What is youtube-game-keywords?

A workflow that gathers videos from subscribed YouTube channels, identifies game-related keywords, and groups them into categories such as Roblox, independent games, and console or PC games.

Use it to create a daily YouTube gaming-keyword report, send it through Feishu, and save the full report in a Feishu cloud document. It requires the described OpenClaw, browser, login, and Feishu setup.

It turns a large subscription feed into a structured daily report instead of requiring manual scanning.

youtube-game-keywords — Skill for Claude Code and Codex by kennyzir

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/kennyzir/7deer_skills

agentmods

npx agentmods add skills/kennyzir/7deer_skills/youtube-game-keywords

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/kennyzir/7deer_skills/youtube-game-keywords/github.svg)](https://agentmods.dev/skills/kennyzir/7deer_skills/youtube-game-keywords)

Your own site

<a href="https://agentmods.dev/skills/kennyzir/7deer_skills/youtube-game-keywords"><img src="https://agentmods.dev/badge/skills/kennyzir/7deer_skills/youtube-game-keywords/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/kennyzir/7deer_skills/youtube-game-keywords"><img src="https://agentmods.dev/badge/skills/kennyzir/7deer_skills/youtube-game-keywords.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,603 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00078	$0.02603
Opus 5.5	$0.00031	$0.01041
Sonnet 5.5	$0.00016	$0.00521
Haiku 4.5	$0.00008	$0.00260

Measured 2mo ago against content hash 1085131a492f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

youtube-game-keywords 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/analyze_keywords.py, scripts/fetch_subscriptions.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

youtube-game-keywords/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

YouTube Game Keywords Skill

从 YouTube 订阅频道抓取游戏相关内容，识别游戏关键词并生成结构化日报。

🚀 快速开始

前置要求

依赖	说明
OpenClaw	本 skill 运行于 OpenClaw 环境（https://openclaw.ai）
飞书 Bot	需要已配置好的飞书 Bot 和 `feishu_doc` / `message` 工具权限
Browser 工具 + YouTube 登录态	用于抓取订阅页（⚠️ 必须已登录 YouTube，见下方说明）
OpenClaw Browser 配置	详见"Browser 配置说明"章节

飞书 Bot 所需权限

权限名称	权限标识	用途
云文档	`docx:document`	创建飞书云文档写入日报
发消息	`im:message:send_as_bot`	向用户发送飞书消息
读取消息	`im:message`	消息交互（可选）

💡 权限开通路径：飞书开放平台 → 应用 → 权限管理 → 搜索权限名称 → 开通

环境变量

变量	说明	必需
`FEISHU_TARGET_USER`	飞书通知目标用户的 open_id	可选（默认发给当前对话用户）

⏰ 定时任务配置

本 skill 支持设置为每天自动执行。在 OpenClaw 中创建以下 cron job 即可：

创建命令：

openclaw cron add \
  --name "YouTube Game Keywords 日报" \
  --schedule "0 10 * * *" \
  --tz "Asia/Shanghai" \
  --payload-kind agentTurn \
  --payload-message "使用 youtube-game-keywords skill，执行 YouTube 订阅频道游戏关键词日报任务。按照 skill 完整流程执行：1. 先尝试运行官方脚本（超时则降级用 browser 抓 YouTube 订阅页）2. 整理游戏关键词日报 3. 发送飞书消息到飞书用户 4. 创建飞书云文档并写入完整报告 5. 在飞书消息里附上文档链接" \
  --payload-timeout 900 \
  --delivery-mode announce \
  --delivery-channel feishu

完整 Cron Job JSON（手动创建时使用）：

{
  "name": "YouTube Game Keywords 日报",
  "schedule": { "kind": "cron", "expr": "0 10 * * *", "tz": "Asia/Shanghai" },
  "sessionTarget": "isolated",
  "payload": {
    "kind": "agentTurn",
    "message": "使用 youtube-game-keywords skill，执行 YouTube 订阅频道游戏关键词日报任务。按照 skill 完整流程执行：1. 先尝试运行官方脚本（超时则降级用 browser 抓 YouTube 订阅页）2. 整理游戏关键词日报 3. 发送飞书消息到飞书用户 4. 创建飞书云文档并写入完整报告 5. 在飞书消息里附上文档链接",
    "timeoutSeconds": 900
  },
  "delivery": {
    "mode": "announce",
    "channel": "feishu",
    "to": "user:YOUR_OPEN_ID",
    "accountId": "default",
    "bestEffort": true
  }
}

参数说明：

参数	值	说明
`schedule.expr`	`0 10 * * *`	每天 10:00 执行，可改为其他时间
`delivery.to`	`user:ou_xxxx`	替换为接收通知的飞书用户 open_id
`timeoutSeconds`	`900`	15 分钟超时，覆盖 browser 抓取耗时
`sessionTarget`	`isolated`	在独立 session 中运行，不影响主对话

Read the full file on GitHub · 278 lines

Files

What ships with it

3 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.

Changes

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.

2mo ago First seen · 278 lines · 78 tokens per session scan A 1085131a492f

Subscribe to this mod's changes

youtube-game-keywords is a skill published in the GitHub repository kennyzir/7deer_skills (336 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 2,603 once invoked, about $0.0003 per session on Opus 5.5. 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.

Game development Research agent-skills ai-agents backlinks codex nextjs roblox

youtube-game-keywords next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
youtube-game-keywordskennyzir/7deer_skills	Skill	336	1mo ago	MIT	A	78	Claude Code, Codex
roblox-audiononlooped/roblox-suite	Skill	28	yesterday	MIT	A	42	Claude Code, Codex
roblox-open-cloudnonlooped/roblox-suite	Skill	28	yesterday	MIT	A	44	Claude Code, Codex
roblox-teleportnonlooped/roblox-suite	Skill	28	yesterday	MIT	A	39	Claude Code, Codex
roblox-datastoresnonlooped/roblox-suite	Skill	28	yesterday	MIT	A	46	Claude Code, Codex
roblox-gamepassesnonlooped/roblox-suite	Skill	28	yesterday	MIT	A	40	Claude Code, Codex
roblox-testingnonlooped/roblox-suite	Skill	28	yesterday	MIT	A	42	Claude Code, Codex