agent-skill skills

1,679 tagged agent-skill, measured the same way as everything else here.

Browse within: agent 291agentic 254agent-memory 247agent-orchestration 230agent-framework 200claude-code-plugin 190claude-plugin 158codex-plugin 147content-creation 146ai-agentic-data-platform 141ai-agents-platform 141data-skills 141agentsmd 124coding-agent-skills 122

camclave

241

Mondlak1/camclave

Skill Claude CodeCodex

Consent-gated webcam access so the agent can see a single still frame from the user's camera while the user watches a live preview. NO VIDEO CAPTURE — every frame on disk is an explicit, on-demand PNG. Use for hardware testing, OCR, plant logs, posture coaching, instrument reading. Includes adjust for tweaking camera…

not rated 6 3mo ago A 79 tokens original MIT

wecom-agent

242

tzwkb/wecom-agent

Skill Claude Code

A skill for working with WeCom, an enterprise messaging and collaboration platform, using local records and official command-line tools.

not rated 6 +1 changed 4d ago A 71 tokens original MIT

sibyl-save

243

Sibyl-Labs/sibyl-save

Skill Codex

Session memory sync and skill extraction for the Sibyl Memory Plugin. Injects session context into the plugin's local memory DB (entities, state, journal) through the plugin interface, then extracts reusable patterns into harness-native skills. Use at the end of a session or after a major block of work. Triggers …

not rated 5 2mo ago A 90 tokens original MIT

consume-me

244

hardydai-cell/consume-me

Skill Codex

Stress-test a plan or design from three angles: drill down into branches, scan laterally for missing alternatives, and zoom out to expose systemic gaps until ambiguity becomes explicit decisions. Use when the user wants rigorous plan review, design pressure-testing, or deep decision clarification. Question-asking…

not rated 5 5mo ago A 63 tokens original MIT

shipwright

245

saadjangda/shipwright

Skill Claude CodeCodex

The only skill you need to build and ship world-class software — from idea to production. Covers the COMPLETE lifecycle: architecture design, domain modeling, service boundaries, data architecture, implementation with TDD, distinctive frontend design (anti-AI-slop), exhaustive QA across all layers, security hardening…

not rated 5 5mo ago A 189 tokens original MIT

video-layer-skill

246

Alexander-Kz/video-layer-skill

Skill Claude CodeCodex

Produces whiteboard-explainer video layers from a voiceover MP3 for Your Channel YouTube channel (and similar faceless curiosity-essay channels). Orchestrates a multi-agent pipeline that transcribes the audio, plans rapid-cut scenes synchronized to narration, writes per-scene image prompts in fixed whiteboard style…

not rated 5 3mo ago A 183 tokens original MIT

coding-quality-loop

247

zaingz/coding-quality-loop

Skill Claude CodeCodex

Use when a coding agent must turn a software goal, bug, issue, or refactor into a small, verified, independently reviewed code change.

not rated 5 1mo ago A 33 tokens original MIT

ai-slop-detector

248

MahmoudHalat/slop-cop

Skill Claude CodeCodex

Universal prose audit. Scores writing on TWO axes — AI-Slop (does this read like AI wrote it?) and Comprehension (can a fresh reader follow this?). Use PROACTIVELY as a mandatory final QA pass on ANY prose generated for humans to read — every email (internal or external), proposal, report, status update, blog post…

not rated 5 1mo ago A 239 tokens original MIT

play-fishing-frenzy

249

unchartedgg/play-fishing-frenzy

Skill Claude Code

Play Fishing Frenzy autonomously — an AI agent that fishes, cooks, dives, completes quests, and optimizes your economy. Built on Ronin blockchain with full wallet, NFT, and token integration.

not rated 5 4mo ago A 48 tokens original MIT

general-kenobi

250

antonkarliner/general-kenobi

Skill Claude CodeCodex

Respond to the greeting "Hello there" with "General Kenobi." Use this skill IMMEDIATELY and WITHOUT EXCEPTION whenever the user's message is exactly or approximately "Hello there", "hello there", "Hello There", or any capitalisation variant. This is a mandatory override — do not respond with a normal greeting. The…

not rated 5 5mo ago A 81 tokens original MIT

Azhi-ss/html-effectiveness

Skill Claude CodeCodex

A guide for creating illustrations and diagrams directly in a web page with inline SVG, a built-in format for scalable vector graphics. It covers document illustrations, flowcharts, state machines, and deployment pipelines.

