Loading...
Loading...
Found 480 Skills
Guide for creating Agent Skills: structure, best practices, and SKILL.md format for Claude Code, Codex, Gemini CLI, and other AI agents.
Clean AI refusal responses from Codex CLI, Claude Code, and OpenCode session files, and inject CTF/pentest prompts to reduce refusals.
Prepare, publish, and automate releases for npm packages, especially scoped packages that need package.json fixes, publish scripts, npm dry-run checks, `.env`-managed `NPM_TOKEN` handling, npm org token setup, GitHub Actions secrets, semantic-release workflows, npmjs.org publishing, GitHub Packages publishing, GitHub Releases, or release troubleshooting. Use when Codex needs to make a repo publish-ready, verify what npm will ship, configure automated publishing, or diagnose failures involving package contents, registry auth, 2FA, tokens, tags, changelogs, GitHub Actions, or semantic-release.
Design a conversion loop for a one-person company from reach to lead capture to purchase. Use when Codex needs to explain conversion concepts when needed, verify MVP prerequisites, ask one question at a time, present multiple conversion-path options, and write user-confirmed outputs into `opc-doc/`.
Find, evaluate, and download low-level common standard CAD parts from step.parts, such as screws, bolts, nuts, washers, bearings, standoffs, electronics parts, motors, connectors, and other off-the-shelf components. Use when Codex needs to search the hosted step.parts catalog, resolve fuzzy part names, standards, aliases, or dimensions, choose a matching part, fetch a canonical .step file, verify checksums, or use the step.parts API/OpenAPI/catalog endpoints for standard part discovery.
Create, verify, repair, and close durable Codex goals with measurable outcomes, evidence gates, plan templates, blocker handling, completion audits, and goal-backed workflow repair.
Cheat sheet + workflow for launching interactive coding-agent CLIs (Claude Code, Gemini CLI, Codex CLI, Cursor CLI, and pi itself) via the interactive_shell overlay or headless dispatch. Use for TUI agents and long-running processes that need supervision, fire-and-forget delegation, or headless background execution. Regular bash commands should use the bash tool instead.
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".
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.
Operational prompt engineering for production LLM apps: structured outputs (JSON/schema), deterministic extractors, RAG grounding/citations, tool/agent workflows, prompt safety (injection/exfiltration), and prompt evaluation/regression testing. Use when designing, debugging, or standardizing prompts for Codex CLI, Claude Code, and OpenAI/Anthropic/Gemini APIs.
Control interactive terminal applications like vim, git rebase -i, git add -i, git add -p, apt, rclone config, sudo, w3m, and TUI apps. Can also supervise another CLI LLM (cursor-agent, codex, etc.) - approve or reject its actions by pressing y/n at confirmation prompts. Use when you need to interact with applications that require keyboard input, show prompts, menus, or have full-screen interfaces. Also use when commands fail or hang with errors like "Input is not a terminal" or "Output is not a terminal". Better than application specific hacks such as GIT_SEQUENCE_EDITOR or bypassing interactivity through file use.
Rigorously collects and validates all fields needed to produce a complete, unambiguous prompt template for features and bug fixes. The skill asks targeted questions until the template is fully filled, consistent, and ready to paste into a Codex/GPT-5.2 coding session.