Loading...
Loading...
Found 508 Skills
Connect Codex CLI as an MCP server — giving you codex_run and codex_review as native tool calls instead of black-box bash commands. codex_run covers six modes: explore (broad codebase discovery), inspect (targeted read-only and injected-context follow-up), build (write/edit code), debug (reproduce→diagnose→fix→verify), test (write/run tests), research (web search only). codex_review runs independent code review in an isolated thread. Each mode bakes in task-specific instructions so Codex performs well per task type. Use this skill whenever the user mentions: "set up codex MCP", "connect codex to claude", "codex MCP server", "install codex tools", "configure codex integration", or wants Codex available as native tools in any agent. Distributed via `npx skills add` — no global install needed.
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.
Multi-instance (Multi-Agent) orchestration workflow for deep research: Split a research goal into parallel sub-goals, run child processes in the default `workspace-write` sandbox using Codex CLI (`codex exec`); prioritize installed skills for networking and data collection, followed by MCP tools; aggregate sub-results with scripts and refine them chapter by chapter, and finally deliver "finished report file path + key conclusions/recommendations summary". Applicable to: systematic web/data research, competitor/industry analysis, batch link/dataset shard retrieval, long-form writing and evidence integration, or scenarios where users mention "deep research/Deep Research/Wide Research/multi-Agent parallel research/multi-process research".
This is intended for use when OpenSpec workflows require dependency-aware parallel subagents that are compatible with OPSX commands, legacy OpenSpec commands, and Codex CLI prompt aliases.
Debate implementation plans between Claude Code and Codex CLI. After Claude Code creates a plan, invoke this skill to have Codex review it. Both AIs debate through multiple rounds until reaching full consensus before implementation begins.
OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex".
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing. Use when Codex needs to create a new local plugin, add optional plugin structure, or generate or update repo-root `.agents/plugins/marketplace.json` entries for plugin ordering and availability metadata.
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
Professional code review with auto CHANGELOG generation, integrated with Codex AI
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Send SMTP email notifications after Codex completes a task. Use when one Codex or Claude run is finished, or when you need to notify on task completion with device name, project name, status, and summary via email.