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.
git clone --depth 1 https://github.com/renky1025/agent-skillsnpx agentmods add skills/renky1025/agent-skills/video-minutesWrote 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/renky1025/agent-skills/video-minutes)<a href="https://agentmods.dev/skills/renky1025/agent-skills/video-minutes"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/video-minutes/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/renky1025/agent-skills/video-minutes"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/video-minutes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00403 | $0.05724 |
| Opus 5 | $0.00201 | $0.02862 |
| Sonnet 5 | $0.00081 | $0.01145 |
| Haiku 4.5 | $0.00040 | $0.00572 |
Grade B, and why
video-minutes scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt install ffmpeg # Ubuntu How it starts
The opening of the file, as written. The whole thing — 726 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video Minutes Skill
智能视频纪要生成器,支持多类型视频自动分类、智能总结、任务分发。
核心特性
- 🤖 AI 自动分类: 自动识别视频类型(会议/课程/访谈等),应用对应模板
- 📝 智能总结: 提取核心要点、行动项、关键决策
- 🏷️ 任务分发: 通过 @tags 将待办分发给其他 skill 执行
- 🔗 多源支持: 本地文件、Zoom/腾讯会议录制、在线视频链接
- 🌐 多语言: 自动检测语言,支持中英日等 99+ 语言
- 📊 多种输出: Markdown/Obsidian/Notion/飞书文档
首次设置 (First-Time Setup)
配置优先级检测:
# 检测配置文件存在性
test -f "video-minutes/config.yaml" && echo "project"
test -f "$HOME/.ai-agent/skills/video-minutes/config.yaml" && echo "user"
test -f "$HOME/.video-minutes-config.json" && echo "legacy"
| 结果 | 操作 |
|---|---|
| 找到 YAML | 读取并应用 |
| 找到 legacy JSON | 迁移到 YAML 格式 |
| 未找到 | 执行首次设置向导 (阻塞操作) |
首次设置向导 (BLOCKING)
⚠️ CRITICAL: 未检测到配置文件时,必须先完成设置向导,阻塞后续所有视频处理操作。
使用 AskUserQuestion 一次性呈现所有问题,等待用户回答后再继续。
🎬 Video Minutes 配置向导
让我为您配置视频纪要生成的默认偏好:
**1. 默认输出语言**
视频语音通常为哪种语言?
- 🌐 自动检测 (推荐)
- 🇨🇳 中文
- 🇺🇸 英文
- 🇯🇵 日文
- 其他: __________
**2. Whisper 模型选择**
语音转文字精度 vs 速度偏好?
- ⚡ Tiny (最快,适合快速预览)
- 🚀 Base (推荐,平衡速度质量)
- 🎯 Small (更精准,慢 2x)
- 🏆 Medium (高精度,慢 4x)
- 💎 Large (最佳质量,慢 8x,需 GPU)
**3. 输出格式偏好**
纪要文档保存为哪种格式?
- 📝 Markdown (推荐,通用)
- 📔 Obsidian (带双链和标签)
- 📊 Notion (自动同步到数据库)
- 🚀 飞书文档 ( Lark )
**4. 输出内容选项**
纪要包含哪些内容?(多选)
- ✅ 内容摘要 (一句话总结)
- ✅ 核心要点 (分点列出)
- ✅ 详细时间线 (带时间戳)
- ✅ 行动项追踪 (TODO 列表)
- ✅ 完整字幕 (可选折叠)
- ✅ 发言人识别 (如果可区分)
**5. 自动扫描路径** (可选)
自动监控哪些目录的新视频?
- 📹 Zoom 录制文件夹
- 📹 腾讯会议录制
- 📹 钉钉会议录制
- 📂 自定义路径: __________
**6. 任务分发集成**
检测到行动项时如何分发?
- ❓ 先问我确认 (推荐)
- 🤖 自动分发到对应 skill
- 📋 仅汇总列出,不分发
**7. 视频类型偏好**
您最常处理的视频类型?
- 💼 会议录像 (提取 TODO)
- 📚 课程讲座 (知识笔记)
- 🎙️ 访谈播客 (Q&A 整理)
- 🎤 演讲汇报 (观点提炼)
- 🛠️ 教程演示 (步骤清单)
配置保存路径: ~/.claude/skills/video-minutes/config.yaml
# config.yaml 示例
version: "1.1.0"
output:
language: auto # auto/zh/en/ja
format: obsidian # markdown/obsidian/notion/lark
directory: "~/Documents/video-minutes"
filename_template: "{date}-{type}-{title}"
content:
include_summary: true
include_key_points: true
include_timeline: true
include_action_items: true
include_transcript: true
transcript_collapsed: true # 默认折叠
speaker_identification: true
max_summary_points: 10
whisper:
model: base # tiny/base/small/medium/large/large-v1/large-v2/large-v3
device: auto # auto/cpu/cuda/mps
compute_type: int8 # int8/int8_float16/float16/float32
language: null # null=auto
classification:
enabled: true
confidence_threshold: 0.7
dispatch:
confirm_before_dispatch: true
auto_dispatch_tags: ["@reminder"] # 自动分发的标签
scanning:
enabled: true
interval_minutes: 60
paths:
- "~/Documents/Zoom"
- "~/Documents/腾讯会议"
integrations:
obsidian_vault: "~/Obsidian/VideoNotes"
notion_database_id: null
lark_webhook: null
What ships with it
17 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.
- README.md 5.4 KB
- references/config/config-schema.md 3.0 KB
- references/config/first-time-setup.md 8.1 KB
- requirements.txt 296 B
- scripts/classifier.py 6.7 KB runs code
- scripts/config_manager.py 5.9 KB runs code
- scripts/dispatcher.py 8.1 KB runs code
- scripts/generate_minutes.py 7.1 KB runs code
- scripts/insanely_fast_transcriber.py 9.9 KB runs code
- scripts/video_processor.py 13 KB runs code
- templates/interview.md 1.5 KB
- templates/lecture.md 1.4 KB
- templates/meeting.md 1.4 KB
- templates/note.md 819 B
- templates/podcast.md 1.9 KB
- templates/presentation.md 1.6 KB
- templates/tutorial.md 2.1 KB
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 · 726 lines · 403 tokens per session scan B 2384bb5198e6
video-minutes is a skill published in the GitHub repository renky1025/agent-skills (11 stars, last pushed 2d ago), licensed MIT. It adds 403 tokens to every session and 5,724 once invoked, about $0.0020 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mindos-zh
A local knowledge-base assistant for storing and finding decisions, meeting notes, procedures, troubleshooting lessons, and preferences across conversations and coding agents. It works only with the MindOS knowledge base.
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
iflytek-ocr-invoice
An image-reading tool that extracts structured information from Chinese invoices, receipts, bills, and tickets. OCR means turning text in a photo or scan into computer-readable data.
iflytek-pdf-image-ocr
AI-powered OCR service for images and PDF documents using iFlytek's advanced recognition APIs.
iflytek-contract-intelligence-review
A contract-review workflow for scanned or digital agreements. It can recognize document text, examine clauses, detect risks, check compliance, and create translation summaries; its output is for review and is not formal legal advice.
training-report
Produce a professional training/workshop report as a .docx file. Use this skill whenever the user mentions "training report", "workshop report", "compte rendu", "compte rendu de formation", "formation report", "debriefing a workshop", "write up a training session", "résumé de formation", or any request to document a…