Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kennyzir/7deer_skills --skill youtube-intelgit clone --depth 1 https://github.com/kennyzir/7deer_skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kennyzir/7deer_skills/youtube-intel)<a href="https://agentmods.dev/skills/kennyzir/7deer_skills/youtube-intel"><img src="https://agentmods.dev/badge/skills/kennyzir/7deer_skills/youtube-intel/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kennyzir/7deer_skills/youtube-intel"><img src="https://agentmods.dev/badge/skills/kennyzir/7deer_skills/youtube-intel.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00088 | $0.02873 |
| Opus 5 | $0.00044 | $0.01437 |
| Sonnet 5 | $0.00018 | $0.00575 |
| Haiku 4.5 | $0.00009 | $0.00287 |
Grade A, and why
youtube-intel scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
youtube-intel · YouTube内容情报
版本： v2.0 — 重构版 核心理念： 情报工作不是搜一个词等结果就完了。需求分析 → 策略制定 → 数据获取 → 清洗识别 → 保存呈现，缺一不可。
两种模式
Monitoring（竞品监测）
触发词：
- "盯着 XXX 频道"
- "监测这几个频道"
- "这个频道最近发了什么"
Discovery（选题发现）
触发词：
- "我想做 XX 类目，有没有机会"
- "帮我扫描 XX 市场"
- "分析这个赛道"
⚠️ 注意：Discovery 模式按下方六步工作流执行，不是搜一个词就出报告。
Discovery 六步工作流
第一步：需求分析 ← 理解用户真正想要什么，识别模糊性
第二步：策略制定 ← 确定搜索词、子分类、数据源
第三步：数据获取 ← 执行搜索
第四步：数据清洗 ← 去重、过滤噪音、统一格式
第五步：识别筛选 ← 识别子分类、竞争度、机会点
第六步：保存呈现 ← 写入 memory，输出结构化报告
第一步：需求分析
目标： 拿到一个类目请求时，先理解用户真正要的是什么。
执行原则：永远先分析，再动手搜。
3. 判断类目粒度
| 粒度 | 示例 | 是否需要拆分 |
|---|---|---|
| 模糊大类 | "AI"、"内容创作"、"电商" | ❌ 需拆分 |
| 明确子分类 | "AI 图像生成"、"YouTube 剪辑技巧" | ✅ 可直接搜 |
| 竞品监测 | "盯着 @某某频道" | ✅ 进入 Monitoring |
4. 模糊类目必须拆分
如果用户说"AI 工具"，直接拆解：
AI 工具
├── AI 图像工具（Midjourney、Stable Diffusion...）
├── AI 编程工具（Cursor、Copilot...）
├── AI 写作工具（Jasper、Claude...）
├── AI 视频工具（Sora、Runway...）
├── AI 语音/音频工具（ElevenLabs...）
└── AI 办公工具（Notion AI、Gamma...）
原则： 一个搜索词 = 一个明确的子分类。找不到子分类就问用户。
5. 需求记录
把分析结果明确告知用户：
分析：
- 你说的"XXX"我理解为：[具体是什么]
- 拆解为以下子分类：[列表]
- 每个子分类独立搜索：[关键词列表]
第二步：策略制定
目标： 为每个子分类制定搜索策略。
6. 制定搜索词矩阵
对每个子分类，确定：
子分类：AI 图像工具
├── 核心搜索词：AI image generator tools 2025
├── 长尾搜索词：best AI art tools comparison, free AI image generator
├── 竞品搜索词：Midjourney alternatives, Stable Diffusion vs DALL-E
└── 趋势搜索词：AI image generator viral 2025
7. 确定数据源优先级
| 数据源 | 用途 | 置信度 |
|---|---|---|
| YouTube 搜索（browser 抓取） | 热门视频、竞争度 | 🟢 高 |
| YouTube 频道页（browser 抓取） | 频道详细数据 | 🟢 高 |
| Social Blade | 订阅数、趋势 | 🟡 中 |
| Google 搜索 | 舆情热度佐证 | 🟡 中 |
| X（Twitter） | 新产品动态 | 🟡 中 |
8. 搜索执行计划
在开始抓取前，先告诉用户：
搜索策略：
- 类目：AI 图像工具
- 搜索词：AI image generator tools 2025
- 数据源：YouTube 搜索 + 频道页
- 预期结果数：20-30 条视频
- 置信度：🟡 中（YouTube 模糊化数据）
第三步：数据获取
使用 browser 工具执行搜索。
YouTube 搜索
URL 格式：https://www.youtube.com/results?search_query={关键词}
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 382 lines · 88 tokens per session scan A 5887ae1c1699
youtube-intel is a skill published in the GitHub repository kennyzir/7deer_skills (312 stars, last pushed 3d ago), licensed MIT. It adds 88 tokens to every session and 2,873 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
migrate-radix-to-base
Migrates React projects and components from Radix UI to Base UI. Use when asked to migrate from radix, move to base-ui, convert radix primitives, or switch a shadcn project's base library. Handles single components ("migrate accordion") and whole projects.
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
copilotkit-upgrade
Use when migrating a CopilotKit v1 application to v2 -- updating package imports, replacing deprecated hooks and components, switching from GraphQL runtime to AG-UI protocol runtime, and resolving breaking API changes.
non-json-content-types
Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).
trigger-authoring-tasks
Covers writing backend Trigger.dev tasks with @trigger.dev/sdk: defining task() and schemaTask(), the run function and its ctx, retries, waits, queues and concurrency, idempotency keys, run metadata, logging, triggering other tasks (and the Result shape), scheduled/cron tasks, and the essentials of trigger.config.ts.…
saas-builder
Clone, verify, map, and build on top of ixartz/SaaS-Boilerplate for a user's SaaS idea. Use when a user wants to reuse SaaS Boilerplate, evaluate how their product fits it, or build product-specific pages, database schema, roles, permissions, MVP features, and launch scope on top of the boilerplate.