All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 435,065 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.
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.
Skill Claude CodeCodex
Detect whether a passage shows AI-like writing signals and return an explainable risk estimate with confidence, caveats, and next steps.
Skill Codex
Use when the agent is running inside yolobox and needs to orient itself to the current sandbox, trust model, runtime/config, mounts, network mode, readonly/output paths, Docker access, forwarded env keys, or other environment constraints and freedoms. Also use when the user explicitly invokes /yolobox.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 107 tokens together
AgentKey — one-stop live data marketplace for your agent: web search, web scraping, social media, finance, crypto, e-commerce, business data, weather/maps, and travel through a single MCP server. No API keys to manage, auto failover across providers, free to start.
YuJunZhiXue/StudyAnalysis-Skills
Skill Claude CodeCodex
A Chinese-language workflow for deeply analysing links, documents, or code and turning them into teaching notes for beginners through advanced readers. It also checks claims against source material and flags possible hallucinations or outdated information.
Skill Claude CodeCodex
Build and maintain a Karpathy-style LLM knowledge base — a self-compiling Obsidian markdown wiki where an Agent ingests raw sources, compiles cross-linked concept/entity/summary pages, answers queries against the corpus, lints the graph for health, and audits in-context human feedback filed from Obsidian or the local…
Skill Claude CodeCodex
Create or update ZeptoClaw skills. Use when designing, structuring, or authoring new agent skills.
Plugin Claude Code ✓ vendor
Bundles 41 skills, 17 commands, 1 agent, 3 MCP servers, 1 plugin · 2,978 tokens together
Getting-started router skill for Rayfin - scaffold a new app with the Rayfin CLI, then use the version-locked skill installed in the project.
Plugin Claude Code
Generate editable PowerPoint decks from papers, PDFs, code repositories, documents, and existing slides.
Skill Claude Code
Process whole-slide pathology images (WSIs) with TRIDENT: tissue segmentation, patch coordinate extraction, and patch/slide feature (embedding) extraction with foundation models (UNI, CONCH, Virchow, Gemma, Titan, GigaPath, etc.). Use when the user works with WSIs (.svs/.tiff/.ndpi/.mrxs/.czi/.dcm), mentions TRIDENT…
Skill Claude Code
Generate an articulated (pull-out drawers / openable doors) 3D GLB model from a reference image, with real PBR textures (diffuse/roughness/normal) and headless render verification. Use when the user asks to build an articulated model (GLB/glTF) from an image, add textures or physical material parameters (roughness…
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 76 tokens together
Search, read and analyze your haiku.rag knowledge base from Claude Code.
Skill Codex
Legacy compatibility entry. Use only when design-in-figma is not installed; otherwise use design-in-figma. Create or update native, editable Figma designs with TemPad Dev MCP: screens, flows, components, and requested local design-system resources, including on an empty canvas. Use when asked to create, mock up, or…
Skill Claude CodeCodex
A quality guide for creating or repairing Mermaid workflow diagrams and structured input forms for skills. Mermaid is a text format that renders diagrams, while A2UI forms collect missing information during an interaction.
Skill Claude CodeCodex
Compiles comprehensive company product context from PDF documents, web research, and industry knowledge.
Skill Claude CodeCodex
Guide an installing agent through a staged PPT or slide workflow without constraining its implementation choices. Use when the user wants a presentation, deck, storyboard, or slide-ready structure from a topic, article, report, or brief, and success depends on some combination of: clarifying the brief, gathering facts…
Skill Claude CodeCodex ✓ vendor
Run and interpret SkillEvaluator for agent skills. Use for any skill benchmark or eval - validating or scoring a SKILL.md, writing evals.json test cases or evals config, explaining benchmark reports, verdicts and exit codes, or gating skills in CI.
Plugin Claude Code
Bundles 1 skill · 44 tokens together
Write idiomatic YAMLScript code. Use when asked to write, convert, or review YAMLScript (.ys files).
Skill Claude CodeCodex
Reference skill for sage-wiki — local-first knowledge graph with MCP server, REST API, compiled wiki, and Obsidian-compatible output.
Agent Claude Code
Senior advisor for hard problems. Consult when stuck on architecture decisions, ambiguous tradeoffs, or when an approach isn't working. Returns guidance, not implementation.
Plugin Claude Code
Bundles 19 skills · 5,921 tokens together
GMGN OpenAPI skills — token info, market data, wallet portfolio & copy-trade scoring, and swap.
yanhua1010/self-media-content-workflow
Plugin Claude Code
Bundles 10 skills · 1,203 tokens together
A toolkit for planning, creating, publishing, and reviewing content for social-media accounts across several platforms.
gemini-cli-extensions/workspace
Skill Claude CodeCodex
CRITICAL: You MUST activate this skill BEFORE creating, querying, or managing calendar events. Always trigger this skill as the first step when the user mentions "calendar", "schedule", "meeting", "event", or checking availability. Contains strict behavioral mandates that override default calendar behavior.
mikobinbin/2026-world-cup-predictor
Skill Claude CodeCodex
A system for predicting the 2026 men's football World Cup champion using player development, team Elo ratings, and additional non-sporting factors.
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: