agent-ui
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in.…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
ai-automation-workflows
Build automated AI workflows combining multiple models and services. Patterns: batch processing, scheduled tasks, event-driven pipelines, agent loops. Tools:…
ai-rag-pipeline
Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs. Tools: Tavily Search, Exa Search, Exa Answer, Claude, GPT-4, Gemini via…
ai-voice-cloning
AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion/non-verbal steering), Inworld TTS…
llm-models
Access Claude, Gemini, Kimi, GLM and 100+ LLMs via inference.sh CLI using OpenRouter. Models: Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 3…
prompt-engineering
Master prompt engineering for AI models: LLMs, image generators, video models. Techniques: chain-of-thought, few-shot, system prompts, negative prompts.…
python-sdk
Python SDK for inference.sh - run AI apps, build agents, and integrate with all models. Package: inferencesh (pip install inferencesh). Supports sync/async,…
related-skill
Discover and install related skills from inference.sh skill registry. Helps find complementary skills for your AI workflow. Use for: skill discovery, workflow…
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…
soia-dev-agent-md-advisor
AI project instruction and configuration design advisor, providing diagnosis, drafting, and rewriting suggestions. Triggers: "review my AGENTS.md", "how to write CLAUDE.md", "how to manage multiple AI entry points"
soia-dev-task-execute
A general closed loop for executing any engineering task: define boundaries, implement the minimal change, verify, independently review, and receipt. Applies to code, configuration, documentation, and maintenance tasks. Triggers: "get this done", "execute by closed loop", "risky maintenance"
agent-browser
Automate browsers or Electron with agent-browser when explicitly requested, already used by the repo, or needed for its session/cloud-browser features.
background-agents
This skill should be used when the user asks about "parallel agents", "background tasks", "run_in_background", "non-blocking agents", "check agent…
prompt-gen
Generate high-quality structured prompts. Use when the user says "help me write a prompt", "optimize this prompt", "generate a prompt", "write an AI instruction", "help me tune the prompt", "prompt engineering", or "prompt engineering". Also applies to scenarios where the user describes a vague AI task and wants to distill it into a usable instruction. If the current environment is…
oc2-bot-development
Develop Outflank C2 event-driven Python bots. Use when creating or debugging OC2 automations.
agent-md-maintenance
Maintain agent instruction files effectively. Use when adding lessons learned, updating conventions, or restructuring project instructions.
opencode-cli
This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode…
skill-check
Audit and validate agent skills against the agentskills.io specification, best practices, and skills-ref implementation. Use when "audit skill", "validate…
electron
Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user…
generate-cover-prompt
AI prompt words for generating WeChat Official Account article cover images. Intelligently analyzes the article title and content, extracts the core value and visual theme, and generates professional prompt words suitable for use with AI drawing tools such as Jimeng. Supports reading article content from context to ensure the cover is highly consistent with the article theme. Use this skill when users need to generate WeChat Official Account article covers, create cover image prompt words, or illustrate articles.
base-trader
Autonomous crypto trading on Base via Bankr. Use for trading tokens, monitoring launches, executing strategies, or managing a trading portfolio. Triggers on…
causal-inference
Add causal reasoning to agent actions. Trigger on ANY high-level action with observable outcomes - emails, messages, calendar changes, file operations, API…
claude-connect
Connect Claude to Clawdbot instantly and keep it connected 24/7. Run after setup to link your subscription, then auto-refreshes tokens forever.