菜单
OpenAI Codex CLI integration for code analysis and editing. Use when the user mentions "codex", "codex cli", "codex exec", "codex resume", "ask codex", or wants to delegate code analysis, refactoring, or automated editing to the Codex CLI. Requires the `codex` binary on PATH.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Security-inspect an AI agent skill (your own or a third party's) with the skillspector CLI, then deliver a plain-English verdict report in chat (safe / caution / do-not-install, threat breakdown, top findings to check, file hotspots). Use whenever you want to vet, scan, audit, or sanity-check a skill before installing or trusting it, point at a skill repo/folder/zip and ask "is this safe?", say "inspect this skill", "scan this skill", "check this skill for malware", "skillspector", or share a GitHub link to a skill/agent and want to know the risk. Also use to re-read confusing skillspector output.
Security-inspect an AI agent skill (your own or a third party's) with the skillspector CLI, then deliver a plain-English verdict report in chat (safe / caution / do-not-install, threat breakdown, top findings to check, file hotspots). Use whenever Ossie wants to vet, scan, audit, or sanity-check a skill before installing or trusting it, points at a skill repo/folder/zip and asks "is this safe?", says "inspect this skill", "scan this skill", "check this skill for malware", "skillspector", or shares a GitHub link to a skill/agent and wants to know the risk. Also use to re-read confusing skillspector output.
Execute GitHub issues one at a time as vertical slices — fetch, branch, TDD, verify, PR, then the next. Use when the user says "ship issue", "resolve
Unified 3D printing pipeline for Bambu Lab printers. USE WHEN user says: print, 3d print, slice, slice this, make me, design a part, model this, STL, 3MF, MakerWorld, browse models, find me a model, printer status, check printer, what's printing, prepare for printing, generate 3MF, fit on one plate, multi-object plate, storage, organizer, mount, holder, bracket, gridfinity, or provides STL files, photos of things to design, or MakerWorld links. Covers design with OpenSCAD MCP, browsing MakerWorld with agent-browser, slicing STL to 3MF with the bundled OrcaSlicer-backed CLI, multi-plate arrangement, and printer control with Bambu MCP. This is the only skill for 3D-printing related work.
USE WHEN: dogfood, QA, exploratory test, find issues, bug hunt, test this app/site/platform, or review the quality of a web application. Systematically explores a web app in a real browser, finds bugs and UX issues, and produces a structured report with full reproduction evidence (step-by-step screenshots, repro GIFs when available, and detailed repro steps) so findings can be handed straight to the responsible team.
USE WHEN: check/audit/update/improve/fix CLAUDE.md or AGENTS.md, CLAUDE.md maintenance, AGENTS.md review, project memory optimization, agent documentation. Audits agent instruction files against modern harness engineering principles (leanness, discoverability, anti-staleness), then applies targeted improvements after approval.
| name | ask-codex |
| description | OpenAI Codex CLI integration for code analysis and editing. Use when the user mentions "codex", "codex cli", "codex exec", "codex resume", "ask codex", or wants to delegate code analysis, refactoring, or automated editing to the Codex CLI. Requires the `codex` binary on PATH. |
Wraps the OpenAI Codex CLI (codex exec, codex resume) with explicit model + reasoning + sandbox selection so Claude Code can hand off work to Codex when its strengths fit (long-running agentic edits, GPT-5.x reasoning, network-enabled tasks).
Prerequisite: the codex CLI must be installed and authenticated on the host. Verify with codex --version before the first run.
AskUserQuestion) which model to run (gpt-5.4 (Recommended — 25% faster, most capable agentic coding model), gpt-5.3-codex, or gpt-5.4-nano) AND which reasoning effort to use (high, medium, or low) in a single prompt with two questions.--sandbox read-only unless edits or network access are necessary.-m, --model <MODEL>--config model_reasoning_effort="<high|medium|low>"--sandbox <read-only|workspace-write|danger-full-access>--full-auto-C, --cd <DIR>--skip-git-repo-check--skip-git-repo-check.codex exec --skip-git-repo-check resume --last via stdin. When resuming don't use any configuration flags unless explicitly requested by the user (e.g. if the user specifies the model or the reasoning effort when requesting to resume a session). Resume syntax: echo "your prompt here" | codex exec --skip-git-repo-check resume --last 2>/dev/null. All flags have to be inserted between exec and resume.2>/dev/null to all codex exec commands to suppress thinking tokens (stderr). Only show stderr if the user explicitly requests to see thinking tokens or if debugging is needed.| Use case | Sandbox mode | Key flags |
|---|---|---|
| Read-only review or analysis | read-only | --sandbox read-only 2>/dev/null |
| Apply local edits | workspace-write | --sandbox workspace-write --full-auto 2>/dev/null |
| Permit network or broad access | danger-full-access | --sandbox danger-full-access --full-auto 2>/dev/null |
| Resume recent session | Inherited from original | echo "prompt" | codex exec --skip-git-repo-check resume --last 2>/dev/null (no flags allowed) |
| Run from another directory | Match task needs | -C <DIR> plus other flags 2>/dev/null |
codex command, immediately use AskUserQuestion to confirm next steps, collect clarifications, or decide whether to resume with codex exec resume --last.echo "new prompt" | codex exec resume --last 2>/dev/null. The resumed session automatically uses the same model, reasoning effort, and sandbox mode from the original session.codex --version or a codex exec command exits non-zero; request direction before retrying.--full-auto, --sandbox danger-full-access, --skip-git-repo-check) ask the user for permission using AskUserQuestion unless it was already given.AskUserQuestion.