guozhi-video-breakdown
Extract evidence from Xiaohongshu, Douyin, TikTok, Reels, Shorts, Bilibili, or local talking-head short videos, dissect viral hooks, captions, retention, editing, and conversion design, then generate
SKILL.mdskills/guozhi-video-breakdown/SKILL.md
GitHub果汁视频拆解
Turn a short-form talking-head sample into evidence-backed viral teardown and an original script package for Xiaohongshu or Douyin.
Operating Principles
- Evidence first: inspect frames, contact sheets, subtitles, transcript, title, cover, and visible comments before judging why it worked.
- Separate raw facts, inferred intent, and reusable pattern.
- Learn mechanisms, not expressions: never copy exact wording, creator persona, watermark, private screenshots, face, voice, or proprietary assets.
- Optimize for Chinese short-video口播: first 3 seconds, subtitle rhythm, retention turns, trust proof, save/comment triggers, and a script that can be recorded.
- Do not bypass login walls, paywalls, private posts, platform restrictions, or rate limits. If a link cannot be downloaded, ask for a local file, transcript, screenshots, or exported subtitles.
Workflow
Clarify the task only when needed.
- If the user already provides a video/link/transcript and wants拆解/复刻, proceed.
- If the output target is missing, default to a 45-60 second Xiaohongshu口播 script.
- Ask only if both the sample and target niche/topic are missing.
Build the evidence packet.
- For a local video or public URL, read
references/evidence-extraction.mdand runscripts/extract_video_evidence.shwhen the environment hasyt-dlp,ffmpeg, andwhisper. - For transcript/subtitles only, skip visual claims and mark visual evidence as unknown.
- For screenshots/contact sheets only, analyze visual rhythm and caption style but mark口播 as unknown.
- For a local video or public URL, read
Dissect the viral mechanism.
- Read
references/viral-autopsy-framework.md. - Cover: target audience, emotion, topic promise, title/cover, first 3 seconds, segment structure, retention nodes, proof, gold lines, visual materials, editing rhythm, conversion trigger, and replication boundary.
- Read
Generate an original replication package.
- Read
references/replication-output-template.md. - Produce: title candidates, cover text, 3 hook variants, full口播稿, timeline/storyboard, subtitle/flower-text plan, materials list, editing notes, CTA/comment trigger, and risk notes.
- Read
Validate before final delivery.
- Confirm whether
contact_sheet/frames were inspected when available. - Confirm whether transcript/subtitles were read when available.
- Mark missing evidence explicitly.
- Check the new script changes audience, story, proof, wording, and assets enough to avoid copying.
- Confirm whether
Resource Routing
- Read
references/evidence-extraction.mdwhen handling a video file, URL, audio file, subtitle, transcript, screenshot set, or contact sheet. - Read
references/viral-autopsy-framework.mdfor any爆款拆解,黄金3秒, retention, or口播机制 analysis. - Read
references/replication-output-template.mdwhenever the user wants复刻脚本, publish-ready口播稿, title candidates, or a production plan. - Read
references/test-prompts.mdwhen validating trigger behavior or reviewing this Skill. - Run
scripts/extract_video_evidence.shonly for local files or public URLs that the user is allowed to analyze.
Validation
For Skill structure:
python3 /Users/guozhi/.codex/skills/standard-skill-maker/scripts/validate_skill.py <this-skill-folder>
For the extraction script:
bash -n scripts/extract_video_evidence.sh
For a real run, test with a short local sample first:
scripts/extract_video_evidence.sh "/absolute/path/to/sample.mp4" outputs/sample-evidence 1 small zh