# Measured Agents > A catalog of agent skills, plugins, MCP servers and agents. Each entry has public facts, an EU AI Act checklist and, when verified, a measured agreement score between an agent and a human expert on a held-out golden set (N >= 30, noise floor <= 0.10), re-measured when the model changes. Scores are never estimates. Tiers: Pilot (10-29 cards, report public, no number), Verified (>= 30), Verified+ (>= 100 or two independent experts). Full catalog as JSON: https://measuredagents.com/catalog.json ## Professions - [Business analyst](https://measuredagents.com/professions/business-analyst): Reports, decks, spreadsheets and documents produced and checked by agents for business decisions. - [Data analyst](https://measuredagents.com/professions/data-analyst): Data collection, cleaning and reporting workflows run by agents and scrapers. - [FinOps engineer](https://measuredagents.com/professions/finops-engineer): Cloud and LLM spend attribution, invoice reconciliation and cost fixes. - [HR compliance officer](https://measuredagents.com/professions/hr-compliance): Employer-level duties under labour and pay-transparency law; deadlines, exposure and what to fix first. Not decisions about individual employees. - [Recruiter](https://measuredagents.com/professions/recruiter): Screening, shortlisting and outreach decisions in recruitment. High-risk domain under the EU AI Act (Annex III, employment); a named human decides every outcome. - [Software engineer](https://measuredagents.com/professions/software-engineer): Code review, security review and frontend decisions encoded as agent skills and plugins. ## Packs - [agent-sdk-dev (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-agent-sdk-dev): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): helps build agents with the Claude Agent SDK. - [claude-md-management (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-claude-md-management): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): maintains CLAUDE.md project instruction files. - [code-modernization (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-code-modernization): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): helps migrate code to current language and library versions. - [code-review (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-code-review): plugin, Anthropic, listed. First-party Claude Code plugin from the official marketplace that reviews a diff or PR for correctness bugs at a chosen effort level. - [code-simplifier (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-code-simplifier): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): simplifies and cleans up changed code without altering behaviour. - [commit-commands (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-commit-commands): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): commands for writing commits and preparing pushes. - [feature-dev (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-feature-dev): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): guided feature development from requirements to implementation. - [gopls-lsp (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-gopls-lsp): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): Go (gopls) language-server integration. - [hookify (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-hookify): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): creates Claude Code hooks from described automation rules. - [mcp-server-dev (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-mcp-server-dev): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): scaffolds and develops MCP servers. - [plugin-dev (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-plugin-dev): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): scaffolds and develops Claude Code plugins. - [pr-review-toolkit (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-pr-review-toolkit): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): a toolkit of pull-request review commands and agents. - [pyright-lsp (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-pyright-lsp): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): Python (Pyright) language-server integration for code navigation and diagnostics. - [rust-analyzer-lsp (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-rust-analyzer-lsp): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): Rust (rust-analyzer) language-server integration. - [security-guidance (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-security-guidance): plugin, Anthropic, listed. First-party Claude Code plugin that adds security guidance while coding; part of the official plugin marketplace. - [brand-guidelines (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-brand-guidelines): skill, Anthropic, listed. Open-source Agent Skill (Apache-2.0) from Anthropic's skills repository that applies a brand's visual and tone guidelines to generated material. - [canvas-design (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-canvas-design): skill, Anthropic, listed. Open-source Agent Skill (Apache-2.0) from Anthropic's skills repository for designing visual canvases such as posters and one-page layouts. - [claude-api (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-claude-api): skill, Anthropic, listed. Open-source Agent Skill (Apache-2.0) from Anthropic's skills repository: reference for building on the Claude API and SDKs (models, tool use, streaming, caching). - [doc-coauthoring (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-doc-coauthoring): skill, Anthropic, listed. Open-source Agent Skill (Apache-2.0) from Anthropic's skills repository for co-authoring documents with a person, section by section. - [docx (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-docx): skill, Anthropic, listed. Agent Skill from Anthropic's public skills repository for creating, reading and editing Word (.docx) documents, including tracked changes and comments. Source-available, not open source. - [frontend-design (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-frontend-design): skill, Anthropic, listed. Open-source Agent Skill (Apache-2.0) from Anthropic's skills repository with design guidance for building polished front-end interfaces. - [internal-comms (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-internal-comms): skill, Anthropic, listed. Open-source Agent Skill (Apache-2.0) from Anthropic's skills repository for drafting internal communications such as announcements, updates and memos. - [mcp-builder (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-mcp-builder): skill, Anthropic, listed. Open-source Agent Skill (Apache-2.0) from Anthropic's skills repository that guides an agent through building an MCP server with tests and documentation. - [pdf (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-pdf): skill, Anthropic, listed. Agent Skill from Anthropic's public skills repository for extracting, merging, splitting, filling and creating PDF files, including OCR of scanned pages. Source-available, not open source. - [pptx (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-pptx): skill, Anthropic, listed. Agent Skill from Anthropic's public skills repository for creating and editing PowerPoint (.pptx) decks, templates, notes and comments. Source-available, not open source. - [skill-creator (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-skill-creator): skill, Anthropic, listed. Open-source Agent Skill (Apache-2.0) from Anthropic's skills repository for creating, improving and evaluating other Agent Skills. - [theme-factory (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-theme-factory): skill, Anthropic, listed. Open-source Agent Skill (Apache-2.0) from Anthropic's skills repository for generating consistent visual themes (colours, type) for generated interfaces and documents. - [web-artifacts-builder (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-web-artifacts-builder): skill, Anthropic, listed. Open-source Agent Skill (Apache-2.0) from Anthropic's skills repository for building self-contained web artifacts (HTML, React) with a consistent structure. - [webapp-testing (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-webapp-testing): skill, Anthropic, listed. Open-source Agent Skill (Apache-2.0) from Anthropic's skills repository for driving and testing a web application in a browser from an agent session. - [xlsx (Anthropic Agent Skills)](https://measuredagents.com/packs/anthropic-skills-xlsx): skill, Anthropic, listed. Agent Skill from Anthropic's public skills repository for reading, editing and building spreadsheets (.xlsx, .csv) with formulas and formatting. Source-available, not open source. - [typescript-lsp (Claude Code official plugin)](https://measuredagents.com/packs/anthropic-typescript-lsp): plugin, Anthropic, listed. First-party Claude Code plugin from the official plugin marketplace (anthropics/claude-plugins-official): TypeScript language-server integration for code navigation and diagnostics. - [Google Maps Scraper (Apify Actor)](https://measuredagents.com/packs/apify-google-maps-scraper): agent, Apify (compass), listed. Apify Store actor that extracts public business listings from Google Maps; usable from agents through the Apify MCP server. Usage-based pricing on the Apify platform. - [Cloudflare MCP servers (official)](https://measuredagents.com/packs/cloudflare-mcp-servers): mcp-server, Cloudflare, listed. Cloudflare's product-specific MCP servers (Apache-2.0) for Workers, observability, DNS and other Cloudflare products, usable from any MCP client with a Cloudflare account. - [Exa MCP Server (official)](https://measuredagents.com/packs/exa-mcp-server): mcp-server, Exa, listed. Official Exa MCP server (MIT) for neural web search and crawling from an agent; usage-based pricing on the Exa API. - [Firecrawl MCP Server (official)](https://measuredagents.com/packs/firecrawl-mcp-server): mcp-server, Firecrawl, listed. Official Firecrawl MCP server (MIT) giving agents web search, scraping and crawling tools; usage-based pricing on the Firecrawl platform. - [GapRoll Pay Transparency (MCP)](https://measuredagents.com/packs/gaproll-pay-transparency-mcp): mcp-server, GapRoll, listed. Public, authless MCP server (Streamable HTTP) that tells a Polish employer which EU pay-transparency duties (Directive 2023/970) apply at its headcount, when the first pay-gap report is due, its risk score and the next fix. No employee data. - [GitHub MCP Server (official)](https://measuredagents.com/packs/github-mcp-server): mcp-server, GitHub, listed. GitHub's official MCP server (MIT) giving agents tools over repositories, issues, pull requests and actions through the GitHub API. - [HeadhuntOS screening skill (synthetic demo)](https://measuredagents.com/packs/headhuntos-screening-skill): skill, Headframe, submitted, tier reference. Demo skill pack built with the expert-knowledge engine on synthetic cases only. Encodes a senior recruiter's confirmed screening rules; every verdict stays a human decision (HITL) and every outbound draft carries the AI Act Art. 50 disclosure. - [Everything (MCP reference server)](https://measuredagents.com/packs/mcp-reference-everything): mcp-server, Model Context Protocol project, listed. Reference and test MCP server maintained in the official modelcontextprotocol/servers repository that exercises prompts, resources and tools; useful for testing MCP clients. - [Fetch (MCP reference server)](https://measuredagents.com/packs/mcp-reference-fetch): mcp-server, Model Context Protocol project, listed. Reference MCP server maintained in the official modelcontextprotocol/servers repository: fetches web content and converts it for the model. - [Filesystem (MCP reference server)](https://measuredagents.com/packs/mcp-reference-filesystem): mcp-server, Model Context Protocol project, listed. Reference MCP server maintained in the official modelcontextprotocol/servers repository: file operations with configurable access controls. - [Git (MCP reference server)](https://measuredagents.com/packs/mcp-reference-git): mcp-server, Model Context Protocol project, listed. Reference MCP server maintained in the official modelcontextprotocol/servers repository: tools to read, search and manipulate Git repositories. - [Memory (MCP reference server)](https://measuredagents.com/packs/mcp-reference-memory): mcp-server, Model Context Protocol project, listed. Reference MCP server maintained in the official modelcontextprotocol/servers repository: knowledge-graph based persistent memory for an agent. - [Sequential Thinking (MCP reference server)](https://measuredagents.com/packs/mcp-reference-sequential-thinking): mcp-server, Model Context Protocol project, listed. Reference MCP server maintained in the official modelcontextprotocol/servers repository: structured, revisable problem-solving through thought sequences. - [Time (MCP reference server)](https://measuredagents.com/packs/mcp-reference-time): mcp-server, Model Context Protocol project, listed. Reference MCP server maintained in the official modelcontextprotocol/servers repository: current time and timezone conversion tools. - [Playwright MCP (Microsoft)](https://measuredagents.com/packs/microsoft-playwright-mcp): mcp-server, Microsoft, listed. Official Playwright MCP server (Apache-2.0) that lets an agent drive a real browser through structured accessibility snapshots for testing and automation. - [Notion MCP Server (official)](https://measuredagents.com/packs/notion-mcp-server): mcp-server, Notion, listed. Official Notion MCP server (MIT) giving agents read and write access to Notion pages and databases through the Notion API. - [Supabase MCP Server (official)](https://measuredagents.com/packs/supabase-mcp): mcp-server, Supabase, listed. Official Supabase MCP server (Apache-2.0) connecting AI assistants to Supabase projects: schema, SQL, migrations and project management. - [ToTheCent LLM Spend (MCP)](https://measuredagents.com/packs/tothecent-llm-spend-mcp): mcp-server, ToTheCent, submitted. Read-only MCP connector (OAuth) that shows where a workspace's LLM API money went by provider, model and feature, how much ties out to the invoice, and the exact config change for each fix. Aggregates only. Pre-launch: listed as submitted until the API is live. - [Context7 (Upstash)](https://measuredagents.com/packs/upstash-context7-mcp): mcp-server, Upstash, listed. MCP server (MIT) that serves up-to-date, version-specific library documentation to coding agents so generated code matches current APIs. Hosted service with free and paid tiers. ## Method - [How verification works](https://measuredagents.com/verified) - [Submit a pack](https://measuredagents.com/submit)