SkillAgentSearch skills...

net-new-video-editor

Turn newly recorded talking-head footage into review-ready vertical video drafts with an explicit edit plan, deterministic FFmpeg rendering, captions, hook cards, audio normalization, and visual QA.

Install / Use

npx skills add ericosiu/ai-marketing-skills --skill net-new-video-editor

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

91/100

Category

Automation

Supported Platforms

Universal

Our assessment of net-new-video-editor

net-new-video-editor scores 91/100 on our quality scale, 1009th of 2,790 Automation skills we index (top 37%).

Its SKILL.md is 4.3 KB long, well organised into 8 sections with 5 code examples: a solid amount of guidance for an agent.

With 3,573 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
26/30
Structure
20/20
Description
15/15
Adoption
15/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so net-new-video-editor is actively maintained.
  • Our last check on 2026-10-29 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-06. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

net-new-video-editor compared with similar skills

All 4 of these similar skills score higher than net-new-video-editor; compare them before choosing.

SkillScoreStarsUpdatedFormat
net-new-video-editor (this skill)by ericosiu913.6k55d agoSKILL.md
Agent-Reachby Panniantong100112.3k8d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.7k7d agoCLAUDE.md
Scraplingby D4Vinci100103.6k2d agoMCP Server

Frequently asked questions

How do I install net-new-video-editor?
Run npx skills add ericosiu/ai-marketing-skills --skill net-new-video-editor. The install tabs above show the steps for each supported agent.
Which AI agents does net-new-video-editor work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is net-new-video-editor safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is net-new-video-editor still maintained?
The repository was last updated about 2 months ago, so net-new-video-editor is actively maintained.

name: net-new-video-editor description: Turn newly recorded talking-head footage into review-ready vertical video drafts with an explicit edit plan, deterministic FFmpeg rendering, captions, hook cards, audio normalization, and visual QA. Use for original Instagram Reels, TikTok videos, YouTube Shorts, LinkedIn videos, founder-led recordings, multiple takes of a new script or idea card, or requests to automate the first video-editing pass. Do not use to mine clips from long-form source videos.

Net-New Video Editor

Create a reversible first edit from fresh recordings. Keep creative decisions in JSON and pixel operations in the bundled renderer.

Preamble

Run from the repository root when the optional shared telemetry helpers are present:

python3 telemetry/version_check.py 2>/dev/null || true
python3 telemetry/telemetry_init.py 2>/dev/null || true

Remote telemetry is opt-in and never includes content, file paths, repository names, or credentials.

Establish the package

Read references/project-contract.md. Locate the exact source recordings, transcript, idea card or brief, proof assets, and screen recordings. Never substitute another recording, brand, account, or asset library.

Initialize a new project only when the destination is clear:

python3 scripts/net_new_video_editor.py init --project <project-dir>

Copy or point only user-authorized inputs into the generated package. Preserve originals.

Inspect before editing

Run:

python3 scripts/net_new_video_editor.py inspect --project <project-dir>

Review intake-report.json. Stop when the package has no playable take, the requested target does not match the supplied footage, or required external assets are missing.

Build the edit plan

Use the transcript and brief to create edit-plan-clean.json. Treat the spoken hook and claim boundaries as ground truth.

  • Select one source take explicitly.
  • Keep segment order intentional and timestamps within the source duration.
  • Remove clear false starts, long dead space, and isolated filler only when the cut remains natural.
  • Preserve breaths that help meaning.
  • Put the hook on screen for at most five seconds.
  • Use captions in short readable phrases.
  • Add proof or screen inserts only when supplied and relevant. The bundled renderer handles the base assembly; add complex overlays in a separate, documented pass.
  • Normalize speech without clipping.

For a second version, copy the plan to edit-plan-aggressive.json and make only named retention edits. Do not silently change factual claims.

Validate each plan:

python3 scripts/net_new_video_editor.py validate --project <project-dir> --plan <plan.json>

Render deterministically

Run the renderer from this skill directory:

python3 scripts/net_new_video_editor.py render \
  --project <project-dir> \
  --plan <plan.json>

The renderer trims paired audio and video, concatenates the selected segments, creates a center-safe 9:16 frame, rasterizes captions and the hook card with Pillow, composites them with FFmpeg, normalizes audio, writes H.264/AAC MP4, and creates three QA frames plus qa-report.json.

Use --dry-run to inspect the FFmpeg command. Use --force only when replacing the exact derived export is intended.

Review the output

Inspect the exported MP4, all three QA frames, qa-report.json, and the plan diff between variants. Verify:

  • audio and mouth movement stay synchronized after every cut;
  • no word starts or ends abruptly;
  • captions match the speech and stay inside safe margins;
  • the crop keeps the speaker visible;
  • the hook is legible and repaid by the video;
  • loudness is consistent and peaks do not distort;
  • every proof insert and numerical claim has a supplied source;
  • the export is 1080x1920 H.264/AAC unless the brief requires another format.

Return the plan, export paths, QA evidence, and any required pickups. Never publish, upload, delete originals, or overwrite an approved master without current explicit approval.

Completion states

  • DONE: both render and QA pass, and the review artifacts exist.
  • DONE_WITH_CONCERNS: the draft is usable but a named creative or source concern remains.
  • NEEDS_CONTEXT: a take, transcript, brief, or approved asset is missing.
  • BLOCKED: FFmpeg, source access, or format validation prevents a safe render.

Related Skills

View on GitHub
GitHub Stars3.6k
CategoryAutomation
Updated1mo ago
Forks684

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions