Cody skill library

Agent skills, carefully picked

A researched collection of useful agent skills for frontend work, marketing, workflows, MCP, RAG, databases, documents, and legal writing — with source links, audit snapshots, and honest caveats.

27

hand-picked skills

18

first-party picks

3.2M

top snapshot installs

Install counts and audits are point-in-time signals, not a guarantee. Read every SKILL.md, inspect scripts and network behavior, and start with the smallest set that fits your work. Snapshot checked September 1, 2026.

27 skills

Agent WorkflowsFirst-party

vercel-labs/agent-browser

agent-browser

Audit warning

Adds persistent, command-driven browser automation for navigation, extraction, form work, and web QA.

770K installs42K
Read the review
AI, MCP & RAGFirst-party

microsoft/azure-skills

microsoft-foundry

Audit warning

First-party operational guidance for building, evaluating, deploying, and managing Microsoft Foundry agents and models.

566K installs1K
Read the review
Data & BackendFirst-party

supabase/agent-skills

supabase-postgres-best-practices

A prioritized Postgres playbook for schema design, security, query performance, and operations.

382K installs3K
Read the review
Agent Workflows

obra/superpowers

systematic-debugging

Keeps an agent in a root-cause investigation loop before it starts patching symptoms.

244K installs280K
Read the review
Marketing & Growth

coreyhaines31/marketingskills

seo-audit

Audit warning

Turns a broad SEO review into a prioritized diagnosis across technical, on-page, and content signals.

199K installs46K
Read the review
Marketing & Growth

coreyhaines31/marketingskills

copywriting

A conversion-copy workflow for pages, headlines, value propositions, and calls to action.

191K installs46K
Read the review
AI, MCP & RAGFirst-party

anthropics/skills

mcp-builder

Audit warning

A design and implementation guide for MCP servers that expose external services to language models.

110K installs173K
Read the review
AI, MCP & RAGFirst-party

google/skills

agent-platform-rag-engine-management

Audit warning

Manages Google Agent Platform RAG corpora, files, retrieval, and grounded generation through the Gen AI SDK.

5K installs19K
Read the review
Agent Workflows

mattpocock/skills

tdd

Guides vertical, behavior-focused red-green-refactor cycles instead of writing a large test suite up front.

817K installs244K
Read the review
Frontend & DesignFirst-party

vercel-labs/agent-skills

web-design-guidelines

Audit warning

Reviews interface code against a maintained set of usability, interaction, and accessibility checks.

599K installs31K
Read the review
Agent Workflows

mattpocock/skills

diagnosing-bugs

A diagnosis loop for stubborn failures and performance regressions where the cause is not yet known.

521K installs244K
Read the review
Marketing & Growth

coreyhaines31/marketingskills

marketing-psychology

Applies behavioral science and decision models to messaging, pricing, and conversion choices.

137K installs46K
Read the review
Marketing & Growth

coreyhaines31/marketingskills

content-strategy

Audit warning

Builds a content plan around audience demand, business goals, and a balanced portfolio of ideas.

133K installs46K
Read the review
Marketing & Growth

coreyhaines31/marketingskills

programmatic-seo

Audit warning

Plans scalable search pages around repeatable query patterns, useful data, and sound indexation controls.

126K installs46K
Read the review
Marketing & Growth

coreyhaines31/marketingskills

ai-seo

Audit warning

Evaluates whether content is easy for answer engines and AI assistants to extract, trust, and cite.

117K installs46K
Read the review
AI, MCP & RAGFirst-party

anthropics/skills

claude-api

Audit warning

A current reference skill for Claude models, API patterns, tools, caching, streaming, MCP, and migration.

62K installs173K
Read the review

How the list was made

Popularity was a filter. Usefulness was the test.

A deliberately small set of useful, inspectable agent skills selected from current skills.sh usage, first-party repositories, GitHub activity, independent roundups, and practitioner discussion.

26 of 27 have 5K+ installs
1

Prefer focused skills that encode a repeatable workflow or a maintained domain playbook.

2

Give first-party repositories extra weight, then use installs, repository activity, and community discussion as supporting signals.

3

Show audit warnings and low-adoption exceptions instead of treating popularity as a security guarantee.

4

Keep the collection small enough that users can install only what matches their work.

Skills shape the workflow. Prompts shape the brief.

Browse the rebuilt prompt library for detailed, model-aware templates designed for GPT-5.6 and Claude Fable 5.1.

Explore prompt templates