仅在用户显式调用 `$deep-research` 时,用 Codex CLI 子任务完成多来源深度调研并综合成带出处的报告。不用于单次查证或已给定材料的总结。
Idioma do texto original: chinês
Copie este prompt para o assistente de IA que você usa.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/feiskyer/codex-settings.Carregando o README do repositório…
Mostrando 12 de 12 skills coletadas.
仅在用户显式调用 `$deep-research` 时,用 Codex CLI 子任务完成多来源深度调研并综合成带出处的报告。不用于单次查证或已给定材料的总结。
Idioma do texto original: chinês
Investigate or fix a GitHub issue by number or URL. Keep investigation-only requests read-only.
Idioma do texto original: inglês
仅当用户显式调用 `$grill-me`,或明确要求"追问我""挑战这个方案""拷打这个设计"时使用。逐问逐答检验关键假设与取舍,默认在对话中交付;仅按要求维护术语表和 ADR。
Idioma do texto original: chinês
仅当用户显式调用 `$handoff`,或明确要求生成会话交接文档时使用。将当前对话压缩为脱敏、可执行的交接文档,供下一个 agent 接续工作;不要自动触发。
Idioma do texto original: chinês
Generate, edit, or composite images with Gemini/Nanobanana. Default for image requests without a named provider; do not override a different provider the user chose.
Idioma do texto original: inglês
把尚有关键取舍的功能或系统想法收敛为设计。用于用户要求讨论方案或需求尚未明确时;不用于 bug 修复、配置修改或照已有方案实现。
Idioma do texto original: chinês
Delegate a task to the Claude Code CLI, typically a headless `claude -p` run. Use when the user wants the work executed through Claude Code rather than answered inline.
Idioma do texto original: inglês
Review a GitHub pull request by number or URL for evidence-backed defects. Not for reviewing local uncommitted changes.
Idioma do texto original: inglês
Generate or edit images when the user names OpenAI, GPT Image, or a gpt-image model. Use the default image skill when no provider is named.
Idioma do texto original: inglês
Generate images when the user names MiniMax or image-01/image-01-live. Use the default image skill when no provider is named.
Idioma do texto original: inglês
Simplify existing code for clarity and maintainability without changing behavior. Use when asked to clean up or simplify code, especially recent changes.
Idioma do texto original: inglês
Extract subtitles or a transcript from a YouTube URL and save normalized timestamped text locally. Use when the user wants the spoken content of a YouTube video as text.
Idioma do texto original: inglês
Arquivo de origem do README: README.md
Ler o README original