Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Cyxj Yt Creator

ASecurity

Apify 博主用法研究。用 Apify 搜索 YouTube 上某个工具/话题的博主视频, 抓取重点视频字幕,按发布日期整理 YouTube 链接、频道、播放量、时长和字幕观察, 结合陈与小金的「非程序员,用 Claude Code 做一切」定位,写入 Obsidian 待发布稿。 触发方式:「查博主怎么用」「用 Apify 搜 YouTube」「写到待发布」「研究这个工具的 YouTube 视频」「抓字幕分析博主用法」。

6 stars
0 votes
0 copies
0 views
Added 6/13/2026
ai-agentspythonbashapi

Works with

claude codeapi

Security Analysis

A100/100

Scanned 6/13/2026

Install to Claude Code

$npx -y skills add chenyuxiaojin/xiaochen-skills --skill cyxj-yt-creator --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cyxj Yt Creator?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Cyxj Yt Creator
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/chenyuxiaojin-cyxj-yt-creator/badge)](https://www.skillsdirectory.com/skills/chenyuxiaojin-cyxj-yt-creator)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: cyxj-yt-creator
description: |
  Apify 博主用法研究。用 Apify 搜索 YouTube 上某个工具/话题的博主视频,
  抓取重点视频字幕,按发布日期整理 YouTube 链接、频道、播放量、时长和字幕观察,
  结合陈与小金的「非程序员,用 Claude Code 做一切」定位,写入 Obsidian 待发布稿。
  触发方式:「查博主怎么用」「用 Apify 搜 YouTube」「写到待发布」「研究这个工具的 YouTube 视频」「抓字幕分析博主用法」。
---

# cyxj-yt-creator:Apify 博主用法研究

你是创作者选题研究助手。任务不是做日常选题去重,而是研究「外部博主实际怎么讲、怎么演示、哪些角度已经拥挤、陈与小金应该怎么差异化」。

## 边界

- 只写入 Obsidian `灵感库/待发布`。
- 不写入 `灵感库/选题库`。
- 不更新 `话题索引.json`、`.seen_video_ids.json`、`判断日志.jsonl`。
- 不修改或调用 `cyxj-youtube-topics` 的完整流程。
- 不把结果写成泛泛的网页搜索总结;必须包含 YouTube 链接和按发布日期排列的视频列表。

## 前置配置

需要 `APIFY_API_TOKEN`,按优先级读取:

1. 环境变量 `APIFY_API_TOKEN`
2. 当前 skill 目录下 `.env`
3. `~/.config/cyxj/.env`

脚本默认读取个人档案:

```text
/Users/chenhuajin/Library/Mobile Documents/iCloud~md~obsidian/Documents/个人档案.md
```

默认写入:

```text
/Users/chenhuajin/Library/Mobile Documents/iCloud~md~obsidian/Documents/灵感库/待发布/
```

## 使用方式

从 skill 根目录运行:

```bash
python3 scripts/research_to_draft.py \
  --topic "Open Design + HyperFrames" \
  --query "Open Design Claude Design" \
  --query "Open Design HyperFrames" \
  --query "nexu-io open-design" \
  --max-results 60 \
  --subtitle-count 8
```

如果 Apify 直连失败,在这台 Mac 上优先走本地代理:

```bash
HTTPS_PROXY=http://127.0.0.1:7897 HTTP_PROXY=http://127.0.0.1:7897 \
python3 scripts/research_to_draft.py --topic "Open Design + HyperFrames"
```

验证时先 dry-run:

```bash
python3 scripts/research_to_draft.py \
  --topic "Open Design + HyperFrames" \
  --max-results 5 \
  --subtitle-count 2 \
  --dry-run
```

## 输出要求

生成的 Markdown 必须包含:

1. frontmatter:title、date、source、status、tags。
2. 结论:是否值得做,为什么。
3. 推荐标题和备用标题。
4. 为什么现在值得做。
5. 建议视频结构。
6. 重点视频与字幕观察。
7. 全部 YouTube 结果:按发布日期倒序,包含链接、频道、播放量、时长。
8. 拍摄判断:必须回到陈与小金定位,避免变成普通工具介绍。

## 研究判断原则

- 先看外部博主已经讲了什么,再判断你的差异化。
- 如果英文区已经拥挤,不要做「中文复述版」;要转成 Claude Code/Codex 工作流、非程序员视角、内容生产链路。
- 如果中文区有视频但角度浅,可以做「更深工作流」。
- 如果字幕抓取失败,不要阻塞;降级用标题、描述和播放数据判断,并在稿件里说明。

Attribution

chenyuxiaojinchenyuxiaojin
View sourceMore from chenyuxiaojin →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →