Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing…
Updated 2026-09-12 01:23:15 +08:00
飞书多维表格(Base)操作:建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式(BaseApp/AppMode 页面与组件)、Workspace 目录、workflow、角色权限、模板中心(多维表格模板分类/列表/搜索);遇到…
Updated 2026-09-12 01:23:09 +08:00
飞书云文档(Docx / Wiki)内容操作:读取、创建、编辑文档,插入或下载图片附件,以及操作思维笔记。用户提供文档 URL/token(包括 doubao.com 的 /docx/、/wiki/)时使用;按 URL 路径/token 而非域名路由。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走…
Updated 2026-09-12 01:23:00 +08:00
Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly…
Updated 2026-09-12 01:22:43 +08:00
Rigor Train skill for deep learning research repositories. Use when a documented or selected training command should be run conservatively for startup…
Updated 2026-09-12 01:22:22 +08:00
Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape…
Updated 2026-09-12 01:22:15 +08:00
Rigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly…
Updated 2026-09-12 01:22:06 +08:00
Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction. Use when the user wants an end-to-end, minimal-trustworthy flow…
Updated 2026-09-12 01:21:59 +08:00
Rigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model…
Updated 2026-09-12 01:21:47 +08:00
Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates. Use when the researcher has chosen the task family,…
Updated 2026-09-12 01:21:38 +08:00
Rigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment,…
Updated 2026-09-12 01:21:27 +08:00
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke…
Updated 2026-09-12 01:21:17 +08:00
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common…
Updated 2026-09-12 01:21:08 +08:00
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical…
Updated 2026-09-12 01:20:53 +08:00
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is…
Updated 2026-09-12 01:20:33 +08:00
Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile…
Updated 2026-09-12 01:20:28 +08:00
Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate…
Updated 2026-09-12 01:20:21 +08:00
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then…
Updated 2026-09-12 01:20:12 +08:00
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained…
Updated 2026-09-12 01:20:02 +08:00
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography,…
Updated 2026-09-12 01:19:55 +08:00