Skills for Claude Code

246,491 that install into Claude Code. Same mod, same page, whichever agent you run: a URL per tool would split one page into five that compete.

validate

16129

aiocean/claude-plugins

Skill Claude Code needs its repo

Run the marketplace validation script to check plugin integrity. Use when finishing plugin work, after adding or modifying plugins, or before committing plugin changes.

not rated 4 12d ago A 30 tokens original MIT

hello-world

16130

VictorTomaili/skill-cli

Skill Claude CodeCodex

Minimal example skill — a copy-paste template for your own skills.

not rated 4 9d ago A 17 tokens original MIT

breachproof

16131

Mikaru0Mystic/breachproof

Skill Claude CodeCodex

Autonomous security audit and hardening that scans, exploits, fixes, and re-scans a codebase to zero findings, mapped to SOC 2.

not rated 4 2mo ago A 35 tokens original Apache-2.0

quartermaster

16132

johntimothybailey/skill-harbor

Skill Claude CodeCodex

Draft Skill Harbor release notes and changesets from the current git diff using the nautical Quartermaster voice. Use when asked for a changeset, hero title, Captain's Briefing, or release notes for this repo.

not rated 4 4mo ago A 46 tokens original MIT

benchmark-runner

16133

sublimotion/agent-aiops-on-aws

Skill Claude Code

Plan, execute, and analyze LLM serving benchmarks across vLLM and SGLang configurations. Use when user says "run benchmarks", "benchmark config", "QPS sweep", "compare serving configs", "custbench", "benchmark analysis", or "generate benchmark report". Do NOT use for writing Terraform (use terraform-automation)…

not rated 4 2mo ago A 94 tokens

mcp-server-dev

16134

euxx/claude-skills-for-copilot

Skill Claude Code

Use when the user asks to build an MCP server, create an MCP integration, wrap an API for AI agents, or expose tools via the Model Context Protocol. Guides through deployment model selection (remote HTTP, MCPB, local stdio), tool-design patterns, and framework choice before scaffolding code.

not rated 4 3mo ago A 65 tokens original MIT

code-ultragraph-review

16135

will-pagane/claude-superdev-harness

Skill Claude CodeCodex

Use when the user asks for an extensive, maximum-quality, whole-codebase review or audit and wants a consolidated findings report (read-only, default). Add --autopilot to run a fully autonomous performance pipeline: read Supabase signals, deep-dive via dynamic workflows, refine fixes with a headless Codex pass, apply…

not rated 4 8d ago A 0 tokens original MIT

obsidian-canvas

16136

GradScalerTeam/claude_cli

Skill Claude CodeCodex

Reference skill for creating and editing Obsidian Canvas (.canvas) JSON files — the JSON 1.0 spec, node/edge shapes, positioning rules, color conventions, and Post-Write Verification Protocol. Use this skill whenever you need to present something visually on a canvas: mind maps, brainstorm boards, project planning…

not rated 4 27d ago A 142 tokens

flash-attention

16137

jstzwj/ai-infra-plugins

Skill Claude CodeCodex

The following reference files contain in-depth documentation for each component.

not rated 4 4mo ago A 0 tokens

project-context

16138

aida-core/aida-marketplace

Skill Claude Code

Auto-triggered skill for project-specific facts, structure, and conventions.

not rated 4 3mo ago A 16 tokens original MPL-2.0

onboard

16140

cpliakas/claude-code-engineering-leaders

Skill Claude Code

Use when setting up the engineering-leaders plugin for the first time on a project, or when re-running onboarding to update shared project context. Gathers shared project context for all agents (one question at a time) and discovers specialist plugins for the Tech Lead to consult. Run this before per-agent onboarding…

not rated 4 20d ago A 71 tokens original MIT archived

pydantic

16141

arnabdeypolimi/claude_code_setup

Skill Claude Code

Python data validation using type hints and runtime type checking with Pydantic v2's Rust-powered core for high-performance validation in FastAPI, Django, and configuration management. Use when working with API request/response validation, settings management, ORM model validation, data parsing and serialization, or…

not rated 4 13d ago A 66 tokens original MIT

grading-claude-agents-md

16142

SpillwaveSolutions/grading-claude-agents-md-agentic-skill

Skill Claude CodeCodex

Grades and improves CLAUDE.md (Claude Code) and AGENTS.md (Codex/OpenCode) configuration files. Use when asked to grade, score, evaluate, audit, review, improve, fix, optimize, or refactor agent config files. Triggers on 'grade my CLAUDE.md', 'score my AGENTS.md', 'is my CLAUDE.md too big', 'improve my agent config'…

not rated 4 8mo ago A 141 tokens

brainstorming

16143

shousper/claude-kit

Skill Claude CodeCodex

Coordinates collaborative design sessions that explore requirements, analyze codebase context, and produce an approved design document with trade-offs. Use when building a new feature, adding functionality, creating components, modifying behavior, starting a project, or planning any creative work. DO NOT TRIGGER when…

not rated 4 14d ago A 70 tokens original MIT

new-plugin

16144

langburd/agent-skills

Skill Claude Code

Scaffold a new plugin bundle in this marketplace — creates plugin.json, SKILL.md with correct frontmatter, per-plugin README, then runs sync.sh.

not rated 4 1mo ago A 34 tokens

writing-skills

16145

w4ngyu/openclaw-superpowers

Skill Claude CodeCodex

Use when creating new skills, editing existing skills, or verifying skills work before deployment.

not rated 4 5mo ago A 20 tokens

china-equity-ic-rigor

16146

equity-rigor/us-equity-research

Skill Claude CodeCodex

A review framework for Chinese-equity research and investment memos intended for an investment committee, the group that assesses proposed trades. It adds checks for sources, calculations, scenarios and conditions that could change the recommendation.

not rated 4 2mo ago A 206 tokens original MIT

context-budget

16147

cveralyon/axel-setup

Skill Claude CodeCodex

Audits Claude Code context consumption across agents, skills, commands, hooks, MCP servers, and the CLAUDE.md/MEMORY chain. Identifies bloat and redundancy, then produces prioritized token-savings recommendations. Backs the /context-budget command.

not rated 4 2mo ago A 55 tokens original MIT

git-gud-security

16148

kidsmeal/git-gud-security

Skill Claude Code

Audit any repo for security holes — a web/app project, a Claude skill, a Claude Code plugin, an MCP server, or an agent. Catches the glaring stuff (exposed servicerole keys, RLS off, committed .env, secrets in the client bundle, allow read,write: if true) and the subtle stuff (IDOR, SSRF, prompt injection in a…

not rated 4 changed 22d ago A 281 tokens original MIT

wordpress-development

16149

gaupoit/wordpress-development-skill

Skill Claude Code

This skill provides comprehensive WordPress development expertise including self-hosted setup with Docker and Nginx, theme development (block and classic), plugin development with security best practices, performance optimization, and security hardening. Use this skill when setting up WordPress environments…

not rated 4 9mo ago A 101 tokens

garryscount

16150

mrieck/garrys-count

Skill Claude Code

Generate a Garry's Count LOC report showing lines of code written today and this week.

not rated 4 6mo ago A 22 tokens original MIT

alpine-js

16151

mgd34msu/goodvibes-gemini

Skill Claude CodeCodex

Adds reactive and declarative behavior to HTML with minimal JavaScript using Alpine.js directives. Use when adding lightweight interactivity to server-rendered pages, building interactive components without a build step, or when user mentions Alpine.js, x-data, or Tailwind-style reactivity.

not rated 4 8mo ago A 58 tokens

back-from-holiday

16152

DanielRohregger/CopilotLibrary

Skill Claude CodeCodex

Creates an interactive, self-contained HTML recap dashboard after a longer absence (vacation, sabbatical, sick leave). Surfaces missed emails, meetings, Teams messages, files, pending decisions, deadlines, and top priorities — with checkboxes, dark mode, filters, and browser-persisted state. Works fully autonomously…

not rated 4 19d ago A 75 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: