CommandVault
Search prompts, CLAUDE.md/AGENTS.md templates, Cursor rules, Agent Skills and MCP servers.
Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
Remote (streamable-http)
Claude Code
claude mcp add --transport http commandvault 'https://commandvault.ai/api/mcp'Configuration JSON (Claude Desktop, Cursor, VS Code)
{
"mcpServers": {
"commandvault": {
"type": "http",
"url": "https://commandvault.ai/api/mcp"
}
}
}Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
Sommaire
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/mcpSetup 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@commandvaultLayout
| 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 2026-10-26: 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. |
MCP servers (70)
| Description | |
|---|---|
| Airtable MCP server (community) · web | Read and write Airtable bases, tables and records, and inspect schemas, with a personal access token. |
| Apify MCP server (official, remote) · web | Run thousands of ready-made Apify Actors for scraping social media, maps, search engines and e-commerce. |
| Asana MCP server (official, remote) · web | Read and update Asana tasks, projects, portfolios and goals through Asana's hosted server. |
| Atlassian Rovo MCP server (official, remote) · web | Search, read and update Jira issues and Confluence pages (plus Compass) through Atlassian's hosted server. |
| AWS API MCP server (AWS Labs) · web | Let an agent run validated AWS CLI commands across every AWS service, with read-only and mutation-consent options. |
| AWS Knowledge MCP server (official, remote) · web | Free hosted server for searching and reading AWS documentation, blogs, What's New posts and regional availability. |
| Azure MCP server (Microsoft) · web | Work with Azure resources such as Storage, Cosmos DB, Key Vault, Monitor and AKS from one Microsoft-maintained server. |
| Box MCP server (official, remote) · web | Search, read and work with Box files and folders, including Box AI Q&A, through Box's hosted server. |
| Brave Search MCP server (official) · web | Web, news, image, video and local search with AI summaries, powered by the independent Brave Search API. |
| Browserbase MCP server (official, remote) · web | Control cloud browsers with Stagehand: navigate, act, observe and extract data from real web pages. |
| Buildkite MCP server (official, remote) · web | Inspect Buildkite pipelines, builds, jobs, logs and test results from your agent. |
| Chrome DevTools MCP · web | Gives your agent Chrome DevTools: performance traces, network requests, console messages and screenshots of a live page. |
| CircleCI MCP server (official) · web | Get CircleCI build failure logs, flaky tests and pipeline status, and validate config, from your editor. |
| ClickHouse MCP server (official) · web | Explore ClickHouse databases and run analytical SQL, read-only by default, plus an optional embedded chDB engine. |
| Cloudflare docs MCP server · web | Search Cloudflare's documentation (Workers, Pages, R2, D1, DNS and more) from your agent. No sign-in. |
| Cloudflare Observability MCP server (official, remote) · web | Query Cloudflare Workers logs and analytics to debug errors and performance from your agent. |
| Cloudflare Workers Bindings MCP server (official, remote) · web | Build on Cloudflare: manage Workers, KV, R2, D1 and Hyperdrive resources from a hosted OAuth server. |
| CommandVault MCP server · web | Search CommandVault's prompts, CLAUDE.md templates, Cursor rules, skills and MCP servers from your editor. |
| Context7: up-to-date library docs · web | Pulls current, version-specific docs and code examples for thousands of libraries into your prompt, so the agent stops inventing old APIs. |
| Datadog MCP server (official, remote) · web | Search Datadog logs, metrics, traces, monitors, incidents and dashboards from your agent. |
| DeepWiki MCP: ask any GitHub repo · web | Ask questions about any public GitHub repository and get answers from its generated wiki. No sign-in. |
| Docker MCP Gateway (official) · web | Run containerised MCP servers from Docker's catalog behind one gateway, with isolation and secrets handling. |
| Dropbox MCP server (official, remote) · web | Search and read files in Dropbox through Dropbox's hosted OAuth server. |
| Everything MCP server (reference test server) · web | Test server exercising every MCP feature: tools, resources, prompts, sampling, logging and more. |
| Exa web search MCP · web | Fast web search and page fetching built for AI agents, with clean text results. |
| Fetch MCP server · web | Fetches a web page and converts it to Markdown for the model to read. |
| Figma MCP server (official, remote) · web | Give your coding agent Figma design context: layout, variables, components and screenshots for design-to-code. |
| Filesystem MCP server (reference) · web | Read, write, search and move files, limited to the folders you allow. |
| Firecrawl MCP server (official) · web | Scrape, crawl, map, search and extract structured data from websites as clean markdown. |
| gcloud MCP server (Google Cloud) · web | Drive Google Cloud through the gcloud CLI from your agent, using your existing gcloud login. |
| Git MCP server (reference) · web | Read and operate on local Git repositories: status, diffs, logs, branches, commits. |
| GitHub MCP server (official, remote) · web | Read and manage repos, issues, pull requests, Actions and code search from your agent, hosted by GitHub. |
| GitLab MCP server (official, remote) · web | Work with GitLab issues, merge requests, pipelines and repositories on GitLab.com or self-managed. |
| Google Workspace MCP (community) · web | Gmail, Drive, Docs, Sheets, Calendar, Slides, Forms, Chat and Tasks in one OAuth server, with tool tiers and read-only mode. |
| Grafana MCP server (official) · web | Search dashboards, query Prometheus and Loki, inspect alerts and incidents in Grafana or Grafana Cloud. |
| Hugging Face MCP server · web | Search models, datasets, Spaces and papers on the Hugging Face Hub, and call Gradio Spaces as tools. |
| Kubernetes MCP server (community) · web | Native Go server for Kubernetes and OpenShift: pods, logs, events, resources and Helm, with read-only mode. |
| Linear MCP server (official, remote) · web | Find, create and update Linear issues, projects and comments without leaving your editor. |
| MCP Toolbox for Databases (Google) · web | One server for Postgres, MySQL, SQL Server, SQLite, BigQuery, AlloyDB, Spanner and more, with prebuilt or custom tools. |
| Memory MCP server (knowledge graph) · web | Gives your assistant a persistent memory as a local knowledge graph of entities, relations and observations. |
| Microsoft Learn MCP server · web | Search and fetch official Microsoft documentation (Azure, .NET, Microsoft 365, Windows) from your agent. No sign-in. |
| monday.com MCP server (official, remote) · web | Read and update monday.com boards, items, updates and docs from your agent. |
| MongoDB MCP server (official) · web | Query MongoDB databases and manage Atlas clusters from an agent, read-only by default in the documented config. |
| Neon MCP server (official, remote) · web | Manage Neon serverless Postgres projects, branches and SQL from your agent over a hosted OAuth endpoint. |
| Netlify MCP server (official) · web | Create, deploy and manage Netlify sites, env vars, forms and extensions from your coding agent. |
| Notion MCP server (official, remote) · web | Search, read and write Notion pages and databases from your AI tool. |
| PagerDuty MCP server (official, remote) · web | Look up and manage PagerDuty incidents, services, schedules and on-call from a hosted server. |
| PayPal MCP server (official, remote) · web | Create invoices, orders, products and subscriptions and look up transactions and disputes in PayPal. |
| Perplexity MCP server (official) · web | Web-grounded answers, deep research and reasoning from Perplexity's Sonar models, plus raw search results. |
| PlanetScale MCP server (official, remote) · web | Query PlanetScale Postgres and MySQL databases and read Insights and schema recommendations via hosted MCP. |
| Playwright MCP: browser automation · web | Lets your agent drive a real browser through the accessibility tree: navigate, click, fill forms, take snapshots and test your app. |
| Postgres MCP Pro (community) · web | Postgres server with schema exploration, EXPLAIN plans, index tuning and health checks, with a restricted read-only mode. |
| Postman MCP server (official, remote) · web | Manage Postman workspaces, collections, environments, mocks and monitors, or generate client code from APIs. |
| Prisma MCP server (official, remote) · web | Create and manage Prisma Postgres databases, backups and connection strings from your agent. |
| Railway MCP server (official, remote) · web | Hosted Railway server for listing projects and services, deploying and handing ops tasks to Railway's agent. |
| Redis MCP server (official) · web | Read and write Redis keys, hashes, lists, streams, JSON and vector indexes through natural language. |
| Semgrep MCP server (official) · web | Scan code for security bugs and secrets with Semgrep rules, or write custom rules, from your coding agent. |
| Sentry MCP server (official, remote) · web | Bring Sentry errors, stack traces and releases into your agent so it can find and fix the bug behind an issue. |
| Sequential Thinking MCP server (reference) · web | A structured scratchpad tool that helps an agent break problems into revisable, branching steps. |
| Shopify Dev MCP server (official) · web | Search Shopify developer docs and introspect the Admin GraphQL schema to build Shopify apps and themes accurately. |
| Snyk MCP server (official) · web | Run Snyk code, dependency, container and IaC security scans from your agent via the Snyk CLI. |
| Sourcegraph MCP server (official, remote) · web | Code search, navigation and history across all your repositories through your Sourcegraph instance. |
| Stripe MCP server (official, remote) · web | Work with the Stripe API and search Stripe's docs and knowledge base from your agent. |
| Supabase MCP server (official, remote) · web | Manage Supabase projects from your agent: run SQL, apply migrations, read logs and advisors, generate TypeScript types. |
| Tavily MCP server (official, remote) · web | Search, extract, crawl and map the web with Tavily's agent-focused search API. |
| Terraform MCP server (HashiCorp) · web | Look up Terraform Registry providers, modules and policies, and work with HCP Terraform workspaces and runs. |
| Time MCP server (reference) · web | Get the current time in any timezone and convert times between timezones. |
| Todoist MCP server (official, remote) · web | Manage Todoist tasks, projects, sections, labels and comments from your agent. |
| Vercel MCP server (official, remote) · web | Search Vercel docs, and inspect your projects, deployments and build logs from your agent. |
| Zapier MCP (official, remote) · web | Give your agent actions in thousands of apps through Zapier, choosing exactly which actions it can run. |
Context files and templates (CLAUDE.md, AGENTS.md, Cursor rules) (40)
| Description | |
|---|---|
| AGENTS.md for a monorepo · web | One root AGENTS.md plus per-package overrides so Codex, Cursor, Jules and other agents work the same way everywhere. |
| Blameless postmortem write-up · web | Turn incident notes into a postmortem the team will actually read. |
| Claude Code custom slash command: /review · web | Save as .claude/commands/review.md to get a one-word, consistent code review in Claude Code. |
| Claude Code hooks: format on save and block dangerous commands · web | A .claude/settings.json with hooks that auto-format edited files and stop risky shell commands. |
| Claude Code slash command: /commit · web | Save as .claude/commands/commit.md for clean, conventional commit messages from your staged changes. |
| Claude Code slash command: /fix-issue · web | Save as .claude/commands/fix-issue.md: give it a GitHub issue number and it reproduces, fixes and tests. |
| Claude Code slash command: /plan · web | Save as .claude/commands/plan.md to make Claude investigate and plan before writing any code. |
| Claude Code subagent: code reviewer · web | A .claude/agents/code-reviewer.md that reviews changes for bugs, risk and simplicity. |
| Claude Code subagent: database migration checker · web | A .claude/agents/migration-checker.md that reviews migrations for locks, data loss and rollback. |
| Claude Code subagent: debugger · web | A .claude/agents/debugger.md that finds root causes instead of patching symptoms. |
| Claude Code subagent: docs writer · web | A .claude/agents/docs-writer.md that keeps README and docs in sync with the code. |
| Claude Code subagent: refactorer · web | A .claude/agents/refactorer.md that simplifies code without changing behavior. |
| Claude Code subagent: security auditor · web | A .claude/agents/security-auditor.md that checks changes for the vulnerabilities attackers try first. |
| Claude Code subagent: test writer · web | A .claude/agents/test-writer.md subagent that writes focused tests in your project's style. |
| CLAUDE.md template for a Django project · web | Give Claude Code your Django project's commands, app layout and rules in one file. |
| CLAUDE.md template for a Go service · web | Tell Claude Code how your Go service is built, tested and structured. |
| CLAUDE.md template for a Laravel app · web | Project memory for Claude Code in Laravel: Artisan commands, structure and conventions. |
| CLAUDE.md template for a Next.js + Supabase app · web | A ready-to-edit CLAUDE.md that tells Claude Code how your Next.js app is built, tested and deployed. |
| CLAUDE.md template for a Python FastAPI service · web | Project memory for Claude Code on a Python API: commands, layout, testing and the rules that keep it safe. |
| CLAUDE.md template for a Ruby on Rails app · web | Project memory for Claude Code in a Rails codebase: commands, structure and Rails-specific rules. |
| Cursor project rules for React + TypeScript · web | A .cursor/rules/*.mdc file that keeps Cursor's agent consistent with your React codebase. |
| Cursor rules for Go · web | A .cursor/rules/go.mdc for idiomatic errors, contexts, interfaces and tests. |
| Cursor rules for Next.js App Router · web | A .cursor/rules/nextjs.mdc file for server components, data fetching, routing and caching done right. |
| Cursor rules for Prisma · web | A .cursor/rules/prisma.mdc for schema changes, migrations and efficient queries. |
| Cursor rules for Python projects · web | A .cursor/rules/python.mdc for typed, tested, well-structured Python. |
| Cursor rules for Supabase · web | A .cursor/rules/supabase.mdc covering row-level security, migrations, auth and safe client usage. |
| Cursor rules for SvelteKit · web | A .cursor/rules/sveltekit.mdc file for load functions, form actions and Svelte 5 runes. |
| Cursor rules for Tailwind CSS · web | A .cursor/rules/tailwind.mdc that keeps utility classes consistent, readable and on-brand. |
| Cursor rules for Vue 3 + TypeScript · web | A .cursor/rules/vue.mdc file for Composition API, typed props and Pinia stores. |
| Form validation schema with friendly errors · web | Generate a Zod schema plus human error messages for any form. |
| GitHub Actions CI for a Node app · web | Lint, typecheck, test and build on every pull request, with caching. |
| GitHub Copilot custom instructions file · web | A .github/copilot-instructions.md that makes Copilot chat and agent mode follow your repo's rules. |
| KPI dashboard spec · web | Define metrics precisely before anyone builds a chart. |
| Make flashcards from my notes · web | Turn notes into spaced-repetition cards that test understanding. |
| Meeting notes to action items · web | Turn messy notes or a transcript into decisions and owners. |
| Plain-English privacy policy draft · web | A readable first draft to review with a lawyer. |
| Project context pack for coding agents · web | A reusable AGENTS.md that stops your AI agent from guessing. |
| README that people actually read · web | A clear README for any project in the right order. |
| SEO blog post brief · web | Everything a writer needs to rank for one keyword. |
| Write a reusable AI skill file · web | Package a repeatable task into instructions an agent can load on demand. |
Prompts, workflows and checklists (55)
| Description | |
|---|---|
| 30-day learning plan for any skill · web | A realistic daily plan with projects and checkpoints. |
| Add a background job safely · web | Move slow work out of the request with retries and idempotency. |
| Autosave Form Drafts · web | Prevent data loss on long forms |
| Break a big project into a plan · web | From a vague goal to milestones, tasks and a first step for today. |
| Build an accessible React component · web | Get a production-ready component with keyboard support, ARIA and tests. |
| Code review as a senior engineer · web | A focused review that finds real bugs instead of nitpicks. |
| Cold email that gets replies · web | Short, specific outreach with follow-ups. |
| Convert a design screenshot into clean HTML/CSS · web | Turn a mockup into semantic, responsive markup without a framework. |
| Convert CLAUDE.md into AGENTS.md, GEMINI.md and Cursor rules · web | Write your project rules once and get the file every major coding agent reads. |
| Database migration safety review · web | Catch locking, data loss and rollback problems before running a migration. |
| Debounced Live Search · web | Reduce server load while users type |
| Decision matrix for a tough choice · web | Compare options against weighted criteria and surface what really matters. |
| Definition of done block for agent context files · web | Paste into CLAUDE.md or AGENTS.md so agents stop declaring victory before the work is verified. |
| Design a REST API for a feature · web | Endpoints, payloads, status codes and edge cases before you write code. |
| Edit for clarity without changing my voice · web | Tighter sentences, same personality. |
| Explain a technical topic to non-technical readers · web | Clear explanations with analogies and no jargon. |
| Explore a new dataset · web | A first-hour analysis plan for any CSV or table. |
| Find and fix React re-render problems · web | Diagnose why a component tree is slow and get concrete fixes. |
| Find leaked secrets and rotate them · web | Locate exposed keys in a repo and plan a safe rotation. |
| Generate an AGENTS.md from an existing codebase · web | Have your coding agent read the repo and write an accurate AGENTS.md instead of guessing. |
