Updated 1w ago
by captain-nook
nook_skills
Nook Lab — AI agent skills for various tasks
20 GitHub stars (20)
+7 in 30 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | +2 |
| Oct 8 | 0 |
| Oct 9 | 0 |
| Oct 10 | 0 |
| Oct 11 | 0 |
| Oct 12 | +1 |
| Oct 13 | 0 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
| Oct 17 | 0 |
| Oct 18 | 0 |
| Oct 19 | 0 |
| Oct 20 | 0 |
| Oct 21 | +1 |
| Oct 22 | 0 |
| Oct 23 | 0 |
| Oct 24 | 0 |
| Oct 25 | 0 |
| Oct 26 | 0 |
| Oct 27 | 0 |
| Oct 28 | 0 |
| Oct 29 | 0 |
| Oct 30 | 0 |
| Oct 31 | 0 |
| Nov 1 | +1 |
| Nov 2 | +1 |
| Nov 3 | 0 |
| Nov 4 | 0 |
| Nov 5 | +1 |
- 18 skills (18 skills found in its SKILL.md files)
- 2 forks (2 forks)
- 1w ago last update (Last updated 1w ago)
Install
Skills CLI
npx skills add captain-nook/nook_skills
Asks which skills and agents to install. Just one: npx skills add captain-nook/nook_skills --skill nook-anim — add -g for every project.
Claude Code
git clone https://github.com/captain-nook/nook_skillscp -r "nook_skills/nook-anim" ~/.claude/skills/
Copies the nook-anim skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add captain-nook/nook_skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
nook-anim
代码渲染为主的短视频动画生产 skill。用户要做动画短片、Logo 片头动效、定格动画、手绘/白板讲解动画、火柴人小剧场、MG 动效与数据信息图、水墨/撕纸风短片、口播 B-roll 动画与章节标题卡动画（给教程、科普视频配画面）、歌词 MV 画面，或要求"用代码做视频""不用视频模型做动画"时使用。按内容类型选叙事骨架、按风格卡选技术路线，生图补足角色与场景（本地 ComfyUI Qwen Image 2.1），配乐走 MiniMax Music3 并由代码对拍，最后用 nookanim 引擎逐帧渲染成片。不用于单纯剪辑已有视频素材或只要一张图。
nook-anim/SKILL.md on GitHub (opens in a new tab) -
nook-card
Create reusable knowledge cards and optional card-to-video handoff specs from user topics, copy, and style references. Use when the user asks for knowledge cards, card images, social cards, cover cards, OpenDesign card generation, card style systems, or Remotion-ready card videos. Always confirm production intent, card count, card asset ratio, output layers, and motion needs before generating.
nook-card/SKILL.md on GitHub (opens in a new tab) -
nook-cover
建设态多平台封面生产 skill。用于规划或生成小红书、微信公众号、B站、YouTube、抖音、视频号等自媒体平台封面。当前 V0.2 聚焦小红书封面：按运行时选择 Codex image2.0、外部原子出图工具或用户素材生成主视觉，再按需用 HTML / 后处理稳定中文标题层。
nook-cover/SKILL.md on GitHub (opens in a new tab) -
nook-h3
Generate, monitor, quality-check, and retry MiniMax H3 video clips through a local ComfyUI API. Use when a storyboard or task manifest must be converted into I2VA, FL2VA, L2VA, Ref2VA, or T2VA clips with official prompt structure, explicit references, sequential polling, semantic output review, failure-specific retries, and resumable batching for any number of tasks.
nook-h3/SKILL.md on GitHub (opens in a new tab) -
nook-humanizer-zh-review
审校和改写中文内容，去除 AI 味，保留 nook 的真实判断、具体细节和渠道风格。作为子审校技能用于最终风格审校、去 AI 味审校、人味审校和润色，适用于公众号文章、长文稿、视频转录稿、口播稿及其他 nook 内容。
nook-humanizer-zh-review/SKILL.md on GitHub (opens in a new tab) -
nook-image-gpt
No description in the SKILL.md.
nook-image-gpt/SKILL.md on GitHub (opens in a new tab) -
nook-image2-gpt
Atomic image generation skill backed by the nook-image2-gpt MCP server. Use when Codex needs stable text-to-image or image-to-image generation through submit_image_task and get_image_result, especially as a low-level image provider for larger skills such as nook-poster.
nook-image2-gpt/SKILL.md on GitHub (opens in a new tab) -
nook-qwen-image
Atomic high-quality text-to-image + image-edit skill backed by ModelScope Qwen-Image and Qwen-Image-Edit. Use when Codex needs Chinese poster, cover, editorial image, typography-heavy visual material, or higher-quality Chinese/English text rendering through a paid ModelScope image channel; use nook-zimage for cheap fast drafts, batch tests, and low-stakes background exploration. Also use this ski…
nook-qwen-image/SKILL.md on GitHub (opens in a new tab) -
nook-search
AnySearch 之上的搜索大脑。当用户要"把一句模糊需求变成精准搜索并落库"、"让 AI 自己决定搜什么/走哪个域/采几条/存哪里"、"采集-清洗-入库自动跑通"，或上层 skill（选题/调研/竞品/写稿）需要"先搜再写"时使用。AnySearch 只负责按 query 去 17 个域取数并原样回传；本 skill 负责翻译意图、路由域、编排调用、清洗结果、落库。需登录的国内平台（小红书/抖音/B站）不在覆盖范围，请使用专门的国内平台采集工具。
nook-search/SKILL.md on GitHub (opens in a new tab) -
nook-short
Plan and draft Chinese short video and Xiaohongshu image-text content for Douyin, Xiaohongshu, and WeChat Channels. Use when Codex needs to turn a mid-form transcript, project recap, idea, flash thought, hot topic, or platform sample data into a weekly 12-piece content plan, content briefs, direct oral scripts, Xiaohongshu carousel text, or when the user asks what is trending on Xiaohongshu/Douyi…
nook-short/SKILL.md on GitHub (opens in a new tab) -
nook-slides
Create Chinese-first slide decks and editable PPTX plans through a strict template-filling workflow. Use whenever the user asks to make slides, PPT, presentation, deck, course slides, report slides, or to turn Markdown/notes/articles into slides. This skill must use the current three Chinese visual systems, locked visible copy, approved component schemas, and deterministic rendering; it must not…
nook-slides/SKILL.md on GitHub (opens in a new tab) -
nook-title
Generate, analyze, score, and revise Chinese WeChat/AI-media titles in nook style, including high-density AI news titles with entity/number/action/consequence structures. Use when the user asks for 公众号标题, 给我取几个标题, 候选标题, 标题评分, 标题风格提炼, AI资讯标题, 爆款标题, or title optimization from an Obsidian draft, article facts, notes, links, or finished manuscript.
nook-title/SKILL.md on GitHub (opens in a new tab) -
nook-topic
选题提炼原子 skill。当用户要"从这批样本/信号给我选题方向"、"本周做什么选题"、"这些素材值不值得做"时使用。输入=采集信号（样本库文件/长文收藏库素材），输出=3-5 个选题方向。可独立驱动，也可被上层的内容规划/编排 skill 调用。只做计算、筛选、提炼，不采集、不写稿。
nook-topic/SKILL.md on GitHub (opens in a new tab) -
nook-trave
Create system-driven self-driving travel roadbooks, especially long China road trips such as Xinjiang routes. Use when the user asks for a self-driving itinerary, roadbook, route guide, travel manual, multi-day driving plan, or on-trip replanning; supports guided questioning, external information orchestration, route/weather/hotel evidence, and mobile-first vertical HTML/PDF-style roadbook produc…
nook-trave/SKILL.md on GitHub (opens in a new tab) -
nook-tv-cover
为 Nook 内容生成视频封面。只支持长封面（YouTube）、短封面（B站）和竖封面（抖音/小红书/视频号）。默认使用科技风封面风格，图生图优先，并按平台尺寸输出。
nook-tv-cover/SKILL.md on GitHub (opens in a new tab) -
nook-wechat-writer
用 nook 内容生产方法写、改、审、拟题、适配微信公众号文章。适用于写公众号文章、长文写作、素材成文、改稿、去 AI 味、定角度、拟标题摘要、整合卡兹克/花叔式写作工作流、文章与短视频脚本互转，或从笔记/素材/转录稿/链接/粗略想法写成可发布的文章。
nook-wechat-writer/SKILL.md on GitHub (opens in a new tab) -
nook-zimage
Atomic low-cost text-to-image skill backed by ModelScope Z-Image Turbo. Use when Codex needs cheap/free text-to-image generation for drafts, background assets, poster materials, testing, or batch visual exploration; use nook-image2-gpt instead for image-to-image or higher-quality production images.
nook-zimage/SKILL.md on GitHub (opens in a new tab) -
humanizer-zh
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
third_party/Humanizer-zh/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory.
-
superpowersby obra An agentic skills framework & software development methodology that works.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
-
skillsby anthropics Public repository for Agent Skills