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.

dependabot-review

2089

ThibautBaissac/rails_ai_agents

Skill Claude Code

Reviews Dependabot gem upgrade PRs for breaking changes, codebase impact, and merge readiness. Use when user pastes a Dependabot PR URL, asks about a gem version bump, or wants to audit open dependency PRs ("which dep PRs are safe to merge", "audit our deps", "check dependabot"). WHEN NOT: Non-Dependabot PRs, npm/yarn…

not rated 672 +1 5mo ago A SkillSpector: warn 89 tokens original MIT

rozenite

2090

callstackincubator/rozenite

Skill Claude CodeCodex

Use Rozenite for Agents to inspect React Native DevTools data and Rozenite plugins on a live app target, either through shell-driven rozenite agent commands or programmatic @rozenite/agent-sdk usage. Trigger this skill for any task that needs live app inspection, debugging, or plugin interaction through Rozenite.

not rated 671 4d ago A SkillSpector: warn 72 tokens original MIT

Decionis Commerce Gate

2092

decionis/agent-safe-pipeline

Skill Claude CodeCodex

Check a price change, stock change, order, refund or return against the merchant's margin, stock and refund policy before acting. Use before any commerce action on Walmart, Shopify, Adobe Commerce or Business Central.

not rated 670 +2 changed 1mo ago A 48 tokens original Apache-2.0

query-memory

2093

wangxijie001/yoji

Skill Claude Code

A memory-search workflow for finding information from earlier conversations. It can search summaries, retrieve original messages, count messages, and look up logged emotional changes.

not rated 668 +2 2mo ago A SkillSpector: pass 94 tokens original MIT

drawio

2094

sparklabx/drawio-ai-kit

Skill Claude CodeCodex

Use when the user asks for any draw.io diagram — cloud architecture (AWS, Azure, GCP, Databricks, multi-cloud, hybrid/DR, landing zone, VPC/network, serverless, data pipeline) or a business process (BPMN, swimlane, workflow with roles). Builds with the drawio-ai layout engine using real stencils, validates, and runs a…

not rated 668 +2 27d ago A 102 tokens original MIT

视频转写

2095

xiaohuailabs/xiaohu-video-translate

Skill Claude CodeCodex

A video transcription and translation tool that turns subtitles or audio into Markdown documents. For translated videos, it transcribes the audio, translates the subtitles, and burns Chinese subtitles into the video.

not rated 667 +4 5mo ago A SkillSpector: warn 120 tokens original MIT

lunwen

2096

Doryoku1223/lunwen-skill

Skill Codex

A Chinese-language writing workflow for producing structured academic theses, graduation projects, technical reports, and course papers. It can use real project code, school templates, sample papers, references, diagrams, screenshots, and Word documents.

not rated 667 +4 7mo ago A 134 tokens original MIT

api-doc-generator

2097

JackyST0/awesome-agent-skills

Skill Claude CodeCodex

Generate API documentation from source code, supporting REST APIs, GraphQL, and various documentation formats.

not rated 667 +2 changed 29d ago A SkillSpector: pass 23 tokens original CC0-1.0

zy-cinematic-realism

2098

popopo-99/zy-cinematic-realism

Skill Codex

Develop supplied scripts, short stories, or synopses into scene understanding, director-facing art concepts, and motivated narrative keyframes; compile scene ideas, visual references, or existing prompts into model-native image prompts when requested. Use for story visual development, cinematic creation, Dream Decode…

not rated 667 +20 changed 4d ago A 136 tokens

tura

2099

Tura-AI/tura

Skill Claude CodeCodex

Work in the Tura agent-runtime repository. Use for Tura architecture, Rust backend, GUI/TUI, prompts, commands, providers, sessions, documentation, tests, packaging, and release work in this directory.

