CommandVault MCP server

CommandVault library

AI commands from commandvault.ai: prompts, CLAUDE.md / AGENTS.md templates, Cursor rules, Claude Code slash commands and subagents, Agent Skills and MCP servers. Every item has fill-in {{blanks}} and links back to its page, where you can fill the blanks in the browser. Entries marked tested on the site were run in Claude Code and Codex before publishing.

This repo is synced automatically every day from the site. To suggest a change, comment on the item's page on commandvault.ai (pull requests to the generated files are overwritten by the next sync).

Use it from your AI tool

MCP server (no key needed):

claude mcp add --transport http commandvault https://commandvault.ai/api/mcp

Setup for Cursor, VS Code, Codex, Claude Desktop and Gemini CLI: commandvault.ai/mcp.

Claude Code plugin (MCP server + a lookup skill + /vault command):

/plugin marketplace add geronco/commandvault-library
/plugin install commandvault@commandvault

Layout

Folder	What's in it
commands/<community>/	Prompts, templates and checklists as Markdown with front matter
skills/<name>/SKILL.md	Agent Skills, ready to copy into .claude/skills/
mcp-servers/<name>.json	MCP server configs (mcpServers format)
data/commands.json, data/commands.csv	Everything in one file, for datasets and scripts

License

Content: CC BY 4.0. Credit "CommandVault (commandvault.ai)" with a link. Code (scripts, workflow, plugin): MIT.

Third-party skills (skills/third-party/) and MCP servers are linked, not copied: each file names the author, source repo and license, and the original keeps its own license.

Synced from commandvault.ai on 2026-11-12: 240 items.

Agent Skills (75)

