All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 437,151 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 Code
Convert PowerPoint (PPTX) files to HTML and back, analyze PPTX structure, generate slide decks from topics via LLM, pre-cache CDN assets, or launch the interactive review web UI. Use this when the user wants to work with PowerPoint presentations -- convert ppt to html, html to pptx, inspect pptx contents, or generate…
tensorlakeai/tensorlake-skills
Plugin Claude Code
Bundles 1 skill · 221 tokens together
Tensorlake SDK for agent sandboxes and sandbox-native orchestration. Use when building AI agents that need sandboxed execution environments, isolated tool calls, or durable workflow orchestration.
Skill Claude CodeCodex
Guidelines for writing and executing Google Apps Script code using ggsrun and finding documentation via workspace-developer. Use when developing or running GAS applications.
Plugin Claude Code
Bundles 1 skill · 46 tokens together
Guides users through configuring tsk Docker container images for their project, including stack, agent, and project layer setup.
JayZeeDesign/awesome-claude-skills
Skill Claude CodeCodex
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
Plugin Claude Code
Bundles 8 skills, 5 agents, 3 hooks · 183 tokens together
Build and run multiple personas across any AI agent.
Skill Claude CodeCodex
Use when working with Payload projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.
Dicklesworthstone/ultimate_mcp_client
Cursor rule Cursor
The MCP Client is built around several key architectural components as found in mcpclient.py.
Skill Codex
Use only the current SciAtlas automated review workflow (reviewpipeline) to take a novice user from zero setup to a final automated review of a research idea or paper, including setup, registration guidance, workflow configuration, retrieval, artifact reading, and synthesis. Trigger when the user asks whether an idea…
Skill Claude CodeCodex
Turn any input (a website URL, a text brief, existing footage, a music track) into a finished, pixel-perfect MP4 — fully local, byte-stable across renders. The agent researches the input and dumps a typed SPEC; the Lazy Frames CLI turns that spec into video. Use for website promos, cinematic clips, motion graphics…
Skill Claude CodeCodex
Run OmniScientist end to end in the OmniScientist CLI using DeepSeek V4 Flash. Turn raw research data (images, signals, audio, video, 3-D, tables, or graphs) and an open direction into perceived evidence, a falsifiable hypothesis, recorded analysis, real citations, a gated candidate paper, PDF, and Overleaf bundle.…
Agent Claude Code
Reads analyzer output · produces daily digest at knowledge/articles/{date}.md.
diegosouzapw/awesome-omni-skills
Skill Claude CodeCodex
ADVOGADO CRIMINALISTA SENIOR — ESPECIALISTA EM DIREITO PENAL E MARIA DA PENHA workflow skill. Use this skill when the user needs Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal and the operator should…
vintasoftware/django-ai-plugins
Plugin Claude Code
Bundles 1 skill · 156 tokens together
Write, review, and rewrite Django migrations for PostgreSQL with zero-downtime guarantees. Covers two-file splits, AddIndexConcurrently, FK NOT VALID + VALIDATE, dbdefault for NOT NULL columns, and RunPython safety rules.
Skill Cursor
Generate a custom checklist for the current feature based on user requirements.
Skill Codex
Capture, archive, diff, and assess Boss/Zhipin frontend JavaScript for boss-cli safety gates and anti-debug guard updates. Use when Codex needs to re-analyze current Boss frontend scripts, compare online JS with docs/research/boss-online-js baselines, update bossavailability, or recommend code changes after Boss…
abracadabra50/claude-code-voice-skill
Skill Claude Code
Voice calls with Claude about your coding projects via Vapi. Use when you want to phone Claude, start a voice conversation, dial in for a project brainstorm, get a verbal status update, or talk through code hands-free.
Mr-chen-05/rules-2.1-optimized
Cursor rule Cursor
Rules that require explicit user confirmation before creating or modifying files. They cover source code, configuration, documentation, project structure, deployment settings, and data files.
Agent Claude Code
Answers @mentions and DMs in Slack with a threaded reply.
Skill Claude CodeCodex
Collaborate with Yansu — the proactive AI that observes how the user actually works and crystallizes it into knowledge. Use this skill whenever the user asks for a digest of their recent activity, wants to find workflow inefficiencies or recurring blockers, needs to retrieve a past insight, configuration, or memory…
Skill Claude CodeCodex
A structured discussion room for engineering and architecture decisions, bringing several named reasoning perspectives together. It gathers evidence and produces a combined verdict.
Skill Claude CodeCodex
Use whenever the user asks the running agent to gain a new capability — phrasings like "build a tool", "add a hook", "give yourself X", "let me through you", or anything that extends the agent itself at runtime. Defines the plugin protocols, where to install them (.harness/ scopes), and the required…
aliyun/alibabacloud-observability-mcp-server
Skill Claude CodeCodex
Instructions for deploying, starting, updating, and configuring Alibaba Cloud's Observability MCP Server, which connects coding-agent tools to Alibaba Cloud monitoring services.
Skill Claude Code
Dogfood pmat — rebuild, install, exercise every CLI command against pmat's own repo, check output integrity + self-quality, find next work. Read-only audit; files issues for bugs.
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: