Use Agent Pulse to inspect local AI-agent activity across Hermes, Claude Code, Codex, DeepSeek, OpenClaw, Copilot, Aider, Qwen, OpenCode, Goose, Cursor,…
Updated 2026-09-12 02:30:48 +08:00
Create Mermaid diagrams (flowchart, sequence, class, ER, state, C4, architecture) from text or source code. Default for GitHub wiki. Use when asked to create a…
Updated 2026-09-12 02:28:26 +08:00
Create and extend complete visual brand systems through the Higgsfield CLI and bundled deterministic local tooling: palettes, SVG logo marks, typography,…
Updated 2026-09-12 01:47:01 +08:00
Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (`higgsfield website …`). Each is a React 19 + TanStack Start SSR app in one…
Updated 2026-09-12 01:46:45 +08:00
UI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages,…
Updated 2026-09-12 01:34:44 +08:00
飞书幻灯片：创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面（创建、删除、读取、局部替换）。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时，也应直接使用本 skill，不要因为域名不是飞书而回退到…
Updated 2026-09-12 01:26:20 +08:00
飞书电子表格：创建和操作电子表格。支持创建表格、管理工作表与行列结构（增删/合并/调整尺寸/隐藏/冻结）、读写单元格（值/公式/样式/批注/单元格图片）、查找替换、多操作批量更新，以及图表、透视表、条件格式、筛选器、迷你图、浮动图片等对象的创建与维护。当用户需要创建电子表格、管理工作表、批量读写或编辑数据、统计汇总与可…
Updated 2026-09-12 01:24:08 +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 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
Compress a memory file such as CLAUDE.md or a todo list into caveman format to save input tokens, keeping a readable backup. Trigger: /caveman-compress.
Updated 2026-09-12 01:16:19 +08:00