Library
85,336 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Anthropic Agent Skills
SkillsAnthropic's public collection of agent skills, including the document skills behind Claude's Word, PDF, PowerPoint and Excel features.
/plugin marketplace add anthropics/skills -
skills.sh and the skills CLI
SkillsA public directory of open agent skills, and the npx command that installs them from GitHub into your coding agent.
npx skills add vercel-labs/agent-skills -
Taste Skill
SkillsDesign rules that steer coding agents away from generic, AI-looking interfaces: layout, type, colour and motion.
npx skills add https://github.com/Leonxlnx/taste-skill --skill "design-taste-frontend" -
Impeccable
SkillsA design skill with commands to audit, critique and polish a frontend, plus a detector for common UI problems.
npx impeccable install -
Skills for Real Engineers
SkillsEngineering skills for coding agents: test-driven development, debugging, code review, architecture and planning.
claude plugin install mattpocock-skills@claude-plugins-official -
Superpowers
SkillsA skills framework and working method for coding agents, from planning a change to building and checking it.
/plugin install superpowers@claude-plugins-official -
Humanizer
SkillsEdits AI-written text so it reads like a person wrote it, based on Wikipedia's guide to the signs of AI writing.
-
Claude Code prompt library
PromptsAnthropic's copy-and-paste prompts for Claude Code, tagged by task, each with a note on why it works.
-
Claude prompt engineering guide
PromptsAnthropic's official guide to getting better results from Claude, one technique at a time.
-
Anthropic's prompt engineering course as notebooks you work through step by step.
-
OpenAI prompting guide
PromptsOpenAI's official guide to writing prompts for its models.
-
Turns a company's website text into a short list of problems you can see evidence for, what each might cost, and the one fix worth raising first.
-
Converts call notes into a written spec with goals, scope, acceptance checks and open questions, ready to hand to a coding agent.
-
Writes a short first email built on one specific thing you noticed about the business, for you to check and send yourself.
-
Price a job from the outcome
PromptsHelps you set a price from the client's situation, risk and value instead of counting pages or hours, and lays out three options.
-
Model Context Protocol
MCP serversThe open standard for connecting AI apps to tools and data. Start here to understand servers, clients, tools and resources.
-
Official MCP Registry
MCP serversThe MCP project's own registry of public MCP servers, so you can look for a connector before building one.
-
MCP reference servers
MCP serversSmall example servers from the MCP project (filesystem, git, fetch, memory and more) that show how MCP works.
-
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Playwright MCP
MCP serversLets an agent drive a real browser: open pages, click, fill in forms and read what's on screen.
claude mcp add playwright npx @playwright/mcp@latest -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
Connect MCP servers to Claude Code
MCP serversAnthropic's guide to adding MCP servers to Claude Code, with examples of local and remote servers.
-
Claude Code
AI repositoriesAnthropic's coding agent. It reads your project, edits files and runs commands from the terminal or your editor.
curl -fsSL https://claude.ai/install.sh | bash -
Claude Code GitHub Action
AI repositoriesRuns Claude Code inside GitHub so it can answer questions on pull requests and issues and make changes when asked.
/install-github-app
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.