Public repository for Agent Skills
content-enrich
Agent skill fromchubbyguan/chubbyskills
内容加工:给任意采集产物(转录稿 / 文章 / 笔记)自动补「摘要 + 要点 + 标签 + 价值判断」, 写进 frontmatter 并在正文顶部插入摘要块。是「加工层」通用能力,惠及仓库所有采集 skill。
How to install content-enrich
npx skills add chubbyguan/chubbyskills# or add only this skill to Claude Code: copy the folder
content-enrich/
# into
~/.claude/skills/content-enrich/ (all projects)
.claude/skills/content-enrich/ (one project)
1# 内容加工(Content Enrich)23采集进来的转录稿、文章往往是大段原始文本,没人愿意回头看。这个 skill 给**任意采集产物**4自动补上可快速消化的元信息——它是「加工层」的通用能力,配合仓库里所有采集 skill 使用。56## 环境要求78```bash9# 零 pip 依赖(仅 Python 标准库)10export DEEPSEEK_API_KEY="your-api-key" # 必需,用于提炼11```1213## 使用方法1415```bash16python scripts/enrich.py 某篇笔记.md # 就地增强单篇17python scripts/enrich.py ./vault/外部输入/ # 批量增强整个目录下的 .md18python scripts/enrich.py 某篇.md --output ./out # 不改原文件,输出到 out/19python scripts/enrich.py 某篇.md --force # 已加工过的重新加工20```2122## 产出2324在原 Markdown 上(原内容完整保留):2526- **frontmatter 注入**:`summary`(一句话总结)、`domain`(领域)、`auto_tags`(标签列表)、`enriched: true`27- **正文顶部插入 `## 📝 摘要` 区块**:一句话 TL;DR、3-5 条要点、「值得深读?」判断、标签2829幂等:默认跳过已加工(`enriched: true`)的文件,可 `--force` 重做。3031## 为什么有用3233- **盘活采集产物**:转录稿 / 文章一眼能看懂讲了啥、值不值得深读34- **便于知识库聚合**:`auto_tags` / `domain` 进 frontmatter,Obsidian Dataview 可直接按标签 / 领域聚合35- **一处投入,惠及全部**:抖音 / B站 / 小红书 / X / 公众号 …… 任何采集产物都能加工3637## 衔接工作流3839```40采集(任意 *-ingest / *-transcribe skill)41 → content-enrich(补摘要 + 要点 + 标签)42 → knowledge-base-management 入库(按 auto_tags / domain 聚合检索)43```4445## 参考4647- [DeepSeek](https://platform.deepseek.com/) — 提炼用 LLM
Excerpt shown under the repository's MIT license.
More skills in chubbyskills
Similar skill repositories
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
The open-source app everyone uses to manage agents at work
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Share work, exchange feedback, and iterate together in one workspace.
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
