В каталоге 183 730 навыков в 14 категориях.
Inverted orchestration—Codex CLI acts as CTO (planning and reviewing), Claude Code executes with native tools. Use when...
Run an automated codex⇄Claude debate to consensus — no round cap, no deadlock exit. Two explicit subcommands. `review` (...
Run an automated code-review debate between the codex CLI (reviewer) and a Claude subagent (author) on the current diff,...
Use for systematic debugging and root cause analysis with Codex. Triggers on "codex debug", "codex root cause", "have co...
Use when a task is ambiguous, underspecified, likely to branch into multiple implementations, or explicitly asks for unk...
Delegate a coding task to the OpenAI Codex CLI as a background implementer, then review its diff and land it yourself. U...
This skill should be used when deciding whether to "delegate to codex", "hand off to codex", "use codex for this", or wh...
Use when product, UI, documentation, or workflow decisions need a lightweight human-readable source of truth before impl...
Use for DESIGN.md visual identity contracts; author, scaffold, lint, diff, and export design contracts with the upstream...
Modern design vocabulary with palettes, typography, layouts, animations, and composition principles. Prevents generic ou...
Design, generate, repair, validate, package, install-test, and privacy-audit V2 animated pets for Codex Desktop from tex...
Build, upgrade, package, and validate standalone Windows desktop-pet applications from approved transparent sprite atlas...
Design, implement, validate, package, and privacy-audit reversible themes for Codex Desktop, including visual concept tr...
Orchestrate multi-agent coding tasks via Codex DevFleet — plan projects, dispatch parallel agents in isolated worktrees,...
Consult Codex CLI (OpenAI) to get a second opinion on difficult problems. Use when facing complex debugging, architectur...
Iterative non-code discussion between the local agent and Codex CLI on any open-ended topic: diet, fitness, writing, dec...
Use OpenAI Codex CLI as a discussion partner to verify ideas, evaluate plans, and improve quality. Automatically trigger...
Mandatory dispatch preflight before any subagent delegation. Use before the first child-work call in every task, and whe...
Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelit...
Map code changes to candidate documentation updates using git diff and mapping rules. Use during docs steps to report im...
Check the Codex CLI, its login, quota and model list, git and the runner's folders (the runner's --doctor --read-only),...
Diagnose OpenAI Codex CLI, Desktop, IDE, skill, plugin, MCP, session, configuration, authentication, network, storage, a...
Analyze local Codex session telemetry and produce privacy-safe efficiency reports with actionable workflow recommendatio...
Use for documents, reports, memos, guides, academic papers, or formal text that needs clear structure, reliable tone, fo...
Apply layered domain routing for frontend, backend, mobile, debugging, security, and specialized engineering concerns. U...
Execute OpenAI Codex CLI prompts and return results
Use when running Codex workers or validators non-interactively through codex exec with evidence. Triggers:
Execute development tasks using OpenAI Codex CLI for code generation, refactoring, feature implementation, and bug fixes...
Run autonomous task execution using the codex CLI. Use when the user asks to "codex exec", "run codex exec", "execute a...
Launch focused Codex subagents via `codex exec` (single, resumed, or batched), capture outputs to files, and aggregate r...
Create or edit Codex execpolicy .rules files (allow/prompt/forbid commands, define prefix_rule patterns, add match/not_m...
Run verification checks before completion using lint/test, security scanning, and optional bundle plus tech debt analysi...
Use when Codex should explore a fuzzy, underspecified, or stubborn problem through bounded rounds rather than finish a k...
Apply Fable-inspired discipline to Codex work: inspect first, track goals and findings, ground conclusions in evidence,...
Use when Codex feels slow, bloated, or heavy after heavy use and the user wants local Codex state hygiene, handoff disci...
Use when Codex feels slow, bloated, or heavy after heavy use. Provides safe session hygiene, archive strategy, and hando...
Use when designing or redesigning a web UI; select fast, prototype, or studio from the requested scope.
Use when implementing web UI in React, Next.js, Tailwind, CSS, or GSAP against an approved design, fast-path brief, or p...
Git-aware development workflows with Codex CLI including intelligent commits, PR automation, branch management, and diff...
Automated git commit with CI/CD gate, GPG signing, and conventional commits
Use when implementation needs isolation from the current workspace; creates git worktrees with safe directory selection...
Run codex goals.
Orchestrate read-only Codex research in any mode, or one to eight Codex agents to implement approved plans from Claude C...
Delegiere Aufgaben an OpenAI Codex CLI im Headless-Mode. Nutzt ChatGPT Subscription (KEIN API Key). Nur Workspace-Zugrif...
排查 Codex/Hermes 的 playwright-ext 从“可用”变为不可用(Extension connection timeout)时的最小闭环流程。先判定 bridge 层,再判定 token/同步链路,避免误把问题归因于“...
Ingest Codex CLI conversation/session history into Obsidian as distilled knowledge. Use for importing or mining ~/.codex...
当 Codex Desktop 在切换 ChatGPT 账号、API Key、自定义 provider、model_provider 或 model 后,本地历史记录消失、旧对话缺失、项目历史看起来移动、需要检查/同步/备份/恢复/删除归档...
Run the great_cto controlled Codex lifecycle with controller-owned writes, verifier evidence, human gates and optional a...
Generate or edit raster images (photos, illustrations, mockups, hero images, product shots, bitmap icons, transparent cu...
Personal-only bridge that delegates raster image generation to Codex's built-in $imagegen via codex exec.
Generate or redesign raster images (PNG mockups, illustrations, photos, UI design polish) from inside Claude Code by dri...
Batch-generate raster images through Codex CLI and its built-in image_gen. Use when the user needs several images at onc...
Ask Codex CLI with its configured model to implement scoped code changes in the current repository, then have Claude ins...
Codex CLI를 sub-agent로 활용하여 실제 구현 작업을 수행합니다. Claude가 작업을 분석/분해하고, Codex가 코드 작성/수정/리팩토링을 담당합니다. "Codex로 구현", "구현해줘", "코드 작...
Use when a broad codebase improvement, UI/UX revamp, release hardening pass, multi-PR cleanup, or "boil the ocean" reque...
Analyze code-change prompts into structured intent JSON with goal, constraints, missing info, normalized prompt, complex...
Invoke OpenAI Codex CLI with the correct configuration for autonomous code generation. Use when you need Codex to genera...
Autonomous issue planning and execution workflow for Codex. Supports batch issue processing with integrated planning, qu...
Use Codex CLI in full-auto mode to fix issues iteratively until tests pass. Autonomous debugging and test-fixing loop wi...
Show the remaining Codex quota on one line (the runner's --limits). Starts one probe app-server for about 1-2 s, with no...
List this Claude session's retained Codex runs (the runner's --list --mine) without touching them or starting any proces...
Pick a CODEX_HOME source and/or an auth.json credential file per tmux-workflow worker so many Codex workers can balance...
Safely inspect, clean, and repair local Codex Desktop project and thread state under $CODEX_HOME or ~/.codex when remove...
Automatically diagnose excessive Codex local SQLite diagnostic log writes and give a concrete fix plan. Use when a user...
Use when work is ambiguous or has multiple viable paths; compares options, assumptions, evidence, tradeoffs, and the bes...
Codex long session, context budget, byte cap, command output protection, needle map, pre-compact raw data, living handof...
Launch, start, monitor, and collect independent Codex subagents (gpt-6-luna at high, xhigh or max; gpt-5.6-sol for small...
Master behavior rules for Codex. Use as the top-priority baseline for request classification, coding quality, dependency...
Use this `codex-mcp` skill to instruct another AI Agent to invoke a tool or execute a workflow on your behalf for the fo...
Run codex MCP plugins.
Use when the user wants to understand, design, or improve Codex itself: hooks, subagents, skills, AGENTS.md or PLANS.md...
Rebuild the canon mirror for a second coding agent (AGENTS.md) after a rules-file version bump: show the changelog delta...
Codex CLI 과거 대화 검색과 장기기억 설정에 사용한다. notify 훅으로 대화 자동 저장, 키워드 태깅, 과거 검색을 제공한다. /mnemo, 므네모, 장기기억, 기억해, 이전에, handoff, 핸드오프,...
Use when an existing Codex task or session ends with “Selected model is at capacity”, “model at capacity”, “server_overl...
Several ChatGPT logins for the Microsoft Store Codex app on Windows. The account list lives in Codex's own avatar menu (...
Use when the user explicitly asks for subagents, parallel agents, delegation, or a team-style split in native Codex; coo...
Comprehensive prompt engineering reference for Codex Opus 4.6. Use this skill whenever you are writing, reviewing, or op...
Coordinate independent work with Codex subagents. Use for requests to orchestrate a task, run a team, or delegate parall...
Authoritative reference for OpenAI Codex CLI's orchestration surface - skills discovery paths, agents/openai.yaml schema...
Orchestrate OpenAI Codex CLI with specialized subagents for code review, debugging, architecture analysis, security audi...
Use this when updating the codex submodule or when patch files in codex-patches/ need to be added, regenerated, or repai...
[CLAUDE CODE ONLY] Leverage Codex CLI for AI peer review, second opinions on architecture and design decisions, cross-va...
Use when the user wants measurable performance optimization, latency/cost/memory/throughput improvement, benchmark-drive...
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference...
Send implementation plan to Codex for critique and validation. Use PROACTIVELY after you produce a non-trivial plan (inc...
Create structured task plan files for complex coding requests. Use during planning phases to write verifiable, dependenc...
Drive the Codex CLI as a benchmark target or dispatched worker. Use when running codex probes, comparing codex postures,...
Use OpenAI Codex from inside Claude Code for code reviews and delegated background tasks.
Use when the user wants to share, install, or migrate Codex skills across machines or teammates (copying ~/.codex/skills...
Use when the user mentions plugin-dev, wants a plugin-dev-like toolkit inside Codex CLI, asks how to start creating skil...
Use when the user asks how to structure Codex skills (folders, SKILL.md, supporting files), wants plugin-dev-like organi...
Use when the user suspects a Codex skill is not triggering, wants to validate SKILL.md frontmatter (name/description), c...
Use when the user needs product-management help for Codex or a Codex-like AI coding product, including product analysis,...
Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or outlines.
从文章/报告/笔记/大纲生成视觉统一的图片型 PPT/PPTX 课件。当用户说"做PPT""课件""幻灯片""演示文稿"时触发。
GPT-Image-2 PPT Generator: converts articles/reports into image-based PowerPoint presentations. Plans outline and visual...
Update the title and body of one or more pull requests.
Tracks project knowledge, decisions, and patterns across sessions
Maintain a minimal, token-aware, verified project memory for Codex repositories. Use when initializing project context f...
Use when asking project status, next priority, sprint health, blockers, deadlines, risk register, or daily brief generat...