Tons of Skills — Claude Code Plugins Marketplace

Built for Claude Code. Every plugin and skill in this catalog targets Anthropic's official CLI.

471 plugins, 3,179 skills, 347 agents, 30 community contributors — validated and ready to install.

Why this repo

• One canonical catalog — every plugin in marketplace.extended.json is the same marketplace.json the Claude Code CLI reads. No registries to reconcile, no manual sync step.
• Spec-correct or it doesn't ship — every PR runs the Intent Solutions validator against the AgentSkills.io open standard plus Claude Code's skill and plugin references. C-grade rejects merge.
• 8-field marketplace frontmatter is enforced, not aspirational — name / description / allowed-tools / version / author / license / compatibility / tags. The 100-point rubric is public.
• Forge-generated and hand-authored, both first-class — /skill-creator --forge <api-name> builds production-grade plugins from any REST API with an audit trail; hand-authored plugins use the same templates and validators.
• Production-tested patterns — the Learning Lab, 11 production playbooks, and a public wiki cover the failure modes that show up at scale (rate limits, MCP reliability, multi-agent cost caps, incident debugging).

pnpm add -g @intentsolutionsio/ccpi    # Install the CLI
ccpi install devops-automation-pack     # Install any plugin

Or use Claude's built-in command:

/plugin marketplace add jeremylongshore/claude-code-plugins

Browse the marketplace | Explore plugins | Download bundles

Killer Skill of the Week — no-ai-slop by Peter Yang

Strip AI slop from any draft — named-pattern edits that keep the writer's real voice

no-ai-slop does two jobs and refuses to fake a third. In Edit mode it makes the minimum effective edit — cutting throat-clearing, weak verbs, and abstract nouns while deliberately preserving the writer's cadence, bluntness, humor, and honest admissions, so a rough draft still sounds like the same person afterward. In Detect mode it names each AI-slop pattern it finds, quotes the offending line, and gives the fix in a few words — and pointedly does NOT score the draft or guess whether an AI wrote it. That restraint is the whole point: AI detectors guess; named patterns are evidence the reader can check. MIT-licensed, single focused skill, actively maintained by Peter Yang.

"AI detectors guess. Named patterns are evidence the user can check." — Peter Yang

Grade: A | Week of July 22, 2026 (W30) | View on GitHub

Previous picks: tonone, mnemos, databricks-pack, kobiton-automate, skyvern, code-cleanup, web-analytics, token-optimizer, executive-assistant-skills, skill-creator, cursor-pack, crypto-portfolio-tracker. See all at tonsofskills.com.

Quick Start

Option 1: CLI (Recommended)

pnpm add -g @intentsolutionsio/ccpi
ccpi search devops              # Find plugins by keyword
ccpi install devops-automation-pack
ccpi list --installed           # See what's installed
ccpi update                     # Pull latest versions

Option 2: Claude Built-in Commands

/plugin marketplace add jeremylongshore/claude-code-plugins
/plugin install devops-automation-pack@claude-code-plugins-plus

Already using an older install? Run /plugin marketplace remove claude-code-plugins and re-add with the command above to switch to the new slug.

Browse the catalog: Visit tonsofskills.com or explore plugins/

📦 Live npm Downloads

Across 454 published packages in the claude-code-plugins namespace. Updated daily by GitHub Actions.

_{"Established" excludes packages first published within the last 30 days, so a bulk-publish event doesn't dominate the headline.}

Top 10 by last 30 days:

_{Last refreshed 2026-07-29T01:26:41.589Z.}

Browse Plugins by Category

Jump to any of the 19 categories below. Plugin counts are catalog totals — auto-generated from marketplace.extended.json.

