Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Agent workflows
Vision-driven browser automation using Midscene Bridge mode. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. Connects to the user's desktop Chrome browser via the Midscene Chrome Extension, preserving cookies, sessions, and login state. Does NOT take over the user's mouse or keyboard — operates through Chrome DevTools Protocol. Use this skill when the user wants to: - Browse, navigate, or open web pages in the user's own Chrome browser - Interact with pages that require login sessions, cookies, or existing browser state - Scrape, extract, or collect data from websites using the user's real browser - Fill out forms, click buttons, or interact with web elements - Verify, validate, test, or QA frontend UI behavior - Take screenshots of web pages - Automate multi-step web workflows - Test what was just built, validate the UI in real browser Powered by Midscene.js (https://midscenejs.com)
An intelligent search router based on opencli commands. Always use this skill when the user wants to search, query, find, or research information, especially when it involves specific websites, social media, technical materials, news, shopping, travel, job hunting, finance, or Chinese-language content.
Plug-in vision for text-only models. Hard rule: when a file path or URL with an image extension (.png, .jpg, .jpeg, .webp, .gif, .heic, .heif) appears anywhere in the conversation (typed by the user, injected as a `[Image: source: <path>]` line, or inside a tag) and you cannot see that image's content, run this skill on it before any other approach: no self-built OCR, no PIL, no tesseract. Also triggers on pasted-image placeholders such as `[Image #1]` and `[Unsupported Image]`. If you can actually see the image, do not use this skill. When unsure, run `modlens guard` before the first read of a session: a deny verdict means the active model has native vision and must read the image itself. Runs the modlens CLI to convert the image into structured JSON evidence: every word transcribed, layout regions, semantics, visual clues. Also use when the user asks how to install, configure, or switch modlens providers (Gemini API key, OpenAI-compatible endpoints, Claude API or Claude Code CLI)
You MUST use this when several units of work might run concurrently through agents - independent investigations, specialist reviews, repository analyses, or plan tasks that look unrelated - covering whether they are genuinely independent, which mutable state needs isolation, how wide the wave should be, and how results are reconciled before integration.
Declarative UI widgets from JSON for React/Next.js from ui.inference.sh. Render rich interactive UIs from structured agent responses. Capabilities: forms, buttons, cards, layouts, inputs, selects, checkboxes. Use for: agent-generated UIs, dynamic forms, data display, interactive cards. Triggers: widgets, declarative ui, json ui, widget renderer, agent widgets, dynamic ui, form widgets, card widgets, shadcn widgets, structured output ui
Tool lifecycle UI components for React/Next.js from ui.inference.sh. Display tool calls: pending, progress, approval required, results. Capabilities: tool status, progress indicators, approval flows, results display. Use for: showing agent tool calls, human-in-the-loop approvals, tool output. Triggers: tool ui, tool calls, tool status, tool approval, tool results, agent tools, mcp tools ui, function calling ui, tool lifecycle, tool pending
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Search, score, scan, and import agent skills from GitHub repositories that contain SKILL.md, CLAUDE.md, .cursorrules, and similar agent skill files. Discover community skills across many tool and provider categories, evaluate relevance with heuristic scoring, check for malware or hardcoded secrets, and install into Hermes, Claude Code, Gemini CLI, or OpenCode agent directories.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Interactive onboarding tour for the context-matic MCP server. Walks the user through what the server does, shows all available APIs, lets them pick one to explore, explains it in their project language, demonstrates model_search and endpoint_search live, and ends with a menu of things the user can ask the agent to do. USE FOR: first-time setup; "what can this MCP do?"; "show me the available APIs"; "onboard me"; "how do I use the context-matic server"; "give me a tour". DO NOT USE FOR: actually integrating an API end-to-end (use integrate-context-matic instead)
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Drive the user's existing Chromium-family browser with deterministic Playwright. Use when asked to inspect, automate, test, or interact with a visible browser tab; continue an authenticated browser workflow; handle 2FA, passkeys, CAPTCHAs, or payment confirmation; record browser behavior; or capture an authenticated network flow.
Convert PRDs to beads for ralph-tui execution. Creates an epic with child beads for each user story. Use when you have a PRD and want to use ralph-tui with beads as the task source. Triggers on: create beads, convert prd to beads, beads for ralph, ralph beads.
Work with the upstash-box Python SDK for sandboxed cloud containers with AI agents, shell, filesystem, git, cron schedules, snapshots, and a headless browser. Use when building with Upstash Box in Python, creating a sandbox or isolated environment to run untrusted or agent-generated code, running AI coding agents in containers, giving an agent a cloud dev environment with a shell and repository, browser automation from a box, scheduling recurring jobs inside a box, saving and restoring snapshots, or orchestrating parallel boxes.