| Graceful 404 Fallback · web | Keep users oriented on bad URLs |
| Harden authentication flows · web | Review sign-up, login and reset flows for common account takeover holes. |
| Incident response first 30 minutes · web | A calm, ordered playbook for when production is down. |
| Instant Email Verification Link · web | Verify new accounts seamlessly |
| Landing page copy that converts · web | Headline, sections and CTA written for one specific audience. |
| Local Business Directory System · web | A full template including initial command and knowledge base to build a local business directory service that you can apply to your local community and start helping small businesses while making a profit. |
| Model a Postgres schema with row-level security · web | Tables, indexes and RLS policies for a multi-user feature. |
| One-Click Password Reset · web | Fast, secure password recovery |
| Outline a long-form article · web | Structure, argument and hooks before you write a word. |
| Plan → implement → verify loop · web | Make an AI agent plan first, work in small steps and prove each one. |
| Practice interview with feedback · web | Mock interview for any role, one question at a time. |
| Pre-launch UI polish checklist · web | Walk a page through the details users notice before you ship. |
| Product launch plan · web | Two weeks of launch tasks across channels, day by day. |
| Repurpose one piece into a week of posts · web | Turn an article, video or talk into social content for each platform. |
| Role-Based Access Control · web | Limit sensitive features to the right people |
| Safety rules block for coding agents · web | A 'never do' section for CLAUDE.md / AGENTS.md that prevents the expensive mistakes. |
| Sanity-check an A/B test result · web | Decide whether an experiment result is real before you ship it. |
| Scroll-to-Top on Every Navigation · web | This commands ensures that when a user lands on any page of an application, the user gets taken to the very top of that page, and not the position the user was on the previous page. |
| Set up Claude Code in an existing repo · web | A first-session prompt that has Claude Code explore your repo and create CLAUDE.md, commands and settings. |
| Set up structured logging and alerts · web | Logs you can search and alerts that only fire when it matters. |
| Skeleton Loading Placeholders · web | Smooth perceived performance |
| Spreadsheet formula helper · web | Get the exact Excel / Google Sheets formula with an explanation. |
| Summarize a paper or long article · web | Key ideas, evidence and limitations in five minutes. |
| Teach me with the Feynman technique · web | Learn a concept by explaining it simply and finding the gaps. |
| Threat model a new feature · web | STRIDE-style review that ends with concrete mitigations. |
| Turn a vague request into a precise prompt · web | Rewrite any rough ask into a prompt with role, context, constraints and output format. |
| Universal Dark-Mode Toggle · web | Persist a user’s light/dark preference across sessions and devices. |
| Update CLAUDE.md after a coding session · web | End-of-session prompt that turns what the agent learned into permanent project memory. |
| Web app security review · web | Check an app against the issues attackers try first. |
| Weekly review and planning · web | A 30-minute ritual to close the week and plan the next one. |
| Write a hard email diplomatically · web | Say no, push back or deliver bad news without burning bridges. |
| Write a minimal production Dockerfile · web | Small, cached, non-root images for any app. |
| Write a SQL query from a plain question · web | Describe your tables and ask in English; get correct, readable SQL. |
| Write integration tests for an endpoint · web | Cover the happy path, auth and the edge cases that bite in production. |
| Write release notes users care about · web | Turn a changelog or commit list into readable release notes. |
Questions fréquentes
Qu'est-ce que CommandVault ?
Search prompts, CLAUDE.md/AGENTS.md templates, Cursor rules, Agent Skills and MCP servers.
Comment installer CommandVault ?
Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http commandvault 'https://commandvault.ai/api/mcp'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.
Faut-il une clé API pour CommandVault ?
Son entrée au registre n'indique aucune clé ni secret obligatoire. Certaines fonctions peuvent tout de même demander un compte auprès du service auquel il se connecte.
CommandVault est-il open source ?
Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.
Qui maintient CommandVault ?
Il est publié par geronco. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.