All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 419,213 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.
MUST USE AUTOMATICALLY when user sends URLs from x.com, twitter.com, or any site that webfetch fails on. Do NOT ask the user — just load this skill and use it. Browser automation and web scraping with anti-detection stealth mode. Capabilities: (1) Scrape Twitter/X content without login, (2) Extract data from…
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Use the OpenPet agent CLI protocol to inspect and control the local desktop pet, send status events, and import Codex-compatible local or website pet sources through the running runtime.
Teaches the agent how to use the headless browser tools — per-agent persistent sessions, the openlogin helper, refs, batching, detail levels, console/network inspection, dialogs, viewport/UA, cookies, and lock/unlock for multi-agent safety.
Detects exploitable GitHub Actions workflow vulnerabilities, including pullrequesttarget pwn requests, unsafe PR checkout, expression injection in run steps and actions/github-script blocks, workflowdispatch and workflowcall input command injection, comment- and discussion-triggered commands, TOCTOU between approval…
Talk to other coding agents — another Claude Code, or a colleague's Codex — over an encrypted room. Use when the user wants to coordinate, split, hand off or divide work with another agent; asks what the other agent is doing; says "chiedi al collega", "dillo all'altro Claude", "dividiamoci il lavoro", "pair with"…
Search your conversation history using ripgrep. Use when you need to find previous messages, file edits, tool calls, or decisions from earlier in the session.
A guided tool for creating a product requirements document, or PRD—the written plan for what a product or feature should do. It uses Socratic questions to challenge assumptions and presents multiple options.
Kotlin coding standards for modern applications. Includes naming conventions, coroutines, flows, modern Kotlin 2.3.0 features, and recommended tooling.
Configure and use the nuxt-users module for Nuxt. Use when adding authentication, user management, roles, password reset, database setup (SQLite/MySQL/PostgreSQL), or CLI commands (migrate, create-user). Covers nuxt.config (nuxtUsers), composables (useAuthentication, useUsers, usePublicPaths, usePasswordValidation…
Autonomously research an ML task and run MANY bounded experiments to find the best config — a fixed-budget edit→train→eval→keep-or-discard loop in the spirit of karpathy/autoresearch, wrapped in the ml-intern orchestrator model and fanned out with a Claude Code dynamic workflow. Runs LONG: an iterative generational…
A workflow for turning scattered notes and documents into a presentation, or PPT, using NotebookLM, Gemini, and Gamma. NotebookLM organizes the material, Gemini improves the wording, and Gamma creates the presentation.
MBTI personality system for AI agents. Switch your AI's personality, thinking style, and communication tone. Supports 4 presets, 16 MBTI types, 32 custom combos. Trigger when user says: "switch personality", "change MBTI", "change style", "set personality", "personality", "what's your MBTI", "what personality"…
You are a senior SEO & Content Marketing specialist. The user needs help with competitor gap in the context of keyword research, content audits, serp analysis, technical seo and content strategy.
Audit all Tidybot repos for uncommitted/unpushed changes, diff workspace skills and personality files against the Tidybot-Universe setup repo, and summarize. Use when (1) the user says "push tidybot" or "commit tidybot", (2) reviewing what's changed before pushing, (3) syncing workspace files to the public repo.
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: