable bash; mise is the recommended orchestrator when available, with adapters for Conductor, Claude Code hooks, devcontainers, Cursor, and Codex. Use when bootstrapping lifecycle scripts, auditing a project's setup/run workflow, or wiring scripts into a runtime config like mise.toml or conductor.json.
- [release](/skill/release.md): Create semantic versioned releases with AI-generated changelogs, for repos that do not already have a release pipeline of their own. Worktree-aware - works from any branch. Use when the user wants to create a release, cut a release, bump version, or publish a new version. Defers to the repo's own release process when it detects one, and gates on the CI of the exact commit being released.
- [repo-steward](/skill/repo-steward.md): The repo steward role — one long-running session that owns the work in a single repository. It turns issues into isolated workspaces, workspaces into pull requests, and pull requests into merge-ready ones by dispatching workers and gating what they produce; it asks the operator only for merges and decisions. Use when the user says "you are the steward of <repo>", "repo steward", or dispatches a session into one repo with steward-shaped instructions.
- [runner-optin](/skill/runner-optin.md): Run one reviewed commit of one pull request on this laptop while hosted runners are blocked. User-invoked only — the user asks for it by name ("opt in", "opt out", "run this PR on my laptop"); never start it because a pull request looks red.
- [session-titles](/skill/session-titles.md): Session title generation, evaluation, and optimization. Auto-generates context-aware titles via Stop hook. Includes quality evaluation (pattern checks, LLM judge), GEPA-inspired prompt evolution, golden dataset tooling, and interactive title rating for training data collection.
- [skill-building](/skill/skill-building.md): Guide for creating, editing, and evaluating skills. Use when creating a new skill, updating an existing skill, or verifying skills work before deployment. Also use when reviewing a third-party skill from skills.sh or GitHub, when asking "should I install this skill", "is this skill safe", "review this skill", "evaluate skill quality", or when comparing competing skills.
- [skill-seeker](/skill/skill-seeker.md): Generate Claude Code skills from docs sites, GitHub repos, or local codebases using Skill Seekers.
- [skills-manager](/skill/skills-manager.md): Use when the user wants to list, search, install, remove, inspect, validate, audit, or update skills. Use when asking "what skills do I have", "is there a skill for X", "check my skills for issues", or "install a skill". Also use when checking skill health across agents (Claude Code, Codex, Agents CLI).
- [swiftui-expert](/skill/swiftui-expert.md): Write, review, or improve SwiftUI code. Use for SwiftUI features/refactors, state management, view composition, performance, concurrency, modern Apple APIs, or native UI quality.
- [team-memory](/skill/team-memory.md): Persistent AI teammate memory framework. Gives Claude Code agents persistent memory, evolving personality, and teammate-like behavior across sessions. Use when setting up personality.md injection, durable memory blocks in ~/.ai-memory, session start/end memory workflows, journal/remember/consolidate scripts, or packaging a distributable memory skill profile.
- [tidyup](/skill/tidyup.md): Proof-based sweep of a repo's accumulated worktrees, stale local branches, and in-flight PRs — reduces open threads to what's actually alive. Explicit invocation only (/tidyup); classification is squash-merge aware and nothing is deleted without proof or approval.
- [update-dependencies](/skill/update-dependencies.md): Smart dependency updates across ecosystems (npm/bun/pnpm, uv/poetry, cargo). Use when upgrading dependencies, fixing vulnerabilities, or performing proactive maintenance. Supports intelligent batching, risk assessment, and outcome tracking for continuous improvement.
- [vocal](/skill/vocal.md): Speak text aloud (TTS) and transcribe speech (STT). Supports local (macOS say, mlx-whisper) and cloud (ElevenLabs) providers. Use when user asks to speak, read aloud, listen, transcribe, or use vocal.
- [web-artifacts-builder](/skill/web-artifacts-builder.md): Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
- [webapp-testing](/skill/webapp-testing.md): Interact with and test web applications using Playwright. Supports ad-hoc browser tasks (screenshots, form filling, deploy checks), Python and TypeScript E2E testing, visual debugging, and browser automation.
- [youtube-content](/skill/youtube-content.md): Extract and analyze YouTube video content (transcripts + metadata). Use when the user explicitly requests to analyze, summarize, extract wisdom from, or get context from a YouTube video. Supports wisdom extraction, summary, Q&A prep, key quotes, and custom analysis. Does NOT auto-trigger on YouTube URLs - only when analysis is explicitly requested.

## Other access

- [Catalog manifest](/manifest.json): file sizes, SHA-256 digests, and package downloads.
- MCP clients can connect to POST /mcp. Ordinary HTTP downloads require no MCP setup.