Loading...
Loading...
Found 518 Skills
Use the turl CLI to resolve Amp, Codex, Claude, or OpenCode thread URIs and print thread content in markdown or raw records.
Create event-driven hooks for AI coding agent automation (Claude Code, Codex CLI). Configure hook events in settings or frontmatter, parse stdin JSON inputs, return decision-control JSON, and implement secure hook scripts.
Adversarial code review using the opposite model. Spawns 1–3 reviewers on the opposing model (Claude spawns Codex, Codex spawns Claude) to challenge work from distinct critical lenses. Triggers: "adversarial review".
Multi-agent swarm orchestration where AI agents spawn, coordinate, and self-organize into collaborative teams. Use when running parallel AI agent tasks, orchestrating multi-agent workflows across Claude Code / Codex / Cursor / custom agents, isolating agent workspaces via git worktrees, tracking task dependencies across agents, or running autonomous experiments. Triggers on: clawteam, agent swarm, spawn agents, multi-agent team, agent orchestration, parallel agents, agent coordination, swarm intelligence, agent spawn, clawteam spawn, agent worktree, agentic team, ml agent experiments, autonomous agents, agent team.
Interactively guide users through configuring ZenMux Base URL, API endpoint, API Key, and model settings for any tool or SDK. Use this skill whenever the user wants to SET UP, CONFIGURE, or CONNECT a tool to ZenMux — including questions like "how do I set up ZenMux in Cursor", "what's the base URL", "how to configure Claude Code with ZenMux", "endpoint for Anthropic API", "help me fill in the API settings". Trigger on: "configure", "setup", "set up", "base url", "endpoint", "api key", "接入", "配置", "设置", "base url 填什么", "怎么填", "怎么接入", "怎么配置", "API 地址", "接口地址". Also trigger when users mention a tool name (Cursor, Cline, Claude Code, Cherry Studio, Open-WebUI, Dify, Obsidian, Sider, Copilot, Codex, Gemini CLI, opencode, etc.) together with ZenMux in a configuration context. Treat the user as a first-time user and guide them step by step. Do NOT trigger for usage queries, documentation lookups, or general product questions — use zenmux-usage or zenmux-context instead.
Multi-platform, multi-channel notification skill for AI code agents. Sends notifications (sound, macOS alert, Telegram, Email, Slack, Discord) when the agent needs user interaction or completes a task. Supports Claude Code, GitHub Copilot CLI, Cursor, Codex, and Aider.
Track Clawdbot AI model usage and estimate costs. Use when reporting daily/weekly costs, analyzing token usage across sessions, or monitoring AI spending. Supports Claude (opus/sonnet), GPT, and Codex models.
Consult external AIs (Gemini 2.5 Pro, OpenAI Codex, Claude) for second opinions. Use for debugging failures, architectural decisions, security validation, or need fresh perspective with synthesis.
Inspect an existing repo and generate OpenEditor onboarding config for it. Use when Codex needs to make a project OpenEditor-compatible by inferring framework or platform from the file tree, creating or updating `.logic-editor.json`, creating `oe-swift.json` for iOS or SwiftUI projects, or explaining which config fields still need manual confirmation.
Convert a web URL into cleaned Markdown with deterministic routing. Use when Codex needs to read article-like content from links and should apply source-aware fetch strategies: default to r.jina.ai for general pages (including X/Twitter), use defuddle.md for YouTube links, and use browser-impersonated extraction for WeChat/Zhihu/Feishu pages with Mozilla Readability cleanup.
Integrate markstream-react into a React 18+ or Next app. Use when Codex needs to add the React renderer, import CSS correctly, choose between `content` and `nodes`, keep Next client boundaries safe, convert renderer overrides, or prepare a repo for `react-markdown` migration.
Compact SGLang torch-profiler triage skill. Use when Codex should inspect an existing `trace.json(.gz)` or profile directory, trigger `sglang.profiler` against a live server, and return one compact report with kernel, overlap-opportunity, and fuse-pattern tables. Single-trace triage is enough for quick diagnosis; mapping+formal two-trace triage gives stronger overlap conclusions.