	Description
Accessibility audit (Addy Osmani) · web	Audit and fix web accessibility issues against WCAG 2.2.
AI search optimization (Marketing Skills) · web	Helps your content get cited by ChatGPT, Perplexity, Claude and Google AI Overviews.
Brainstorming before building (Superpowers) · web	Turns a rough idea into an agreed design through focused questions before any code is written.
Canvas design (Anthropic) · web	Create original posters and static art as PNG or PDF, guided by a design philosophy.
Claude API reference (Anthropic) · web	Up-to-date guidance for building apps on the Claude API and Anthropic SDKs.
Claude Code automation recommender (Anthropic) · web	Analyzes your codebase and recommends hooks, subagents, skills and MCP servers to set up.
Claude Code hook development (Anthropic) · web	How to write Claude Code hooks that validate, block or automate tool use.
CLAUDE.md improver (Anthropic) · web	Audits your repo's CLAUDE.md files, scores them and makes targeted improvements.
Cloudflare Agents SDK (Cloudflare) · web	Build stateful AI agents on Cloudflare with the agents package.
Cloudflare platform guide (Cloudflare) · web	Helps pick and use the right Cloudflare products for apps, APIs, agents and storage.
CodeQL scan (Trail of Bits) · web	Builds a CodeQL database and runs data-flow and taint analysis to find vulnerabilities.
Conversation to spec (Matt Pocock) · web	Turns what you've discussed into a structured spec and files it in your issue tracker.
Conversion rate optimization (Marketing Skills) · web	Reviews a page or form and suggests changes and experiments to lift conversions.
dbt analytics engineering (dbt Labs) · web	Build and modify dbt models the right way: ref/source, tests and checking results with dbt show.
Deploy to Vercel (Vercel) · web	Deploys the current project to Vercel and returns a preview or production URL.
Doc co-authoring workflow (Anthropic) · web	A structured workflow for writing specs, proposals and decision docs together with Claude.
Excel spreadsheets (Anthropic) · web	Create, clean and analyze Excel and CSV files with working formulas and formatting.
Exploratory data analysis (K-Dense) · web	Careful, local exploratory analysis of data files with leakage, missingness and outlier checks.
Expo native UI (Expo) · web	Build native-feeling Expo screens with Apple HIG styling, native controls and SF Symbols.
Find bugs in your branch (Sentry) · web	Reviews the changes on your branch for bugs, security holes and quality issues.
Frontend design (Anthropic) · web	Push UI work past generic defaults toward a distinctive, deliberate visual design.
Gemini API development (Google) · web	Google's guide to writing correct, current code against the Gemini API in Python and TypeScript.
Git worktrees for isolation (Superpowers) · web	Sets up an isolated git worktree with a clean, passing baseline before feature work starts.
GitHub Actions security review (Sentry) · web	Finds exploitable flaws in GitHub Actions workflows, like pwn requests and script injection.
Gradio apps (Hugging Face) · web	Build Gradio web UIs and demos in Python, from simple forms to chatbots.
Grill me (Matt Pocock) · web	Has Claude interview you relentlessly to stress-test a plan or design.
Hugging Face Hub CLI (Hugging Face) · web	Use the hf CLI to download, upload and manage models, datasets, Spaces and jobs on the Hub.
Improve codebase architecture (Matt Pocock) · web	Scans a codebase for places to deepen modules and presents them as a visual HTML report.
Iterate on a PR until green (Sentry) · web	Loops on a pull request, fixing CI failures and review feedback until checks pass.
LLM fine-tuning on HF Jobs (Hugging Face) · web	Fine-tune language and vision models with TRL or Unsloth on Hugging Face cloud GPUs.
Marketing copywriting (Marketing Skills) · web	Writes and rewrites landing, pricing and product page copy that sounds human and converts.
MCP server builder (Anthropic) · web	Build well-designed MCP servers in Python or TypeScript that wrap an external API.
Neon Postgres (Neon) · web	Neon's guide to connections, branching, migrations, autoscaling and search on Neon Postgres.
PDF toolkit (Anthropic) · web	Read, create, merge, split, fill and OCR PDF files from inside Claude.
Playwright CLI browser automation (Microsoft) · web	Control a real browser from the terminal with playwright-cli: navigate, click, fill, test.
Postgres best practices (Supabase) · web	Supabase's prioritized Postgres rules for schema, indexes, RLS, migrations and slow queries.
PowerPoint decks (Anthropic) · web	Build, edit and QA PowerPoint presentations, from pitch decks to template updates.
Property-based testing (Trail of Bits) · web	Write and review property-based tests with Hypothesis, fast-check, proptest and more.
React & Next.js performance (Vercel) · web	Vercel's ranked rules for faster React and Next.js code: waterfalls, bundles, rendering.
React composition patterns (Vercel) · web	Patterns for flexible React components: compound components, context and fewer boolean props.
React Native performance (Callstack) · web	Callstack's ranked guide to fixing React Native jank, slow startup, big bundles and leaks.
Repository threat model (OpenAI) · web	Produces a threat model for a codebase: trust boundaries, assets, attackers and mitigations.
Requesting code review (Superpowers) · web	Sends finished work to a reviewer subagent that checks it against the plan and requirements.
Security diff review (Trail of Bits) · web	Security-focused review of a PR or diff, with blast radius, history and test coverage checks.
Semgrep security scan (Trail of Bits) · web	Runs a planned, approved Semgrep scan of a codebase and merges results into SARIF.
SEO audit (Marketing Skills) · web	Diagnoses technical, on-page and content SEO problems and gives a prioritized fix list.
Skill creator (Anthropic) · web	Design, test and tune your own Agent Skills, including evals and description tuning.
Skill: accessibility check · web	Reviews a page or component against the most common WCAG failures and fixes them.
Skill: changelog from git history · web	Turns commits since the last release into a readable, user-facing changelog.
Skill: conventional commit messages · web	Writes clear Conventional Commits messages from the staged diff, with a body that explains why.
Skill: incident postmortem · web	Drafts a blameless postmortem from notes, logs and a timeline.
Skill: Next.js App Router conventions · web	Keeps the agent on current App Router patterns: server components, server actions, caching and metadata.
Skill: pull request description · web	Drafts a reviewer-friendly PR description from the branch's commits and diff.
Skill: safe dependency upgrades · web	Upgrades packages one at a time with changelog checks and tests between each step.
Skill: Supabase RLS review · web	Audits Supabase tables, policies and functions for data-exposure mistakes before they ship.
Skill: systematic debugging · web	Makes the agent reproduce, isolate and prove a bug's cause before changing code.
Skill: test-first changes · web	Has the agent write a failing test, make it pass, then tidy up, for any behaviour change.
Stripe integration best practices (Stripe) · web	Stripe's own guidance on choosing the right APIs and building secure payment integrations.
Subagent-driven development (Superpowers) · web	Executes a plan by sending each task to a fresh subagent, with a review after every step.
Supabase (Supabase) · web	Official guidance for any Supabase work: database, auth, RLS, storage, edge functions, CLI.
Supply-chain risk audit (Trail of Bits) · web	Audits your dependency tree for advisories, abandoned packages and risky install scripts.
Systematic debugging (Superpowers) · web	A four-phase process that finds the root cause of a bug before any fix is attempted.
TDD loop (Matt Pocock) · web	A compact red-green-refactor guide focused on good tests, seams and avoiding mocks.
Terraform style guide (HashiCorp) · web	Write Terraform that follows HashiCorp's official style, naming and file layout.
Terraform tests (HashiCorp) · web	Write and run Terraform's native .tftest.hcl tests, including mocks and assertions.
Test-driven development (Superpowers) · web	Enforces red-green-refactor: write a failing test first, then the minimal code to pass it.
Upgrade Stripe versions (Stripe) · web	Step-by-step help upgrading Stripe API versions, SDKs, Stripe.js and webhooks.
Verify before claiming done (Superpowers) · web	Requires Claude to run real checks and show evidence before saying work is finished.
Web app testing with Playwright (Anthropic) · web	Drive a local web app in a real browser to test flows, grab screenshots and read logs.
Web artifacts builder (Anthropic) · web	Build multi-component React + Tailwind + shadcn/ui apps bundled into a single HTML file.
Web interface guidelines review (Vercel) · web	Audits UI code against Vercel's web interface guidelines and reports issues by file and line.
Web quality audit (Addy Osmani) · web	Audits a site for performance, accessibility, SEO and best practices, Lighthouse-style.
Word documents (Anthropic) · web	Create and edit Word .docx files with real formatting, tracked changes and comments.
Wrangler CLI (Cloudflare) · web	Run and troubleshoot Wrangler for local dev, previews, deploys and resources.
Writing implementation plans (Superpowers) · web	Converts a spec into a step-by-step implementation plan with small, testable tasks.