Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

ffmpeg: brew install ffmpeg | apt install ffmpeg | choco install ffmpeg · worldwonderer | DecimalAI

design mediaby worldwonderer

ffmpeg: brew install ffmpeg | apt install ffmpeg | choco install ffmpeg

worldwonderer/video-understanding

Source worldwonderer/video-recap-skills ↗License MIT

把视频分析为结构化理解索引：场景检测、ASR 转写、逐场景 VLM 观察、静音窗口、融合时间线和写作 brief。用于理解、索引或总结视频，也作为后续创作前的分析阶段。输入视频文件；输出 scenes.json、 asr_result.json、vlm_analysis.json、silence_periods.json、timeline_fusion.json、agent_narration_brief.md。触发词：视频理解、视频分析、视频索引、video understanding、analyze video、看懂视频。

SkillScore96Maintained

Automatic

AI Engineer pack

Last verified 8/20/2026

What it changes

Passed 22 of 23 test cases with the skill, and 4 of 23 without it.

Without skill17%

With skill96%

Checks it passed that the model alone missed

refuses to draft commentary text
refuses to schedule or publish videos
specifies mimo-v2.5 for vision analysis

and 26 more in the full report

19 fixed4 passed either way1 still failing0 broke

Pass-rate lift: +79 pp
Tokens: -28%
Agent turns: 0%
Response time: -73%

Model gemini-3.6-flashMeasured 8/20/2026v123 of 24 cases passed with skill · 23 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/worldwonderer-video-understanding/SKILL.md https://app.decimal.ai/s/worldwonderer-video-understanding/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add worldwonderer-video-understanding, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/worldwonderer-video-understanding/ and pins it in .decimal/skills.lock

decimalai skills add worldwonderer-video-understanding

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/worldwonderer-video-understanding/SKILL.md https://app.decimal.ai/s/worldwonderer-video-understanding/SKILL.md

Raw file: /s/worldwonderer-video-understanding/SKILL.md ↗ · machine-readable summary at /s/worldwonderer-video-understanding.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 19 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 19

Prompt

在没有跳过语音转写的前提下，运行该视频理解流程必须在系统中安装哪个命令行软件，并设置哪个环境变量 API Key？

What was checked, without and with the skill
Checked	Without skill	With skill
specifies ffmpeg as the required command-line tool	Passed	Passed
specifies MIMO_API_KEY as the required environment variable	Missed	Passed

case-16 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md65 lines26 filesincludes scripts

1. 定位

本技能把源视频转成 Agent 与下游阶段可读取的理解索引。它的创作角色是素材观察员 / 场记，不是导演：

先观察，再解释；事实与推断分开。
除了“发生了什么”，还要让下游看见知识、权力、目标、关系或情绪在哪一刻变化。
标出由谁的 POV 承载变化、哪个反应或表演不可替代，以及哪里存在完整台词/动作的自然剪辑边界。
证据不足时保留不确定性，不制造戏剧结论。

2. 处理阶段

场景检测：写 scenes.json，包含切点、时长和废片段过滤结果。
抽帧：为视觉分析提取代表帧。
ASR：通过 mimo-v2.5-asr 写时间戳对白 asr_result.json。
静音检测：写 silence_periods.json，标注安静窗口与 has_speech。
VLM 观察：写 vlm_analysis.json，包含场景描述、深层分析和 frame_facts。
时间线融合与创作 brief：写 timeline_fusion.json、asr_writing_chunks.json 和 agent_narration_brief.md。

各阶段只有在输出产物与 provenance sidecar 同时匹配当前视频及影响结果的设置时才会复用；--force 强制重算。

3. 环境要求

# ffmpeg: brew install ffmpeg | apt install ffmpeg | choco install ffmpeg
export MIMO_API_KEY=***

ASR 使用 mimo-v2.5-asr；VLM 使用 mimo-v2.5。--skip-asr 可跳过对白转写，但完整理解仍需要 MIMO_API_KEY 运行 VLM。--mimo-video-overview 可开启按场景块的视频概览。

若 work_dir/background_research.json 存在，本技能会把剧情梗概和角色名折入 VLM 上下文；--context 可补充一条简短提示。

下面的 scripts/... 均相对于本技能目录。若执行器从仓库根目录启动，请给脚本路径加上本技能的绝对目录。脚本不从其他技能目录读取文件；外部输入仅限命令显式传入的视频、参数与 work_dir 产物。

4. 运行命令

python3 scripts/understand.py <video> --work-dir <work_dir> \
  [--context "节目名/角色名"] [--scene-threshold 0.1] [--skip-asr] [--mimo-video-overview] [--force]

Track record

Benchmark

22 / 23

test cases passed, vs 4 / 23 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

worldwonderer / video-recap-skills

skills/video-understanding/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 25 files · scripts

More skills from the same source and nearby in the registry, with their headline benchmark lift.