All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 436,665 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.
Cloud cost awareness for agents. Reminds the agent to check usage/billing before spending on metered services (Vercel, Cloudflare, Neon, Railway, E2B, Browserbase, AWS...) and to tear down what it provisions.
★not rated 113 3mo agoA
tokens not measured
originalMIT
Agent-native image workflow and optional prompt optimizer for /bananahub and generic agent image generation requests. Normalizes non-English prompts into English by default, generates or edits images across Gemini/Nano Banana, OpenAI GPT Image, chat-compatible routes, and Codex/host-native image tools when available…
Conversationally evolve an existing CoDD project. Use when the user describes a functional change in natural language ("add logout button", "change course model to master + delivery target", "remove daily log step") and you need to update requirements, design docs, lexicon, source code, and tests together while…
Troubleshoot and configure the Anthropic Subscription Proxy for OpenClaw. Use when the user has "The AI service returned an error", 401 auth failures through the proxy, key routing issues, pi-ai baseUrl overwrites, or needs help setting up the Claude Code proxy with OpenClaw. Also use when the proxy is not receiving…
Guidance for using the AgentHub Python SDK (agenthub-python). Use when developing agents that call different LLM APIs, need a unified interface for LLM providers, mention AgentHub, request agenthub-python, or already import it.
A study assistant skill for exam preparation that works from uploaded course materials, past exam questions, teacher presentations, assignments, and Markdown files. It converts and cleans the material before creating questions, answers, and exam-focused explanations.
Assisted job-application filler. Extracts the JD, scores fit, fills every form field from your profile and answer memory, and stops before Submit for your review. Runs interactively in Claude Code.
★not rated 113 4mo agoA
tokens not measured
originalMIT
Run the cold-start interview — learns your AI governance practice and writes /.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md from your AI policy, a reference impact assessment, and key vendor AI agreements. Use when the practice profile is missing or contains [PLACEHOLDER] markers, or when user…
Use Agent Search MCP for free-first English and Chinese web search with compact evidence and minimal tool calls. Trigger for factual discovery, claim verification, Chinese web results, selected-page extraction, provider failures, freshness limits, or search token and spend controls. Choose freesearch…
Use immediately for any bare YouTube or YouTube Shorts URL, youtu.be link, Bilibili or b23.tv link, or other video URL; do not ask what the user wants. Treat a message containing only a supported video URL as a request to create timestamped notes and a report, then publish to the configured local, Notion, or Obsidian…
A workflow for managing a personal content system, including recent publishing data, profile notes, collected information, and daily suggestions. The description is partly in Chinese and refers to Typefully and other external services.
Use when the user activates Rocky mode in Hermes, asks Hermes to speak as Rocky, wants Project Hail Mary / Eridian roleplay, or says to use Rocky voice. Persona skill: every user-visible response should be rendered in Rocky's voice until the user says 'Rocky stop', 'stop Rocky', or 'normal mode'.
Türk iş hukuku workflows: işe alım ve iş sözleşmesi incelemesi, fesih ve arabuluculuk risk kontrolü, ücret/çalışma süresi Q&A, işçi/bağımsız çalışan/alt işveren sınıflandırması, izin takibi, iç soruşturma ve işyeri politikaları.
★not rated 113▲
+3 6mo agoA
tokens not measured
originalApache-2.0
A restrained storytelling approach for nonfiction, personal narratives, profiles, and emotionally dense short fiction. It uses precise details, objects, actions, repetition, and withheld explanations to shape the story.
A plugin containing the Zettaranc knowledge base, a Chinese A-share stock-trading system. It includes buy and sell signals, trading strategies, analysis tools, and trading principles.
A workflow for using the TRIM command-line tool with fnOS, a storage-server operating system. It covers logging in and working with files, photos, videos, applications, Docker, and storage status.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
Generates a consistent illustrated image for every scene of a story — keeping characters, locations, and visual style coherent across the whole sequence using cascading reference images. Reads a {slug}scenes.json (from scene-splitter), proposes a visual style, ASKS the user for the aspect ratio and image model…
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: