Communitygithub.com

Knowledge Video Editor

Intelligently edits talking-head videos for knowledge content, adding visual packaging, bilingual subtitles, cover frames, and outputting horizontal (16:9) or vertical (9:16) final cut. Suitable for science popularization, tool tutorials, business analysis, opinion sharing, storytelling, and industry interpretation.

What is Knowledge Video Editor?

The **Knowledge Video Editor** skill transforms a raw talking-head video (real or digital presenter) into a polished, publish-ready knowledge video with minimal manual intervention. It autonomously performs 13 sequential steps: environment check, video analysis, content understanding, transcription with smart editing, logic visualization, storyboard generation, adaptive layout, bilingual subtitle creation, cover frame generation, rendering, and quality control. It supports six content types (knowledge, practice, analysis, opinion, story, industry) and employs 21 visual components, two premium color schemes (Deep Space Black Gold / Pearl Ink Green), a capsule-style dynamic chapter navigation bar, a circular presenter avatar, and automatic quality assurance. The skill is designed for platforms like Claude Code, Cursor, and Codex, and enforces strict rules: the first frame must be a complete cover, bilingual subtitles with Chinese above English, presenter always visible, and text scaled 12% larger by default. It refuses to fake output and demands honest reporting when requirements cannot be met.

Works with✓Claude Code✓Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/WWF885/knowledge-video-editor/tree/main

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Knowledge Video Editor · Intelligent Talking-Head Video Editor

Make knowledge visible, logic clearer, and viewing less tedious.

This Skill transforms "an unedited talking-head video" into "a publish-ready knowledge video." You just provide the video, and it autonomously performs: understand content → determine type → fine-cut audio → direct and plan → visualize logic → add bilingual subtitles → generate first-frame cover → quality check → deliver final cut.

Core principle: Fully automatic by default, no step-by-step confirmation required; but never fake the final cut.


1. Determining Whether to Use This Skill

Use ItDon't Use It
Real or digital presenter talking-head videos (explaining knowledge, methods, or opinions to camera)Pure vlogs, travel clips (no explanatory narrative)
Existing talking-head footage needing repackaging as a knowledge videoPure film editing, narrative films, short dramas
Need horizontal/vertical final cut, bilingual subtitles, and cover frameOnly need transcoding, cropping, or resolution change
Batch standardized output (same visual style)Need to keep original and only add subtitles (use basic subtitle workflow)

Judgment basis: Does the video contain "information that can be presented in a structured way"? If yes, proceed with this Skill.


2. Three Golden Rules Before Starting

  1. Check the environment first, then act. Execute python3 scripts/check_environment.py --json to confirm ffmpeg / transcription engine / rendering engine / fonts are ready. If critical capabilities are missing, report the actual gaps—never "pretend" to produce a final cut.
  2. Plan first, then render. Must generate director_plan.json and storyboard.json (per-second scene breakdown), then validate with validate_storyboard.py before rendering.
  3. Leave original footage untouched. All intermediate artifacts go under <project>/work/, final output under <project>/output/. Never overwrite the user's original video.

3. 13-Step Execution Pipeline

StepActionOutputScript
1Environment self-checkenv_report.jsoncheck_environment.py
2Video property detection (orientation/duration/resolution/framerate/presenter position)video_meta.jsonanalyze_video.py
3Content understanding and segmentation (determine overall type + per-segment attributes)analysis.jsonanalyze_video.py --content or host LLM
4Speech transcription + editing decisions (repetitions/verbal errors/pauses/filler words/beginning-end)transcript.json + edl.jsontranscribe.py
5Fine-cut execution (trimming + noise reduction + loudness normalization + timeline remapping)edited.mp4 + timemap.jsonedit_video.py
6Full video director plan (video type/topic/cover/chapters/pacing)director_plan.jsonLLM + templates
7Logic visualization (knowledge points → visual component mapping)visual_map.jsonLLM + 07 specification
8Per-second storyboard (every 1 second planned, composition reviewed every 3 seconds)storyboard.jsonLLM + storyboard.schema.json
9Adaptive layout (horizontal/vertical safe areas, presenter avatar region)layout.jsonconfig/safe-areas.json
10Chinese-English bilingual subtitles (sentence-level, semantic breaks, width measurement)subtitle.srt + subtitle.jsontranscribe.py --bilingual
11First-frame cover generation (first frame is the cover)cover.pngrender_video.py --cover-only
12Final rendering (Remotion composition + presenter avatar + sound effects/BGM mixing)output/01_FinalCut.mp4render_video.py
13Quality check and auto-fix (content/visuals/subtitles/audio/decoding)qc_report.mdquality_check.py

One-click pipeline: python3 scripts/run.py --video <source> --out <directory> --ratio 16:9


4. Non-Negotiable Hard Rules (Violation = Rework)

  1. The first frame must be a complete cover. No black screen, blank space, or title still in entrance animation. Title max 2 lines, each line max 4 characters (letters/digits counted same), total ≤ 8 characters, centered, extra-bold large font.
  2. From the second shot, the cover title must completely disappear. Cover defaults to 1.5–2 seconds, synchronized with speech start—no silent waiting inserted.
  3. Horizontal must include dynamic chapter navigation bar. 3–6 chapters, each 2–6 characters, smoothly switches with speech progress, max 8% of frame height, hidden during cover. Navigation bar uses capsule floating style (border-radius = height/2, frosted glass, 1px stroke, sliding highlight block, bottom thin progress line). No "text+checkmark+dash" stacking allowed.
  4. Whole video uses only one main color scheme. Deep Space Black Gold or Pearl Ink Green, no mixing.
  5. Bilingual subtitles: Chinese above, English below, sentence-synced, must measure character width—no overflow, no blocking core knowledge area, no infinite font size reduction.
  6. Audio priority: original voice > key sound effects > BGM. BGM must be low volume and duck behind voice.
  7. Don't delete key arguments to shorten duration, don't change original opinions, don't rewrite facts.
  8. Don't crop horizontal output directly to vertical—must re-layout and re-render.
  9. Quality score < 90 must auto-locate and fix; if unfixable, report honestly—never declare pass.
  10. All assets must be licensable—no images/music/video from unknown sources.
  11. Every frame must include the presenter. Presenter shots use V01/V02 full frame; knowledge visuals (keywords, flows, comparisons, cards, numbers, summaries, etc.) must overlay V21 circular presenter avatar in the top-right corner—no frame allowed without presenter.
  12. Three iron rules for circular avatar framing and position. (a) The circle must show hair + full facial features + shoulders, with 6–10% headroom above and at least 25% space below chin for neck and collar—no forehead or chin cropping; (b) Fixed top-right, vertical below navigation bar, horizontal at top-right edge, with 48–52px margin; (c) Must never overlap title, knowledge cards, or subtitles—content area must yield to it (vertical content shifts down, horizontal right side leaves 344px safe zone). Three framing parameters: zoom (inner width / circle diameter, 1.0 standard for head-shoulders, use 1.2–1.5 only if person appears small) + focus_x/focus_y (face center) + anchor_y (face center vertical position in circle, close-up 0.42 / wide shot 0.28); must render one still frame for acceptance before final.
  13. Explanatory text defaults to 12% larger. Knowledge visual titles, bullet points, card body rendered uniformly at text_scale 1.12—prefer reducing words over shrinking font.

5. Video Type Determination (Not User-Selected, But Determined by You)

Judge overall video first, then segments. Different strategies can be mixed within the same video.

TypePreferred Editing StylePresenter Ratio Reference
knowledge Science popularizationFlowcharts, structure diagrams, dynamic whiteboard20–35%
practice Tool tutorialScreen recording, local zoom, operation demo15–30%
analysis Business analysisData charts, comparison charts, causal chains25–40%
opinion Opinion sharingPresenter + keywords + cases40–60%
story StorytellingPresenter narrative + scenes + timeline45–65%
industry Industry interpretationMaps, citations, real footage, charts25–45%

Ratio is a reference, not a check-in. Wrong type judgment = wrong overall style; this step determines 80% of the work.


6. Directory Structure

knowledge-video-editor/
├── SKILL.md                 # This file: single entry point, rule master
├── AGENTS.md                # Execution protocol for each Agent (Codex/Claude/Gemini/Doubao, etc.)
├── README.md                # Human-readable instructions and showcase
├── VERSION
├── references/              # 10 detailed rule documents (no code)
├── config/                  # Machine-readable config (theme/ratio/safe zones/glossary/schemas)
├── scripts/                 # 8 executable scripts (analysis→editing→validation→rendering→QC)
├── templates/remotion/      # Visual rendering engine (React components)
├── assets/                  # Fonts/icons/music/sound effects (licensed assets, leave empty in repo with note)
└── examples/                # 4 real director plan examples

7. Reference Index (Read on demand—don't ingest all at once)

Need to SolveRead
How to determine type and segmentreferences/01_VideoUnderstandingAndTypeJudgment.md
What to cut, keep, and how not to cut wrongreferences/02_AutomaticFineEditing.md
How to make cover that won't get rejectedreferences/03_FirstFrameCoverSpecification.md
Horizontal/vertical layout and navigation bar parametersreferences/04_HorizontalVerticalAndDynamicNavigation.md
Two theme color values and usage scenariosreferences/05_ColorAndVisualDesign.md
Per-second storyboard writing and animation curvesreferences/06_IntelligentStoryboardAndPerSecondDynamics.md
How to choose V01–V20 components, how to make V21 avatarreferences/07_VisualComponentUsageSpecification.md
Subtitle font size, line breaks, safe zonesreferences/08_BilingualSubtitlesAndSafeZones.md
BGM and sound effect density, duckingreferences/09_BackgroundMusicAndSoundEffects.md
How to score QC 100 and how to fixreferences/10_QualityCheckAndAutoRepair.md

8. Command-Line Quick Reference

# 1. Environment check
python3 scripts/check_environment.py --json

# 2. Read video properties
python3 scripts/analyze_video.py --video input.mp4 --out work/video_meta.json

# 3. Transcribe (Chinese-English bilingual)
python3 scripts/transcribe.py --video work/edited.mp4 --bilingual --out work/

# 4. Fine-cut per EDL
python3 scripts/edit_video.py --video input.mp4 --edl work/edl.json --out work/edited.mp4

# 5. Validate storyboard (no pass, no render)
python3 scripts/validate_storyboard.py --storyboard work/storyboard.json

# 6. Render (including cover export, circular presenter avatar)
python3 scripts/render_video.py --storyboard work/storyboard.json --ratio 16:9 \
  --audio work/edited.mp4 --cover cover.png --out output/01_FinalCut.mp4

# 7. Quality check
python3 scripts/quality_check.py --video output/01_FinalCut.mp4 \
  --storyboard work/storyboard.json --report output/08_AutoQCReport.md

# 8. Full pipeline
python3 scripts/run.py --video input.mp4 --out project/ --ratio 9:16 --theme pearl-green

All scripts support --dry-run to preview intended actions.


9. Data Structures (Must Follow Contract)

Director plan and storyboard use a unified JSON contract: config/storyboard.schema.json. Minimal usable structure:

{
  "video_type": "knowledge",
  "aspect_ratio": "16:9",
  "resolution": [1920, 1080],
  "theme": "dark_gold",
  "cover": {
    "lines": ["工作方式", "彻底变了"],
    "position": "center",
    "visible_from_first_frame": true,
    "duration": 2
  },
  "presenter": {
    "always_visible": true,
    "badge": { "enabled": true, "diameter_px": 192, "top_px": 316, "focus_x": 0.58, "focus_y": 0.30, "zoom": 1.0, "anchor_y": 0.42 }
  },
  "navigation": { "enabled": true, "chapters": ["现状", "逻辑", "案例", "总结"] },
  "subtitles": { "languages": ["zh", "en"], "layout": "chinese_above_english", "safe_area_check": true },
  "storyboard": [
    { "scene_id": "S001", "start": 0, "end": 2, "visual_type": "cover",
      "motion": "subtle_push", "sfx": "soft_impact" },
    { "scene_id": "S002", "start": 2, "end": 5, "visual_type": "presenter",
      "cover_visible": false,
      "animation_plan": [
        { "time": 2, "action": "show_navigation" },
        { "time": 3, "action": "highlight_keyword" },
        { "time": 4, "action": "subtle_zoom" }
      ] }
  ]
}

During actual execution, must also include: asset absolute paths, exact frame numbers, real subtitle timestamps, graphic coordinates, animation curves, licensing info, horizontal/vertical safe zones, and avatar framing parameters.


10. Cross-Agent Adaptation

The same rules are readable by any Agent; whether final cut can be produced depends on the environment.

AgentHow to ReadCan Render
Codex / Claude Code / Gemini CLIAGENTS.md → SKILL.mdYes (requires ffmpeg + node)
Doubao Work / WorkBuddyThis SKILL.mdDepends on environment
Text-only LLMOutput only director_plan.json + storyboard.jsonNo, pass to rendering environment

Division of labor: reasoning belongs to the model, rendering belongs to the program. Don't let the LLM guess pixels, and don't let the rendering engine make semantic judgments.


11. Delivery Checklist

<topic>/
├── 01_FinalCut.mp4
├── 02_FirstFrameCover.png
├── 03_FineCutAudioVideo.mp4
├── 04_ChineseEnglishSubtitles.srt
├── 05_FullTranscription.md
├── 06_DirectorPlan.json
├── 07_Storyboard.json
├── 08_AutoQCReport.md
└── 09_EditableVideoProject/

When outputting both horizontal and vertical, each gets its own final cut, cover, storyboard layout, and subtitle project, sharing content analysis and fine-cut timeline.


12. When Must Stop and Report

  • Transcription engine unavailable with no alternative → report, don't make up lines.
  • Source video severely blurry/without audio/without valid explainer content → report, don't force-edit.
  • Asset copyright unclear → don't use, and explain why.
  • Rendering fails multiple times → report the error verbatim, don't hand over a half-baked product as final.

Honesty matters more than completion.

Related Skills