AI & Machine Learning

🤖 36 plugins · category slug: ai-ml

_{⬆ Back to category index}

AI Agents & Agency

🎭 10 plugins · category slug: ai-agency

_{⬆ Back to category index}

API Development

🔌 26 plugins · category slug: api-development

_{⬆ Back to category index}

Business Tools

💼 21 plugins · category slug: business-tools

_{⬆ Back to category index}

Community

👥 25 plugins · category slug: community

_{⬆ Back to category index}

Crypto & Web3

₿ 27 plugins · category slug: crypto

_{⬆ Back to category index}

Database

💾 26 plugins · category slug: database

_{⬆ Back to category index}

Design

🎨 8 plugins · category slug: design

_{⬆ Back to category index}

DevOps & Infrastructure

🔧 36 plugins · category slug: devops

_{⬆ Back to category index}

Examples & Templates

📚 5 plugins · category slug: examples

_{⬆ Back to category index}

MCP Servers

🧩 16 plugins · category slug: mcp

_{⬆ Back to category index}

Packages

📦 5 plugins · category slug: packages

_{⬆ Back to category index}

Performance

⚡ 25 plugins · category slug: performance

_{⬆ Back to category index}

Productivity

✅ 34 plugins · category slug: productivity

_{⬆ Back to category index}

SaaS Skill Packs

🎁 106 plugins · category slug: saas-packs

_{⬆ Back to category index}

Security

🔐 27 plugins · category slug: security

_{⬆ Back to category index}

Skill Enhancers

✨ 9 plugins · category slug: skill-enhancers

_{⬆ Back to category index}

Testing

🧪 28 plugins · category slug: testing

_{⬆ Back to category index}

Analytics

📁 1 plugins · category slug: analytics

_{⬆ Back to category index}

How Agent Skills Work

Agent Skills are instruction files (SKILL.md) that teach Claude Code when and how to perform specific tasks. Unlike commands that require explicit /slash triggers, skills activate automatically when Claude detects relevant conversation context.

The Activation Flow

1. INSTALL     /plugin install ansible-playbook-creator@claude-code-plugins-plus
2. STARTUP     Claude reads SKILL.md frontmatter → learns trigger phrases
3. ACTIVATE    You say "create an ansible playbook for Apache"
4. EXECUTE     Claude matches trigger → reads full skill → follows instructions

What a Skill Looks Like

---
name: ansible-playbook-creator
description: |
  Generate production-ready Ansible playbooks. Use when automating server
  configuration or deployments. Trigger with "ansible playbook" or
  "create playbook for [task]".
allowed-tools: Read, Write, Bash(ansible:*), Glob
version: 2.0.0
author: Jeremy Longshore <jeremy@intentsolutions.io>
license: MIT
---

# Ansible Playbook Creator

## Overview
Generates idempotent Ansible playbooks following infrastructure-as-code best practices.

## Instructions
1. Gather target host details and desired state
2. Select appropriate Ansible modules
3. Generate playbook with proper variable templating
4. Validate syntax with `ansible-lint`

## Output
- Complete playbook YAML ready for `ansible-playbook` execution

The Numbers

Plugin Types

AI Instruction Plugins (309 plugins)

Markdown files that guide Claude's behavior through structured instructions, skills, commands, and agents. No external code — everything runs through Claude's built-in capabilities.

MCP Server Plugins (10 plugins)

TypeScript applications that run as separate Node.js processes. Claude communicates with them through the Model Context Protocol.

SaaS Skill Packs (106 plugins across 22 pack collections)

Pre-built skill collections for specific platforms — Deepgram, LangChain, Linear, Gamma, and others. Each pack includes install/auth, core workflows, debugging, deployment, and advanced pattern skills.

Building Your Own

Templates

All templates live in templates/.

Step by Step

1. Copy a template: cp -r templates/command-plugin my-plugin
2. Edit .claude-plugin/plugin.json with your metadata
3. Add your skill to skills/my-skill/SKILL.md
4. Validate: ccpi validate ./my-plugin
5. Submit a pull request

Skill Frontmatter Reference

---
# Recommended (all fields optional per Anthropic spec)
name: my-skill-name # kebab-case, matches folder name
description: | # Include "Use when..." and "Trigger with..."
  Describe what this skill does. Use when building X.
  Trigger with "build X" or "create X workflow".
allowed-tools: Read, Write, Bash(npm:*) # Comma-separated, scoped Bash recommended
version: 1.0.0 # Semver
author: Your Name <you@example.com>
license: MIT

# Optional
model: sonnet # Model override (sonnet, haiku, opus)
context: fork # Run in subagent
agent: Explore # Subagent type
user-invocable: false # Hide from / menu
argument-hint: '<file-path>' # Autocomplete hint
hooks: {} # Lifecycle hooks
compatibility: 'Node.js >= 18' # Environment requirements
compatible-with: claude-code, cursor # Platform compatibility
tags: [devops, ci] # Discovery tags
---

Path variable: Use ${CLAUDE_SKILL_DIR} to reference files relative to the skill directory.

Learning Lab

Production agent workflow patterns with empirical verification — guides, diagrams, and working examples.

Start Here (5 min) | Architecture Map | System Summary

Contributors

Community contributors make this marketplace better. Newest first.

• @mjaskolski (Michal Jaskolski) — Added 25 externally-synced agent skills from wondelai/skills covering product strategy, UX design, marketing/CRO, sales/influence, and growth frameworks. (#303)
• @clowreed (B12.io) — Created b12-claude-plugin, an official B12.io plugin with a website-generator skill that takes users from idea to production-ready website draft in one conversation. (#307)
• @duskfallcrew (Duskfall Crew) — Reported PHP webshell payloads in penetration-tester plugin README that triggered AV false positives. Drove a complete v2.0.0 rebuild with real Python security scanners. (#300)
• @rowanbrooks100 (Rowan Brooks) — Created brand-strategy-framework, a 7-part brand strategy methodology used by top agencies with Fortune 500 clients. (#292)
• @RichardHightower (Rick Hightower) — Creator of SkillzWave (44,000+ agentic skills). His quality reviews exposed validation gaps and drove 4,300+ lines of fixes plus new validator checks. Author of the Claude Code Skills Deep Dive series. (#293, #294, #295)
• @TomLucidor (Tom) — His question about paid API requirements sparked the "Make All Plugins Free" initiative (v4.1.0) and drove 2,400+ lines of constraint documentation across 6 plugins. (#148)
• @alexfazio (Alex Fazio) — Production agent workflow patterns and validation techniques that inspired the Learning Lab system (v4.0.0).
• @lukeslp (Lucas Steuber) — Created geepers-agents with 51 specialized agents for development, deployment, quality audits, research, and game development. (#159)
• @BayramAnnakov (Bayram Annakov) — Created claude-reflect, a self-learning system that captures corrections and syncs them to CLAUDE.md. (#241)
• @jleonelion (James Leone) — Fixed bash variable scoping bug in Learning Lab scripts and improved markdown formatting. (#239)
• @CharlesWiltgen (Charles Wiltgen) — Created Axiom, iOS development plugin with 13 production-ready skills for Swift/Xcode. (#121)
• @aledlie (Alyshia Ledlie) — Fixed 7 critical JSON syntax errors and added production CI/CD patterns. (#117)
• @JackReis (Jack Reis) — Contributed neurodivergent-visual-org plugin with ADHD-friendly Mermaid diagrams. (#106)
• @terrylica (Terry Li) — Built prettier-markdown-hook with zero-config markdown formatting. (#101)
• @beepsoft — Quality feedback on skill implementations that drove ecosystem-wide improvements. (#134)
• @clickmediapropy — Reported mobile horizontal scrolling bug. (#120)

Want to contribute? See CONTRIBUTING.md or reach out to jeremy@intentsolutions.io

Resources

Built on the Anthropic stack

This catalog targets Claude Code as its only first-class harness. Every reference page in the SKILL.md spec, plugin structure, MCP integration, hooks, and subagents work in this repo is grounded in the deep references below — not the top-level docs.

Claude Code documentation

• Documentation hub — landing page for every Claude Code surface
• Skills reference — frontmatter spec, dynamic-context-injection model, control-who-invokes mechanism, subagent execution semantics
• Plugins reference — plugin.json schema, the four component types, install paths
• Plugin marketplaces spec — the marketplace.json schema this repo publishes
• Subagents reference — agent.md frontmatter, disallowedTools denylist, effort / maxTurns controls
• Hooks reference — 30+ lifecycle events, PreToolUse blocking, matcher patterns
• MCP integration — stdio / HTTP / SSE / WebSocket transports, env-var handling, server lifecycle
• Settings reference — ~/.claude/settings.json, permission modes, attribution config

Anthropic SDKs and code

• Claude Code CLI source — the official CLI repo
• Anthropic cookbook — production patterns, tool-use examples, RAG recipes
• Anthropic Python SDK — pip install anthropic, async + streaming + tool-use APIs

Open standards

• AgentSkills.io specification — the open SKILL.md standard Claude Code follows; this repo's enterprise rubric sits on top of it

Project Wiki

The GitHub wiki hosts deeper reference content than this README — 50+ pages covering installation, the full SKILL.md spec, plugin structure, validation, 11 production playbooks, and the Learning Lab walkthroughs.

Getting started — zero-to-first-plugin in under 30 minutes

• Installation — CLI install + marketplace setup
• Your First Plugin — build, validate, publish
• Your First Skill — author a SKILL.md from scratch

Reference — the spec, frontmatter, and validation rules

• SKILL.md Specification — the canonical Intent Solutions skill standard
• Frontmatter Reference — every YAML field explained
• Validation and Grading — the 100-point rubric + validator commands
• Plugin Structure — directory layout + plugin.json

Playbooks — production patterns for operating Claude Code at scale

• Playbook Index — all 11 production playbooks
• Multi-Agent Rate Limits — token-bucket + backpressure
• Incident Debugging — SEV protocols + RCA

Labs — interactive walkthroughs

• Learning Lab Index — Skills / Plugins / Orchestration tracks

Technical Deep Dives

• Claude Skills Deep Dive — Lee-Han Chung's definitive technical analysis
• Skills Deep Dive Series — Rick Hightower's architecture-focused analysis
• SkillzWave — Universal skill installer supporting 14+ coding agents

Community

• Claude Developers Discord — 40,000+ members
• GitHub Discussions — Ideas, Q&A, show and tell
• Issue Tracker — Bugs and feature requests
• Awesome Claude Code — Curated resource list

Ecosystem

• AgentSkills.io — Open standard for skill compatibility fields
• Numman Ali's Skills — Externally-synced community skills
• Prism Scanner — Open-source security scanner for agent skills, plugins, and MCP servers (39+ rules, AST taint tracking, A-F grading)
• CCHub - A desktop control panel for the Claude Code / Codex / Gemini CLI ecosystem. Manage MCP servers, config profiles, agent skills, CLAUDE.md, hooks, and workflow templates from a single Tauri app (Windows / macOS / Linux).

FAQ

What is this? A Claude Code plugin marketplace: 471 plugins, 3,179 skills, 347 agents, all validated against the AgentSkills.io open standard and the Claude Code skills / plugins references.

How do I install a plugin? Use the CLI (ccpi install <name>) or Claude Code's built-in /plugin marketplace add jeremylongshore/claude-code-plugins followed by /plugin install <name>@claude-code-plugins-plus. The Quick Start covers both paths.

Plugin vs skill — what's the difference? A plugin is the distribution unit (folder with plugin.json + components); a skill is one component type inside a plugin (a SKILL.md file). One plugin can ship many skills, commands, agents, hooks, and MCP servers. The Plugin Structure wiki page is the deeper explanation.

Where do I browse the catalog? tonsofskills.com is the search-and-browse surface. The plugins/ directory is the source of truth on GitHub.

Where do I get support? Open an issue for bugs, a discussion for ideas, or email jeremy@intentsolutions.io. For the underlying CLI itself, see Anthropic's Claude Code docs first.

Troubleshooting

Common install + author paths:

• Plugin install fails or doesn't activate — see the Troubleshooting wiki page for the common "missing required field" / "frontmatter wrong shape" / "marketplace not reachable" cases.
• Marketplace add fails — verify slug with /plugin marketplace list; the public slug is jeremylongshore/claude-code-plugins (GitHub 301-redirects to the canonical -plus-skills repo).
• MCP server doesn't connect — the MCP-Server-Plugins wiki page covers transport selection and the most common transport-mismatch errors. Anthropic's MCP integration reference is the upstream source.
• Validator says my skill is C-grade — see Validation and Grading for the 100-point breakdown and the public /grading rubric page for worked examples.
• Compatibility field deprecation — compatible-with was deprecated in schema 3.4.0. Migrate with python3 scripts/batch-remediate.py --migrate-compatible-with.

Star history

Important Notes

Not on GitHub Marketplace. Claude Code plugins use a separate ecosystem with JSON-based catalogs hosted in Git repositories. This repository is a Claude Code plugin marketplace.

Free and open-source. All plugins are MIT-licensed. No monetization mechanism exists for Claude Code plugins. See Monetization Alternatives for external revenue strategies.

Production status. Claude Code plugins launched in public beta (October 2025) and are now a stable part of the Claude Code workflow. This marketplace tracks all specification changes.

License

MIT License — See LICENSE for details.

Version: 4.33.0 | Last Updated: 2026-05-25 | Skills: 2,754 | Plugins: 431