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Searches and recovers Claude Code JSONL history across all active config homes and archives registered in ~/.claude/history-sources.json. Use --all-projects when the project is unknown, --codex to include Codex rollout search, and --kimi to include Kimi CLI (kimi-code) session search. Uses internal timestamps and searches messages, thinking, tool inputs/results, queues, attachments, summaries, titles, and file-history paths. Recovers exact captured bytes from Claude file-history snapshots, including post-Write edits and binary files; otherwise labels Write checkpoints as lower fidelity. Use for keyword/date-bounded history search, prior-conversation forensics, deleted-file recovery, vanished ~/.claude/jobs artifacts, tool/file-operation analysis, or requests mentioning session history, find in history, previous conversation, or .claude/projects. For a recent Claude+Codex+Kimi CLI inventory, use local-conversation-history instead
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
CodeStable is an AI coding workflow for serious software engineering that keeps humans in the loop. Rather than centering on Agent orchestration, it organizes requirements, architecture, features, issues, and historical decisions to make development driven by Codex and Claude controllable, traceable, and continuously evolvable.
Build RAG (Retrieval Augmented Generation) pipelines with web search and LLMs. Tools: Tavily Search, Exa Search, Exa Answer, Claude, GPT-4, Gemini via OpenRouter. Capabilities: research, fact-checking, grounded responses, knowledge retrieval. Use for: AI agents, research assistants, fact-checkers, knowledge bases. Triggers: rag, retrieval augmented generation, grounded ai, search and answer, research agent, fact checking, knowledge retrieval, ai research, search + llm, web grounded, perplexity alternative, ai with sources, citation, research pipeline
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously, build all pages of a site, generate multiple pages in sequence, or run a 'design loop' / 'baton loop' / 'autonomous site build' — even if they say 'just keep going' or 'build the next page' or 'next page' mid-flow.
Use when building, refactoring, or documenting Graft apps and proxies, including when asked to create a tool server, API server, dual-protocol server, or MCP-HTTP bridge. Graft's core thesis: define tools once and serve them as both HTTP REST endpoints and MCP tools from the same server, with discovery, docs, and OpenAPI generated automatically. Covers concrete actions such as defining tools and handlers, configuring authentication middleware, setting up HTTP and stdio transports, generating OpenAPI documentation, wrapping existing APIs via proxy mode, and wiring up the full CLI workflow
Analyzes a single MLflow trace to answer a user query about it. Use when the user provides a trace ID and asks to debug, investigate, find issues, root-cause errors, understand behavior, or analyze quality. Triggers on "analyze this trace", "what went wrong with this trace", "debug trace", "investigate trace", "why did this trace fail", "root cause this trace".
The single interface for building, improving, and debugging exo workflows. Routes to one of three intents. BUILD takes a rough idea, or an agent template slug from the ghostsecurity.ai catalog, through interrogation, assessment, resource creation in dependency order, and one manual run, then hands off. IMPROVE runs the observe-and-iterate loop over recent runs, proposing and applying changes behind two gates. DEBUG diagnoses one failed or misbehaving run by walking the dependency graph of everything it touched. Use whenever the user wants to create a new exo workflow, iterate on or improve an existing one, or find out why a specific run failed.
Add AgentMail tools to agent frameworks with the TypeScript or Python AgentMail Toolkit. Use for Vercel AI SDK, LangChain, OpenAI Agents SDK, LiveKit Agents, or MCP adapters; do not use for direct mailbox operations, raw SDK implementation, CLI usage, or MCP client setup.
World-class prompt engineering skill for LLM optimization, prompt patterns, structured outputs, and AI product development. Expertise in Claude, GPT-4, prompt design patterns, few-shot learning, chain-of-thought, and AI evaluation. Includes RAG optimization, agent design, and LLM system architecture. Use when building AI products, optimizing LLM performance, designing agentic systems, or implementing advanced prompting techniques.
Discover and install related skills from inference.sh skill registry. Helps find complementary skills for your AI workflow. Use for: skill discovery, workflow expansion, capability exploration. Triggers: related skills, find skills, skill discovery, complementary skills, expand workflow, more capabilities, similar skills, skill suggestions
Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI). Creates an epic with child beads for each user story. Use when you have a PRD and want to use ralph-tui with beads-rust as the task source. Triggers on: create beads, convert prd to beads, beads for ralph, ralph beads, br beads
Optimizes or restructures CLAUDE.md/AGENTS.md with progressive disclosure and zero information loss. Use when the user asks to optimize, audit, 精简/瘦身/重构, or split instruction files, asks for their best practices (最佳实践), sees Memory files taking a large share of /context, reports rules in instruction files being ignored, or a task starts moving instruction sections. Not for generic task drift unless instruction files are in scope; not for moving memory entries into docs (use claude-code-ops-router).
Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you need role-based agent collaboration with memory, or for production workflows requiring sequential/hierarchical execution. Built without LangChain dependencies for lean, fast execution
Route audio, video, transcript, subtitle, and edit-prep requests into the right media-understanding workflow before execution. Use this when the user wants transcription, subtitle generation, beat mapping, B-roll planning, or edit-ready outputs and the first question is which skill and model chain should run.
Retrieves MLflow traces using CLI or Python API. Use when the user asks to get a trace by ID, find traces, filter traces by status/tags/metadata/execution time, query traces, or debug failed traces. Triggers on "get trace", "search traces", "find failed traces", "filter traces by", "traces slower than", "query MLflow traces".
Creates and improves portable Agent Skills with a validator, routing scenarios, and evidence-based keep, cut, merge, or retire decisions. Use when asked to “write a skill”, “update all skills”, “audit my SKILL.md”, “remove redundant instructions”, or fix skill triggering.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.