yfge

Use when turning architecture, layering, ownership, dependency direction, schemas, structural metrics, quality thresholds, baselines, allowlists, or generated quality snapshots into repository checks.

Use when evaluating repository agent-readiness, mapping harness roles, choosing the next smallest improvement, or designing and reconciling agent entrypoints such as AGENTS.md, CLAUDE.md, GEMINI.md, Cursor rules, or GitHub instructions.

Use when designing or reconciling design docs, task boards, external trackers, execution plans, delivery records, handoffs, review evidence, task-to-change traceability, or repository commit-coupling policy.

Use when connecting observed behavior, logs, metrics, request IDs, run IDs, screenshots, traces, external dependency results, or artifacts into a runtime evidence loop.

Use when designing repository validation commands, doctor scripts, test matrices, JSON or JUnit outputs, CI gates, smoke checks, or harness command surfaces.

从观点摘要和原始素材生成可发布的文章。支持多种文体（博客、知乎回答、公众号、技术文章），自动应用防 AI 写作规则。适用于：直播内容二次创作、观点输出为文章、素材整合成稿、任何"有料但还没成文"的场景。

从长文本（直播文稿、会议记录、播客转录、文章）中提炼核心观点、金句、争议点和行动项。输出结构化的观点摘要，可直接供 article-forge 等下游 skill 使用。适用于：直播回放分析、会议纪要提炼、长文精读、内容策划前的素材整理。

从长视频（直播回放、会议录像、播客）中批量生成短视频切片。基于转写文稿精确定位观点边界，自动去除静音卡顿和口吃，输出音画同步的短视频。适用于：直播切片、会议精华提取、短视频二创、播客精彩片段。

视频内容全链路处理。一个视频进去，文字稿+观点摘要+短视频切片+可发布文章全出来。串联 video-to-text → insight-extractor → video-clipper → article-forge 四个 skill 的完整流水线。适用于：直播回放、播客、会议录像的一站式内容加工。

视频/音频转文字稿。从视频文件中提取音频，用 whisperX 进行语音识别、时间戳对齐和说话人分离，输出带时间戳和说话人标签的文字稿。适用于：直播回放转写、会议录音转文字、播客转录、任何视频/音频转文稿的场景。

Backend validation workflow for ai-video-studio. Use when changing FastAPI endpoints, services, repositories, models, migrations, prompts, task orchestration, or when diagnosing pytest failures. Chooses between quick, full, targeted, and diagnostic backend checks while treating AGENTS.md, ai-pic-backend/TESTING_GUIDE.md, ai-pic-backend/pytest.ini, and ai-pic-backend/tests/README.md as the source of truth.

Frontend validation workflow for ai-video-studio. Use when changing Next.js pages, components, hooks, API client code, route guards, auth flows, or when deciding whether lint, tests, build, and browser verification are required. Chooses between mandatory lint, conditional frontend tests, and risk-driven builds while deferring user-visible flow checks to the MCP E2E skill.

Chrome DevTools E2E workflow for ai-video-studio. Use when a change affects login, frontend/backend integration, AI generation, image or video flows, or any user-visible path that AGENTS.md requires to be verified in a real browser. Reads AGENTS.md for the current validation policy and account, follows the shared validation matrix, captures console and network evidence, and produces an agent_chats-ready Validation section.

知乎盐选故事写作。生成有反转、有吸引力、无 AI 味的短篇付费故事。适用于用户提到盐选、知乎故事、付费故事、写故事、编故事等场景。

知炼 - 将知识库(Markdown博客)智能转化为知乎回答并自动发布。支持搜索热点问题、匹配知识库、撰写文章、自动发布、质量审核、回存知识库的完整闭环。

Search, discover, and install OpenClaw agent skills from multiple registries. Use when: user asks "find a skill for X", "is there a skill that can...", "how do I do X" (where X might have an existing skill), wants to browse available skills, or asks to install/add a skill. Also triggers on "search skills", "explore skills", "what skills exist for...", or "extend capabilities".

Use when the user asks Codex to work with Feishu or Lark docs, notifications, Bitable records, or Wiki knowledge bases.