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.

skill-authoring

1393

uvwt/agentdock

Skill Claude CodeCodex

A guide for creating and maintaining AgentDock skills, which are instruction packages that teach an agent how to handle a specific kind of work.

not rated 1.3k +5 changed 1mo ago A SkillSpector: pass 52 tokens original Apache-2.0

swift-mlx-lm

1394

kellyvv/PhoneClaw

Skill Claude CodeCodex

MLX Swift LM - Run LLMs and VLMs on Apple Silicon using MLX. Covers local inference, streaming, wired memory coordination, tool calling, LoRA fine-tuning, embeddings, and model porting.

not rated 1.3k +5 3mo ago A SkillSpector: pass 52 tokens original Apache-2.0

douyin-video

1395

yzfly/douyin-mcp-server

Skill Claude CodeCodex

A tool for downloading videos from Douyin, a Chinese short-video platform, and extracting spoken words as text. It can save downloads and transcripts in folders named after each video.

not rated 1.3k +3 4mo ago A Socket: passSnyk: warn 96 tokens original Apache-2.0 archived

critique

1396

remorses/critique

Skill Claude CodeCodex

Git diff viewer. Renders diffs as web pages, images, and PDFs with syntax highlighting. Use this skill when working with critique for showing diffs, generating diff URLs, or selective hunk staging.

not rated 1.3k +1 changed 4d ago A SkillSpector: pass 45 tokens original MIT

wcag22-a11y-audit

1397

AIPexStudio/AIPex

Skill Claude CodeCodex

WCAG 2.2 Accessibility Audit skill that systematically evaluates web pages against 8 core Success Criteria (1.1.1, 1.4.3, 1.4.11, 2.1.1, 2.1.2, 2.4.3, 2.4.7, 4.1.2) using accessibility tree inspection and visual analysis. Use this skill when you need to perform accessibility testing/auditing on a live webpage.

not rated 1.3k +8 2mo ago A SkillSpector: pass 111 tokens original MIT

gooseworks-ai/goose-skills

Skill Claude CodeCodex

Generate an AI creator talking to camera, saying an approved script, as one continuous track — H3 Max reference-to-video through the GooseWorks fal-proxy (charged to your GooseWorks credits). Plans takes on line boundaries under H3's 15s cap, dry-runs a cost estimate, generates the first take alone so its voice can be…

not rated 1.3k +7 changed 12d ago A 132 tokens original MIT

mcp-cli

1399

philschmid/mcp-cli

Skill Claude CodeCodex

Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers.

not rated 1.3k +2 9mo ago A 35 tokens original MIT

geo-optimizer

1400

Auriti-Labs/geo-optimizer-skill

Skill Claude CodeCodex

Audit and fix a website for AI search visibility (Generative Engine Optimization). Use when asked to check whether a site or page can be found and cited by ChatGPT Search, Perplexity, Claude or Google AI Overviews, to score it 0-100 with geo audit, or to fix robots.txt AI crawler rules, llms.txt, JSON-LD schema, meta…

not rated 1.3k +31 changed 3d ago A 91 tokens original MIT

fenics-fem

1401

Cai-aa/CAE-Agent-Hub

Skill Claude CodeCodex

Use this Skill to solve PDEs with the finite element method using FEniCS/dolfinx: weak form formulation, mesh generation with gmsh, Poisson/elasticity problems, boundary conditions, and paraview export.

not rated 1.3k +51 10d ago A SkillSpector: warn 53 tokens original MIT

crit-cli

1402

tomasz-tomczyk/crit

Skill Claude Code

Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…

not rated 1.3k +14 changed 2d ago A SkillSpector: pass 110 tokens original MIT

adapter-author

1403

DefiLlama/DefiLlama-Adapters

Skill Claude CodeCodex

Validates whether a DefiLlama request belongs in DefiLlama-Adapters, then helps coding agents create and validate TVL adapters when it does. Use when a user wants to add a new DefiLlama TVL protocol listing, check repo fit, create or fix a TVL adapter, choose adapter helpers or registries, run node test.js, prepare PR…

not rated 1.3k +4 yesterday A SkillSpector: pass 103 tokens

ascii-video

1404

math-inc/OpenGauss

Skill Claude CodeCodex

Production pipeline for ASCII art video — any format. Converts video/audio/images/generative input into colored ASCII character video output (MP4, GIF, image sequence). Covers: video-to-ASCII conversion, audio-reactive music visualizers, generative ASCII art animations, hybrid video+audio reactive, text/lyrics…

not rated 1.3k +2 7mo ago A SkillSpector: pass 118 tokens original MIT

mao-zedong-perspective

1405

leezythu/maoxuan-skill

Skill Claude CodeCodex

A Chinese-language thinking framework based on Mao Zedong's published writings, using ideas such as identifying the main contradiction and testing conclusions through practice.

not rated 1.3k +10 2mo ago A 217 tokens original MIT

shellm

1406

laude-institute/headlong

Skill Claude CodeCodex

Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.

not rated 1.3k +4 yesterday A SkillSpector: warn 49 tokens original Apache-2.0

competitor-analysis

1407

firecrawl/web-agent

Skill Claude CodeCodex

Compare two or more companies, products, or platforms across pricing, features, positioning, and docs. Use this skill whenever the user says "compare X vs Y", "how does X stack up against Y", "alternatives to X", "competitive landscape of …", "X vs Y vs Z", or asks for a competitor matrix. Uses search to discover…

not rated 1.3k +7 15d ago A SkillSpector: pass 108 tokens original MIT

manimgl-best-practices

1408

adithya-s-k/manim_skill

Skill Claude CodeCodex

Trigger when: (1) User mentions "manimgl" or "ManimGL" or "3b1b manim", (2) Code contains from manimlib import , (3) User runs manimgl CLI commands, (4) Working with InteractiveScene, self.frame, self.embed(), ShowCreation(), or ManimGL-specific patterns. Best practices for ManimGL (Grant Sanderson's 3Blue1Brown…

not rated 1.3k +29 9mo ago A Socket: passSnyk: pass 167 tokens original MIT

benchmark

1409

soniqo/speech-swift

Skill Claude Code needs its repo

Run performance + quality benchmarks. ASR reports WER, RTF, process memory, and throughput across engines/variants. Arguments include asr, tts, vad, diarize, asr-quick.

not rated 1.3k +10 changed 21d ago A SkillSpector: warn 0 tokens original Apache-2.0

teamskill-creator

1410

XiaoLuoLYG/GOD

Skill Claude CodeCodex

Creates, converts, or modifies Teamskills — the multi-role extension of the Skills standard (specialized roles + workflow + bind constraints). Use when the user wants to author a multi-role agent team, convert a single-agent skill into one, or refactor an existing team. Do NOT use for single-agent Skills — use…

not rated 1.3k +11 15d ago A SkillSpector: warn 74 tokens original Apache-2.0

matlab/matlab-agentic-toolkit

Skill Claude CodeCodex

Use when writing MATLAB functions with arguments blocks — repeating arguments (arguments (Repeating)), .?ClassName property import in constructors, name-value forwarding with namedargs2cell, or migrating from inputParser or validateattributes. Also when reviewing signatures for implicit-conversion pitfalls (size…

not rated 1.3k +28 changed 29d ago A 199 tokens

ongridio/ongrid

Skill Claude CodeCodex

A tool for carrying out explicitly requested Ongrid operations involving devices, alerts, rules, dashboards, platform APIs, restricted hosts, or Kubernetes.

not rated 1.3k +20 yesterday A 44 tokens AGPL-3.0

attackgen-tabletop

1413

mrwadams/attackgen

Skill Claude CodeCodex

Turn a MITRE ATT&CK/ATLAS threat group or case study — or a frontier AI agent deployed inside the organisation — into a full incident-response tabletop exercise (MSEL): scenario narrative, kill chain or agent threat scope, timestamped injects, discussion questions, and a detection-coverage scorecard, using the…

not rated 1.3k +1 changed 13d ago A SkillSpector: pass 155 tokens GPL-3.0

vision-skills

1414

Anionex/agent-vision-toolkit

Skill Codex

Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/htmlshot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long…

not rated 1.3k +4 changed 29d ago A SkillSpector: pass 132 tokens original MIT

babylonjs-engine

1415

freshtechbro/claudedesignskills

Skill Claude Code

Comprehensive skill for Babylon.js 3D web rendering engine. Use this skill when building real-time 3D experiences, browser-based games, interactive visualizations, or immersive web applications. Triggers on tasks involving Babylon.js, 3D scenes, WebGL/WebGPU rendering, entity-component systems, physics simulations…

not rated 1.3k +55 11mo ago A Socket: passSnyk: pass 97 tokens original MIT

starknet-js

1416

starknet-io/starknet.js

Skill Claude CodeCodex

Use when writing or debugging JavaScript/TypeScript that interacts with Starknet through the starknet.js SDK — building Call objects or calldata, encoding/decoding Cairo types (felt252, u256, structs, arrays, spans, ByteArray, Option/Result/custom enums), or working with contracts, accounts, providers, transactions…

not rated 1.3k changed 1mo ago A SkillSpector: warn 79 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: