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/joonlab/joonlab-claudecode-setting-for-sharenpx agentmods add skills/joonlab/joonlab-claudecode-setting-for-share/gemini-video-analysisWrote 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/joonlab/joonlab-claudecode-setting-for-share/gemini-video-analysis)<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/gemini-video-analysis"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/gemini-video-analysis/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/joonlab/joonlab-claudecode-setting-for-share/gemini-video-analysis"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/gemini-video-analysis.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 | $0.00233 | $0.02500 |
| Opus 5.5 | $0.00093 | $0.01000 |
| Sonnet 5.5 | $0.00047 | $0.00500 |
| Haiku 4.5 | $0.00023 | $0.00250 |
Grade A, and why
gemini-video-analysis 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 1mo 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gemini Video Analysis
Gemini 3 모델을 사용해 영상(YouTube URL · 로컬 mp4/mov/webm 등)을 분석하는 스킬. 단순 요약부터 구조화된 JSON 추출, 추론형 Q&A까지 분석 의도에 맞춰 최적화된 프롬프트·temperature·모델을 적용한다.
트리거 신호
다음 조건 중 하나라도 충족하면 이 스킬을 사용한다:
- 사용자가 YouTube URL (
youtube.com/watch,youtu.be/) 또는 로컬 영상 파일 경로(.mp4,.mov,.webm,.mkv,.avi,.3gp,.flv,.wmv)를 주면서 분석·요약·이해·추출·번역·정리를 요청 - 명시 키워드: "영상 분석", "비디오 분석", "영상 요약", "릴스 분석", "쇼츠 분석", "유튜브 분석", "video analysis", "analyze this video"
- 영상 내 정보 추출 요청: "이 영상에서 ~ 찾아줘", "타임스탬프 알려줘", "챕터 나눠줘", "출연자가 누구야"
- 영상 기반 Q&A: "이 영상 보고 ~에 대해 알려줘", "이 영상의 메시지는?"
핵심 워크플로
영상 분석 요청이 들어오면 반드시 아래 순서로 진행한다:
1단계 — 영상 source 확인
- URL인지 로컬 파일 경로인지 판별 (
scripts/analyze.py가 자동 처리하지만, 잘못된 경로 등은 미리 검증) - 로컬 파일이면 존재·크기 확인 (
ls -la) - YouTube의 경우 public 영상인지 확인 (private/unlisted 불가)
2단계 — 분석 task 판별
사용자 요청에서 task를 추론한다. 모호하면 summary로 진행하되, 명시 단서가 있으면 우선한다:
| 신호 | task |
|---|---|
| "요약", "어떤 내용", "뭐야" | summary |
| "챕터", "타임스탬프", "구간 나눠", "하이라이트" | chapters |
| "JSON", "구조화", "데이터 추출", "스키마" | structured |
| "특정 구간", "X초~Y초", "처음 N분만" | clip (start/end 인자 필요) |
| "왜", "어떻게", "분석해", "마케팅 관점", "개선점", "타겟" | qa (thinking 켬) |
| "고화질로", "세밀하게", "빠른 액션 봐줘" | high-fps |
3단계 — 모델 선택 (AskUserQuestion 필수)
항상 사용자에게 어떤 모델을 쓸지 묻는다. 단, 1초~10초 안에 끝나는 명백한 작업이라도 묻는다 (정책). 질문 시 비용 추정치를 함께 제시:
영상 길이를 모르면 보수적으로 "~30초" 가정 (Reel/Shorts 기본), 명시되어 있으면 그 값으로 계산.
- 토큰 추정:
prompt ≈ 100 × duration_sec + 1000(영상 토큰화 + 프롬프트), output 약 300, thinking은 Pro 1500 / Flash 800 / Lite 0 - 비용 계산은
scripts/_common.py:estimate_cost()함수 그대로 사용
질문 예시 (영상이 ~30초 추정인 경우):
question: 어떤 Gemini 3 모델을 쓸까요?
header: Model
options:
- 🏆 Pro (gemini-3.1-pro-preview) - 최고 품질, thinking 강함 (예상: ~$0.02 / ~30원)
- ⚡ Flash (gemini-3-flash-preview) - 균형 잡힌 속도/품질 (예상: ~$0.003 / ~5원)
- 🪶 Flash-Lite (gemini-3.1-flash-lite-preview) - 가장 빠르고 저렴 (예상: ~$0.0005 / ~1원)
structured/qa task는 Pro/Flash 권장, summary/chapters는 Flash 권장, 단순 분류는 Flash-Lite로도 충분하다는 힌트를 옵션 description에 포함.
What ships with it
7 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.
- 1mo ago First seen · 185 lines · 233 tokens per session scan A c6eb8e0dc139
gemini-video-analysis is a skill published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (14 stars, last pushed 1mo ago), licensed MIT. It adds 233 tokens to every session and 2,500 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.