Route CEO-first multi-window work into owner-led role loops. Use for 总控/CEO、架构/CTO、内容主编、角色派发与复用、模型路由、来源窗口回调、role-windows 台账、skill 命中统计或 multi-window loop engineering。
中文简介正在准备中。当前显示原文说明。
Dirtytrii/codex-skills112026年10月9日 更新
免费在 GitHub 公开
hatch-pet
Explicit compatibility adapter for repairing existing v1 Codex pets with 8x9 atlases. Not for new pets or v2/8x11 packaging; use the installed v2-capable pet skill for those tasks.
中文简介正在准备中。当前显示原文说明。
查看安装方法包含的文件（15）
- SKILL.md1.3 KB
- agents/openai.yaml258 B
- LICENSE.txt10.5 KB
- references/animation-rows.md1.7 KB
- references/codex-pet-contract.md788 B
- references/legacy-v1-workflow.md36.1 KB
- references/qa-rubric.md4.1 KB
- scripts/compose_atlas.py5.6 KB
- scripts/derive_running_left_from_running_right.py5.0 KB
- scripts/extract_strip_frames.py13.6 KB
- scripts/inspect_frames.py8.8 KB
- scripts/make_contact_sheet.py2.9 KB
- scripts/prepare_pet_run.py32.1 KB
- scripts/render_animation_previews.py2.5 KB
- scripts/validate_atlas.py5.3 KB
SKILL.md（原文）
安装前可以查看交给 AI 代理的指令内容。
Legacy v1 Pet Compatibility
This packaged entrypoint preserves the old v1 pipeline without competing with the current v2 pet skill.
- Confirm the user explicitly requested v1 compatibility and inspect the existing pet manifest/atlas. Do not infer v1 from this skill's name or from a missing version field alone.
- For new pets, v2, 8x11 or 16-direction work, use an available v2-capable pet skill identified by its full location/provider. Never recursively invoke this same adapter. If no such skill is available, stop with the missing capability; do not silently produce v1 or install a dependency.
- Only for confirmed v1 work, load the retained v1 workflow. Keep all scripts relative to this skill root. Preserve original assets and write a separate output until validation passes.
- Report the actual atlas dimensions, manifest version (including absent for a legacy artifact), checks performed and compatibility limits. Never label v1 output as v2-compatible.
This compatibility package does not vendor or claim to validate the v2 implementation. New v2 work remains owned by the selected v2 skill and its tests.
评价
还没有评价。欢迎分享你的使用感受。
评论
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
同一仓库的技能
Read-only first workflow for diagnosing application incidents by collecting service, log, network, configuration, and functional evidence before proposing any fix.
中文简介正在准备中。当前显示原文说明。
Dirtytrii/codex-skills112026年10月9日 更新
Run user-authorized black-box web security tests and evidence-based reports. Use for 黑盒安全测试、渗透测试、数据泄露、未授权访问、公开 JS/API、登录爆破防护、CORS 或安全响应头检查。
中文简介正在准备中。当前显示原文说明。
Dirtytrii/codex-skills112026年10月9日 更新
Choose the narrowest reliable browser surface across Codex Browser, signed-in Chrome, Playwright CLI, and platform scripts. Use for browser automation, logged-in workflows, UI inspection, screenshots, form filling, publish previews, or frontend QA.
中文简介正在准备中。当前显示原文说明。
Dirtytrii/codex-skills112026年10月9日 更新
提议并执行 rubric 或 bucket 升级。两种模式：**完整 rubric bump**（最高风险动作，5 步强制 + 跨模型审核）和 **--bucket-only 轻量重校**（只换 bucket 边界，不动 rubric 公式）。**Phase 2 强制走 cheat-score-blind sub-agent 给校准池重打分**——不接受 self-scored fallback。触发词："升级 rubric"/"bump rubric"/"更新公式"/"我想加一个维度"/"调整权重"/"重校桶"/"recalibrate bucket"。
中文简介正在准备中。当前显示原文说明。
Dirtytrii/codex-skills112026年10月9日 更新
初始化 cheat-on-content 内容校准工作区。仅在用户明确开始该工作流，或其子 skill 确认缺少 .cheat-state.json 时使用；不响应一般项目初始化、安装诊断或 Codex 首次会话。
中文简介正在准备中。当前显示原文说明。
Dirtytrii/codex-skills112026年10月9日 更新