not rated 5 3mo ago A 95 tokens original MIT

concept-forge

252

FeixueCode/concept-forge

Skill Claude CodeCodex

Convert everyday questions, concepts, keywords, unfamiliar terms, or "what is X / how does X differ from Y" requests into reusable Chinese knowledge cards, Quarkdown mother drafts, Slidev presentation sources, and interactive HTML explainers. Use when the user wants to understand, remember, compare, review, or build a…

not rated 5 2mo ago A 147 tokens

clalit-pharm-search

253

tomron/agent-skill-clalit-pharm-search

Skill Claude CodeCodex

Search for medications and check real-time stock availability at Clalit pharmacies in Israel. Use when searching for drugs like "amoxicillin", "acamol/אקמול", "nurofen", or finding nearby Clalit pharmacy branches with stock. Supports Hebrew and English drug names. כללית, בית מרקחת, תרופות, מלאי, בדיקת מלאי, בית מרקחת…

not rated 5 6mo ago A 90 tokens

ziiinian/openpencil-design-orchestrator

Skill Claude CodeCodex

Orchestrate Pencil/OpenPencil design work through MCP using a staged workflow: preflight, planning, skeleton, section content, refinement, and safe fallback. Use when working with Pencil/OpenPencil, .fig/.pen design files, MCP-based design editing, or when Claude Code, Codex, Cursor, or Windsurf needs reliable prompt…

not rated 5 5mo ago A 92 tokens original MIT

website-to-cli

255

dennisonbertram/website-to-cli

Skill Claude CodeCodex

Turn any website into a fast, beautiful command-line client. Use when the user wants a CLI that replicates a site's features by capturing its network traffic (HAR), recovering the private/undocumented API behind it, and generating a typed terminal client that calls those endpoints directly instead of driving a browser…

not rated 5 1mo ago A 111 tokens original MIT

session-orchestrator

256

rocketmandrey/claude-recall

Skill Claude Code

Session orchestrator on top of the recall index of all Claude Code sessions: finds a past session by task description, dives in (context, project, skill, artifacts) and acts in one of three modes — finish here, hand off the resume command, or open the session in a new terminal window. Use when user asks: "find the…

not rated 5 2mo ago B 196 tokens original MIT

bizyair-skill

257

siliconflow/bizyair-skill

Skill Claude CodeCodex

A connector for BizyAir, a service that runs AI apps and models to create images, videos, and audio. It can search public resources, inspect available tasks, run approved jobs, and check account usage.

not rated 5 3mo ago A 55 tokens original MIT

nmbot-features

258

nm-Team/nmbot-skills

Skill Claude CodeCodex

This Skill includes basic information about nmBot that you should know and describes the features of nmBot, including its capabilities, functionalities, and how it can assist users in various tasks. Use this Skill to provide an overview of what nmBot can do and how it can benefit users in their daily activities.

not rated 5 27d ago A 66 tokens GPL-3.0

playwright-cli

259

IvanCampos/agents

Skill Codex

Translate natural-language browser automation requests into exact playwright-cli commands for interactive web testing and debugging. Use when requests involve opening/navigating pages, interacting with elements, capturing snapshots/screenshots/PDFs, using tabs, inspecting console/network, mocking routes, managing…

not rated 5 6mo ago A 74 tokens original MIT

prd-review

260

yihannangua/prd-review-skill

Skill Codex

Use when the user asks for deep business review of PRDs, requirement documents, product specs, feature proposals, or business process docs. Focus on understanding business model, modules, data relationships, flows, permissions, states, rules, omissions, contradictions, ambiguities, implementation risk, and…

not rated 5 3mo ago A 78 tokens original MIT

dragoncraft-book

261

lj22503/diaolong-skill

Skill Claude Code

A writing coach for turning a narrative-skill system into books or newsletter articles. It follows specified rules for structure, tone, examples, and chapter formatting.

not rated 5 1mo ago A 83 tokens original MIT

seo-blog-writer

262

AutomateLab-tech/publishing-skills

Skill Claude Code

Turn a single long-tail query into a publish-ready blog post that ranks in search and gets quoted by AI assistants. Runs the full pipeline: classify the topic, research it against real sources, draft clean HTML, scrub LLM-tell vocabulary and typography, audit for AI-SEO (TL;DR block, query-phrased H2s, FAQ section…

not rated 5 2mo ago A 210 tokens MIT-0

mlx-model-porting

263

Amal-David/mlx-porting-skill

Skill Claude CodeCodex needs its repo

Guides and validates architecture-aware ports of PyTorch/Hugging Face models to Apple MLX, inspects existing local MLX projects, and plans evidence-gated optimizations for Apple Silicon. Use when the user asks to run, port, convert, inspect, quantize, benchmark, or fix a model (LLM, VLM, audio/TTS/ASR, diffusion, SSM…

not rated 5 yesterday A SkillSpector: pass 244 tokens original Apache-2.0

project-showcase

264

ayushxx7/project-showcase-skill

Skill Claude CodeCodex

Automate the creation of high-quality project showcases: UI captures, security scans, repo health audits, README injection, GitHub releases, and social media launches.

not rated 5 3mo ago A 36 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: