Evals & quality
Evals, verification, observability and measurement.
Superpowers (obra)
Skills framework/methodology: verification-before-completion, writing-plans, executing-plans, systematic-debugging, TDD, subagent-driven development.
Matt Pocock Skills (handoff, research, grill-me)
Popular engineering skills incl. handoff (write a resumable handoff doc), research, grill-me (interrogate a plan), tdd, code-review.
Anthropic Skills (skill-creator, webapp-testing)
Anthropic's public skills repo incl. skill-creator (turn a workflow/correction into a skill) and webapp-testing (Playwright).
Mem0
Memory layer for agents (OSS SDK, CLI, MCP; optional cloud): store and retrieve user/owner facts and preferences.
Humanizer (anti-AI-slop)
Skill that rewrites text to remove common signs of AI-generated writing.
Marketing Skills (Corey Haines)
~50 SKILL.md files: cold-email, prospecting, revops, emails, lead-magnets, launch, directory-submissions, pricing, analytics-tracking, CRO, copywriting, SEO.
Obsidian skills
Agent skills for Obsidian (by its CEO): use the Obsidian CLI and open formats (Markdown, Bases, JSON Canvas).
CCXT
A unified trading API for 100+ crypto exchanges and prediction markets in JavaScript, Python, PHP, C# and Go.
agent-browser (Vercel Labs)
Browser-automation CLI for agents plus its skill (snapshot/click/fill), local or cloud browsers.
Playwright MCP (Microsoft)
Official Playwright MCP server: drive a real browser via accessibility snapshots.
Langfuse
Open-source LLM/agent tracing, evals, prompt management; self-host or cloud.
Task Master (claude-task-master)
AI task-management system (CLI + MCP): parse a PRD into tasks with dependencies, track status, pick next task.
Beads (issue memory for agents)
Git-backed issue tracker CLI (`bd`) designed as long-term task memory for coding agents.
promptfoo
CLI to test prompts, agents and RAG with assertions; red-teaming and vulnerability scanning for LLM apps.
vectorbt
A fast vectorized backtesting engine for testing many trading strategy variants on historical data.
backtesting.py
A small Python framework to backtest trading strategies, with stats and interactive plots.
Firecrawl MCP Server (official)
MCP for scraping, crawling, search and structured extraction (hosted v2 endpoint or local).
Exa MCP Server (official)
Hosted MCP (mcp.exa.ai) for neural web search, crawling and company research.
Notion MCP server (official)
Notion's official MCP server to search, read and edit Notion pages and databases.
prediction-market-analysis
A framework for collecting and analyzing prediction-market data; its README lists research papers that used it.
AI Marketing Skills (Eric Siu / Single Grain)
~35 agency workflows as skills: outbound-engine, lead-dossier, sales-pipeline, revenue-intelligence, growth-engine, SEO ops, content ops.
Google Analytics MCP (official)
Official GA4 MCP server: run reports and realtime queries against GA4 properties.
Google Workspace MCP
An MCP server for Gmail, Google Calendar, Docs, Sheets, Slides, Chat, Forms, Tasks and Drive.
Supabase MCP (official)
Hosted Supabase MCP (mcp.supabase.com) with read_only and project scoping flags: SQL, schema, logs, docs.
Web quality skills (Lighthouse / Core Web Vitals)
Agent skills for auditing and fixing web quality (performance, accessibility, SEO) based on Lighthouse and Core Web Vitals.
Financial Datasets MCP server
An MCP server for the Financial Datasets stock-market API: financial statements, prices and news.
pmxt (unified prediction-market API)
'CCXT for prediction markets': one API for trading and data on Polymarket, Kalshi and other venues.
Stripe AI (official MCP + skills)
Stripe's agent toolkit, hosted MCP (mcp.stripe.com, OAuth) and skills (stripe-best-practices, upgrade-stripe).
Alpaca MCP server (official)
Alpaca's official MCP server: trade stocks, ETFs, crypto and options and pull market data from an agent.
Sentry MCP / toolkit (official)
Sentry's agentic tooling incl. the hosted Sentry MCP (mcp.sentry.dev): read issues, errors, releases.