not rated 665 +5 1mo ago A 46 tokens AGPL-3.0

seo-audit

2100

seo-skills/seo-audit-skill

Skill Claude Code

Audit websites for SEO, technical, content, security, JS rendering, and AI readiness using SEOmator CLI. Returns LLM-optimized reports with health scores across 373 rules and 20 categories, and can diff two audits to show what a deploy changed. Use when analyzing websites, debugging SEO issues, checking site health…

not rated 665 +7 changed 23d ago A 80 tokens original MIT

hooks-wizard

2101

loocor/codmate

Skill Claude CodeCodex

Generate CodMate hook drafts from requirements.

not rated 664 7mo ago A 12 tokens original Apache-2.0

myclaw-backup

2102

LeoYeAI/openclaw-backup

Skill Claude CodeCodex

Backup and restore all OpenClaw configuration, agent memory, skills, and workspace data. Part of the MyClaw.ai (https://myclaw.ai) open skills ecosystem — the AI personal assistant platform that gives every user a full server with complete code control. Use when the user wants to create a snapshot of their OpenClaw…

not rated 664 +1 8mo ago B 179 tokens original MIT

electron

2103

Gentleman-Programming/Gentleman-Skills

Skill Claude CodeCodex needs its repo

Electron patterns for building cross-platform desktop applications. Trigger: When building desktop apps, working with Electron main/renderer processes, IPC communication, or native integrations.

not rated 663 +2 7mo ago A 33 tokens original MIT

obsidian-e2e

2104

uphy/obsidian-reminder

Skill Claude Code

An automated end-to-end test workflow for a running Obsidian application, controlled through Chrome DevTools Protocol. Obsidian is a note-taking app, and end-to-end testing checks behavior across the real application rather than only individual functions.

not rated 662 +1 changed 6d ago A SkillSpector: warn 140 tokens original MIT

librechat-docs

2105

LibreChat-AI/librechat.ai

Skill Claude CodeCodex

Use the official LibreChat documentation to install, configure, operate, and troubleshoot LibreChat.

not rated 662 1mo ago A SkillSpector: warn 24 tokens original MIT

browser-use-terminal

2106

browser-use/terminal

Skill Claude CodeCodex

Direct browser control via the Browser Use Terminal CLI. Use when the user wants to automate, scrape, test, or interact with web pages — you drive the browser yourself with Python helpers.

not rated 662 +4 8d ago A 41 tokens original MIT

PKU-YuanGroup/OpenAI4S

Skill Claude CodeCodex

Handles batch effects in bulk RNA-seq via design-matrix inclusion (the correct path for DE), ComBat/ComBat-seq for visualization, SVA for unknown latent factors, RUVSeq for negative-control-gene-anchored unwanted variation, and limma::removeBatchEffect for plotting only. Encodes the Nygaard 2016 cardinal sin against…

not rated 662 +5 yesterday A SkillSpector: pass 187 tokens original MIT

nebula-runtime

2109

Kuddev/nebula

Skill Codex

A skill for controlling a live Nebula terminal workspace from an AI coding agent. It can work with panes, tabs, files, commands, and other Codex or Claude agents.

not rated 661 2mo ago A SkillSpector: pass 144 tokens GPL-3.0

echo-custom-mcp

2110

truffle-ai/dexto

Skill Claude CodeCodex

Use bundled skill files for quick skill bundle checks.

not rated 659 +1 yesterday A 10 tokens

scientific-writing

2111

Boom5426/Nature-Paper-Skills

Skill Claude CodeCodex

Use when writing or revising scientific manuscripts, abstracts, figures, or references for journal submission and you need full-paragraph prose, scientific structure, citation-style guidance, or reporting-guideline support.

not rated 659 +13 changed 29d ago A SkillSpector: warn 43 tokens original MIT

lynote-ai/ai-text-detector

Skill Claude CodeCodex

Detect whether a passage shows AI-like writing signals and return an explainable risk estimate with confidence, caveats, and next steps.

not rated 657 +2 25d ago A 33 tokens original MIT

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: