agentleFS
Eugenevdm01Eugenevdm01/eugenes-meta-agent/skills/automated-video-editor/SKILL.md

automated-video-editor

Skill4 starsChanged 6 months agoMITView on GitHub

Automated short-form video editing and cloud content pipeline workflow. Use when ingesting Dropbox uploads, editing Reels/TikToks/Shorts, merging multiple clips into one video, adding captions/B-roll/music/audio cleanup, queueing staggered posts, or handing completed videos to an organic social posting agent.

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 12 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈12

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to operate as a practical short-form video editor for Eugene’s content machine.

    line 8
  2. Distinctive:

    When new files arrive, classify them before editing.

    line 16
  3. Distinctive:

    Use this workflow when Eugene records one idea across multiple files, such as filming himself first, stopping the camera, switching to the …

    line 27
  4. Distinctive:

    Use short crossfades only when the transition should feel intentional.

    line 31
  5. Distinctive:

    Remove dead time at the start and end of each clip, but avoid cutting too tightly if it makes speech unnatural.

    line 32
  6. Distinctive:

    Keep continuity by matching loudness, color temperature, and crop position across clips.

    line 33
  7. Distinctive:

    Add captions after the clips are merged so caption timing follows the final timeline.

    line 34
  8. Distinctive:

    Every finished video should support a simple funnel motion: attention → trust → action.

    line 39
  9. Distinctive:

    When Eugene uploads five videos, do not publish all five immediately.

    line 53
  10. Distinctive:

    Use the organic posting agent or VanX/GHL social planner handoff for completed assets.

    line 63
  11. Distinctive:

    Use established open-source patterns as reference, not as mandatory dependencies.

    line 83
  12. Very specific:

    Read references/github_video_editing_patterns.md when choosing tools or editing patterns for a new automation path.

    line 92
  13. Very specific:

    Use scripts/merge_vertical_clips.py when a simple deterministic multi-clip merge is needed.

    line 96
  14. Distinctive:

    Never post a newly edited video live if the user is actively reviewing audio, visual quality, caption accuracy, or destination accounts.

    line 108

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Automated Video Editor

Use this skill to operate as a practical short-form video editor for Eugene’s content machine. The goal is to turn raw phone videos into publish-ready vertical content while keeping the process simple, repeatable, and cloud-friendly.

Core Operating Rule

Do not treat each uploaded clip as an isolated task by default. First determine whether the upload is a single standalone video, a multi-clip continuation, or a batch of separate videos that should be scheduled over time. Preserve publishing control and avoid posting all completed videos at once unless Eugene explicitly asks for immediate publishing.

Intake Classification

When new files arrive, classify them before editing.

Intake TypeHow To IdentifyRequired Action
Single videoOne clip with complete hook, body, CTA, or no matching sequence markerEdit as one standalone short-form video.
Multi-clip continuationFiles are close in timestamp, numbered, share a folder, or Eugene says phrases like “let me show you”, “part two”, “then I turned the camera around”Merge clips in story order before captions and final polish.
Batch contentMultiple unrelated clips uploaded togetherProcess separately and place into the publishing queue with staggered release slots.
Needs manual reviewUnclear order, missing audio, broken file, or duplicate takesCreate a review note and ask for the minimum clarification needed.

Multi-Clip Merge Workflow

Use this workflow when Eugene records one idea across multiple files, such as filming himself first, stopping the camera, switching to the back camera, then continuing.

  1. Sort clips by capture timestamp, filename sequence, or explicit manifest order.
  2. Normalize every clip to the same frame rate, resolution, audio sample rate, and orientation before merging.
  3. Use short crossfades only when the transition should feel intentional; otherwise use hard cuts for natural social content.
  4. Remove dead time at the start and end of each clip, but avoid cutting too tightly if it makes speech unnatural.
  5. Keep continuity by matching loudness, color temperature, and crop position across clips.
  6. Add captions after the clips are merged so caption timing follows the final timeline.
  7. Export a single vertical master and a short QA sample when the edit is complex.

Editing Standards For Funnel Junkies Organic Content

Every finished video should support a simple funnel motion: attention → trust → action. The edit should make the message clearer, not overproduce the video.

Editing LayerStandard
FormatDefault to 9:16 vertical, 1080x1920, H.264 MP4, AAC audio.
HookKeep the first 1–3 seconds sharp; remove rambling lead-in unless it adds authenticity.
CaptionsUse large, mobile-readable captions with emphasis on money, freedom, mistake, proof, or action words.
AudioPrioritize intelligible natural voice. Fix noise first, then de-hollow, then loudness. Never boost noise just to hit loudness.
B-rollUse only when it clarifies the promise, proof, travel/freedom context, or demonstration.
CTAMatch the intended funnel action, usually comment keyword, DM, join community, watch webinar, or book.
QACheck final file plays, captions are in sync, speech is understandable, and no wrong platform/account is targeted.

Queue And Scheduling Logic

When Eugene uploads five videos, do not publish all five immediately. Queue them into the next available publishing slots according to the current content plan.

PriorityRule
1Urgent campaign or event-specific videos go first.
2Highest commercial-intent content gets the next available prime slot.
3Batch uploads are staggered across multiple days or time blocks.
4Duplicate angles are separated so the feed does not feel repetitive.
5Completed but unapproved sensitive posts stay in review, not scheduled.

Use the organic posting agent or VanX/GHL social planner handoff for completed assets. A completed asset should include the video, caption, destination channels, content pillar, CTA, and recommended publish slot.

Recommended File Manifest

For multi-clip or batch uploads, create or update a manifest.json alongside the project.

{
  "project_type": "multi_clip_merge",
  "clip_order": ["clip_001.mov", "clip_002.mov"],
  "caption_intent": "show demonstration after front-camera hook",
  "cta": "comment START",
  "publishing_status": "ready_for_queue",
  "preferred_channels": ["instagram_reel", "facebook_reel"],
  "approval_required": true
}

Useful Open-Source Patterns

Use established open-source patterns as reference, not as mandatory dependencies.

NeedUseful Reference Pattern
Silence and jump-cut automationWyattBlue/auto-editor style audio/silence-based cutting.
Python compositing and deterministic editsZulko/moviepy style programmable video operations.
Caption generationWhisper plus FFmpeg subtitle burn-in patterns such as m1guelpf/auto-subtitle.
Vertical short-form assemblyFFmpeg filter graphs for crop, scale, concat, drawtext, loudness, and export.

Read references/github_video_editing_patterns.md when choosing tools or editing patterns for a new automation path.

Bundled Script

Use scripts/merge_vertical_clips.py when a simple deterministic multi-clip merge is needed. It creates a normalized 9:16 MP4 using FFmpeg concat after standardizing clips.

Example:

python /home/ubuntu/skills/automated-video-editor/scripts/merge_vertical_clips.py \
  --inputs clip1.mov clip2.mov \
  --output merged_reel.mp4

Approval Rule

Never post a newly edited video live if the user is actively reviewing audio, visual quality, caption accuracy, or destination accounts. Publishing requires explicit approval unless a previously approved recurring automation rule exists for that exact content category and destination.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.