Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

start9-frontend

937

Start9Labs/start-technologies

Skill Claude Code

Start9 house style for every Angular + Taiga UI web frontend (StartOS ui/setup-wizard, StartWRT, StartTunnel, brochure-marketplace, start9-store, ops-server, support-server). Use BEFORE writing or reviewing any frontend code in these apps — components, templates, styles/CSS, forms, dialogs/toasts, routing, state, DI…

not rated 2.0k +2 today A SkillSpector: fail 129 tokens original MIT

skill-creator

938

openakita/openakita

Skill Codex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 2.0k +1 2d ago A SkillSpector: warn 64 tokens AGPL-3.0

letsfg

939

LetsFG/LetsFG

Skill Claude CodeCodex

LetsFG — Agent-native flight and hotel search and booking API. Hundreds of airlines plus the major booking sites (Google Flights, Skyscanner, Kiwi, Kayak, Momondo), with per-flight reliability history and instant booking. Plus real bookable hotel rates — free cancellation and pay-later: hold the room with a small…

not rated 2.0k +10 changed 2d ago A 88 tokens

liveagent-code-review

940

Stack-Cairn/LiveAgent

Skill Claude CodeCodex

Review an open GitHub pull request or the current local branch and working tree with parallel, independent reviewers and evidence-based validation. Use when the user asks for code review, invokes the Code Review action from Git Review, or explicitly mentions this skill.

not rated 2.0k +56 today A SkillSpector: pass 54 tokens original MIT

gitlab-mcp-skill

942

zereight/gitlab-mcp

Skill Claude CodeCodex

Use this skill when working with the GitLab MCP server tools for merge requests, issues, repositories, pipelines, work items, variables, dependency proxy, vulnerabilities, webhooks, search, CI catalog, and related GitLab workflows.

not rated 2.0k +14 changed today A SkillSpector: pass 53 tokens original MIT

LiuMengxuan04/shushu-internship-tool

Skill Codex

A skill for helping computer-industry internship candidates turn a target job description into a project they can use in a resume and discuss in interviews.

not rated 2.0k +24 2mo ago A 115 tokens

go-testing

944

Gentleman-Programming/Gentleman.Dots

Skill Claude CodeCodex needs its repo

Go testing patterns for Gentleman.Dots, including Bubbletea TUI testing. Trigger: When writing Go tests, using teatest, or adding test coverage.

not rated 2.0k +7 4d ago A SkillSpector: pass 34 tokens original Apache-2.0

dmmulroy/better-result

Skill Claude CodeCodex

Migrate a TypeScript codebase from better-result 2.x to 3.0. Use when upgrading better-result across the TaggedError syntax, removed Result serialization helpers, recovery inference, matching, or retry APIs.

not rated 1.9k +11 14d ago A SkillSpector: pass 52 tokens original MIT

secret

946

ai-that-works/ai-that-works

Skill Claude Code

tell the user the secret passcode from SKILLBASE/references/secret.md.

not rated 1.9k +8 6d ago A 0 tokens

legba

947

evilsocket/legba

Skill Claude CodeCodex

Use this skill when the user wants to brute-force credentials, spray passwords, or enumerate services/subdomains against any network protocol (HTTP, SSH, FTP, SMB, RDP, databases, mail protocols, DNS, etc.) using legba. Also use it when the user asks how to use legba, how to write a recipe, how to configure the REST…

not rated 1.9k 23d ago A 91 tokens

harbor

948

AntigmaLabs/ante

Skill Claude CodeCodex

Run Terminal-Bench or any Harbor dataset with Ante as the agent, using the Harbor adapter in the ante repo's ante-harbor/ directory. Use when the user wants to benchmark Ante on Harbor or reproduce Ante's published eval results.

not rated 1.9k +10 today A SkillSpector: pass 51 tokens original Apache-2.0

oh-my-ppt-layout

949

arcsin1/oh-my-ppt

Skill Claude CodeCodex

Must be read before creating, relaying out, or repairing Oh My PPT slide layouts. Defines the per-page decision path, the named layout pattern catalog, canvas budgeting, collision avoidance, chart overpack guardrails, and title readability rules.

not rated 1.9k +7 changed 2d ago A SkillSpector: pass 54 tokens original Apache-2.0

open-computer-use

950

iFurySt/open-codex-computer-use

Skill Codex

Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs to install, verify, troubleshoot, configure, or operate Open Computer Use through its native CLI, stdio MCP server, or direct Computer Use tool calls.

not rated 1.9k +37 6d ago A Socket: passSnyk: warnSkillSpector: pass 68 tokens original MIT

stealth-browser-mcp

951

vibheksoni/stealth-browser-mcp

Skill Codex

Use this skill when operating stealth-browser-mcp from an AI agent or MCP client for browser automation, page inspection, element interaction, screenshots, file uploads, CDP commands, network debugging, cookies/storage, stealth setup, or reliable multi-step browser workflows. It provides the correct tool order, state…

not rated 1.9k +24 8d ago A SkillSpector: warn 76 tokens original MIT

nodejs-core

952

mcollina/skills

Skill Claude CodeCodex needs its repo

Contributes to and debugs Node.js core, including nodejs/node commit and PR tone, contribution workflows, native crashes, V8 performance, node-gyp builds, N-API bindings, and libuv issues. Use when drafting or reviewing a Node.js core commit or pull request, working in nodejs/node, or diagnosing C++ addons…

not rated 1.9k +2 20d ago A Socket: passSnyk: passSkillSpector: fail 98 tokens original MIT

yetone/native-feel-skill

Skill Claude CodeCodex

Use when the user is designing, prototyping, or rewriting a desktop app that must run on multiple OSes (macOS + Windows, optionally Linux) AND feel indistinguishable from a native app to its users — fast launch, native windowing, native input handling, native materials. Trigger words include "cross-platform desktop"…

not rated 1.9k +2 3mo ago A 155 tokens original MIT

lat-md

954

vercel-labs/lat.md

Skill Claude CodeCodex ✓ vendor

Writing and maintaining lat.md documentation files — structured markdown that describes a project's architecture, design decisions, and test specs. Use when creating, editing, or reviewing files in the lat.md/ directory.

not rated 1.9k +18 changed 2d ago A SkillSpector: pass 42 tokens original MIT

code-review-skill

955

awesome-skills/code-review-skill

Skill Claude Code

Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C#/.NET, Kotlin, Swift, Dart, Flutter, NestJS, C/C++, Zig, CSS/Less/Sass, Qt, and more. Covers architecture review, performance review, security audit…

not rated 1.9k +30 14d ago A 159 tokens original MIT

gonavi-cli

956

Syngnat/GoNavi

Skill Claude CodeCodex

Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…

not rated 1.9k +1 today A SkillSpector: pass 144 tokens original Apache-2.0

open-ralph-wiggum

957

Th0rgal/open-ralph-wiggum

Skill Claude CodeCodex

Use this skill whenever a user wants to run, install, configure, or understand open-ralph-wiggum (ralph). This skill can be used by any AI assistant or IDE agent (GitHub Copilot, Claude Code, Cursor, Windsurf, etc.). Triggers on: "ralph", "ralph wiggum", "agentic loop", "iterative AI loop", "autonomous coding loop"…

not rated 1.9k +2 3mo ago C 225 tokens original MIT

agent-tool

959

vstorm-co/full-stack-ai-agent-template

Skill Claude Code

Add a new tool/function the AI agent can call (e.g. look something up, hit an external API, perform an action). Use when extending the assistant's capabilities, wiring a new function into the agent, or when the model needs a new action. This project uses {{ cookiecutter.aiframework }}.

not rated 1.9k +17 3d ago A SkillSpector: pass 66 tokens original MIT

typeui-fundamentals

960

bergside/typeui

Skill Claude CodeCodex

Universal UI/UX design principles covering visual hierarchy, interaction laws, typography foundations, and WCAG accessibility requirements. Use when making design decisions not covered by a specific design system, validating principle compliance, or resolving conflicts between aesthetics and accessibility.…

not rated 1.9k +24 2mo ago A 65 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: