Documents skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

record-video

Generate and record gameplay video footage for Cuttle. Use when the user describes an in-game situation and a sequence of moves and wants a video clip of it — e.g. "record a video of…", "make a clip showing…", "generate footage of…", "film a scenario where…". Optionally organizes the clip under a named topic/category (the tutorial video it's for). Translates the description into a Cypress test in tests/e2e/specs/playground/videoPlayground.spec.js, marks it .only(), clears every other .only(), runs Cypress headless with video, and saves a named .mp4 to tests/e2e/videos/.

196 repo starsObserved in 1 repos
Documents
GitHub

imagegen-scene-ppt

面向中文 toB 商业汇报的 PPT 工作流路由：新做汇报先生成图片型 PPT；已有图片页或生成后的页图，再按目标拆解为元素重组 PPTX、semantic visual-replica 或 SVG。适用于图片页转可编辑 PPT、v4/v5 元素重组、图片型 PPT 结构重建。

195 repo starsObserved in 1 repos
Documents
GitHub

og-screenshot

Capture website screenshots sized precisely for OG images (1200x630) using chrome-devtools-mcp.

195 repo starsObserved in 1 repos
Documents
GitHub

reviewer-simulator

Simulate a strict academic reviewer and produce a manuscript risk report without editing the draft. Use when the user asks to act as a reviewer, find weaknesses before submission, inspect evidence gaps, check overclaims, evaluate manuscript readiness, combine advisor notes or meeting minutes into revision priorities, or generate a 审稿人模拟检查 report.

195 repo starsObserved in 1 repos
Documents
GitHub

skill-optimization-guide

技能文档（SKILL.md）优化指南。当用户要优化某个技能包的 SKILL.md 文档结构、精简行数、消除冗余、抽取 references 时触发。适用于技能包超过 200 行需要瘦身、多章节重复需要合并、完整代码需要抽取到 references/samples 等场景。不适用于：技能包的功能开发、运行时测试、静态诊断评分（应使用 skill-static-diagnosis）。

194 repo starsObserved in 2 repos
Documents
GitHub

fal-audio

Generate AI audio using Fal.ai audio models. Use when you need to: (1) convert text to natural speech, (2) create podcast-style audio content, or (3) clone voices from audio samples.

194 repo starsObserved in 1 repos
Documents
GitHub

fal-video

Generate AI videos using Fal.ai Seedance models. Use when you need to: (1) animate images into short videos, (2) create motion from still photos, or (3) generate high-quality video content from images.

194 repo starsObserved in 1 repos
Documents
GitHub

kling-video

Generate AI videos using Kling video generation models. Use when you need to: (1) create videos from text prompts, (2) animate images into videos, (3) transform existing videos with AI, or (4) create AI avatar videos with speech.

194 repo starsObserved in 1 repos
Documents
GitHub

large-file-write

解决 heredoc 或 shell 命令写入大文件内容被截断的问题。优先使用 agent 结构化文件写入工具；超大文件可用该工具创建 Node.js payload 后执行。适用于需要可靠写入超过 100 行文本文件时。

194 repo starsObserved in 1 repos
Documents
GitHub