- Home
- Skills
- Workflow Automation
- short form clipper
short form clipper
Automated video clipper for turning long-form content into captioned, high-retention Shorts and Reels using FFmpeg.
Free
Works with the AI Agents you already use
short form clipper
Example session with this skill installed
Clip the most exciting 30 seconds from /home/user/video/podcast.mp4 focusing on 'market crash', use the retentive preset, and save to /home/user/clips.
- Read your context and instructions
- Compiled the short form clipper
- Generated the document
I have processed the video and generated a high-retention clip focusing on the 'market crash' segment.
Clip Selection & Audit
| Metric | Value |
|---|---|
| Source Range | 12:45 - 13:15 |
| Target Aspect | 1080x1920 (Vertical) |
| Preset | retentive (Hook, Flash, Punch, 6-word cards) |
| Retention Score | PASS (Longest static stretch: 3.2s) |
| Output Path | /home/user/clips/podcast_clip_1.mp4 |
# Execution Command Used
node "$SKILL_DIR/scripts/clip/clip.mjs" auto "/home/user/video/podcast.mp4" \
--focus "market crash" \
--count 1 \
--max-seconds 30 \
--preset retentive \
--out "/home/user/clips" \
--poster
Next steps
- Inspect the generated
/home/user/clips/podcast_clip_1.jpgposter to verify caption placement. - Run
node "$SKILL_DIR/scripts/clip/clip.mjs" retain /home/user/clips/podcast_clip_1.mp4for a full frame-by-frame audit. - Use the generated
.txtsidecar for the TikTok/Reels description.
podcast_clip_1.jpg
PDF · document
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop manually scrubbing through podcasts to find clips. This skill bundles a local Node.js and FFmpeg utility to automate the entire short-form video production pipeline, from moment selection to final render.
What it does
- Automated Clipping identifies high-impact moments in long videos using transcript heuristics and keyword focus.
- Dynamic Captions burns karaoke-style or boxed captions directly into the video with customizable fonts and colors.
- Hard-Edit Effects applies visual punches, flashes, and shakes to maintain viewer retention.
- Audio Processing removes silences, trims lead-ins, and ducks background music with beat-sync capabilities.
- Multi-Format Rendering generates vertical, square, or horizontal variants ready for TikTok, Reels, and Shorts.
- Retention Auditing analyzes finished clips for static stretches, caption load, and timing gaps.
How it works
- Intake the source via an absolute local path or URL to extract the transcript.
- Plan the selection by letting the tool score and propose windows based on your focus keywords.
- Configure the look using built-in presets like
camp,bold, orretentive, or define custom flags for effects. - Render the MP4 files locally using the bundled Node.js script and FFmpeg.
- Audit the output with a retention check to verify the clip meets platform standards.
Frameworks & tools
Built for Node.js 18+ environments. It utilizes FFmpeg and FFprobe for all media processing, with optional yt-dlp support for remote URL ingestion.
Why this beats prompting it yourself
Prompting an AI to "describe a clip" still leaves you with hours of manual editing. This skill provides the actual execution engine, turning high-level editorial decisions into precise FFmpeg commands without needing a cloud subscription or manual timeline work.
Use cases
- Convert hour-long podcast episodes into a series of 30-second TikToks.
- Add professional karaoke captions and progress bars to raw talking-head footage.
- Clean up webinar recordings by automatically removing dead air and filler.
- Batch-process video archives into platform-specific aspect ratios with burned-in branding.
Known limitations
Does not support AI-based face tracking or subject reframing. Framing is limited to center crop or blurred padding. Requires absolute file paths for all local inputs.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Workflow Automation.
No face-tracking/reframe (center crop only). No speed ramps or dissolves. Requires Node 18, FFmpeg, and absolute local paths. Moment selection requires a caption track.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 2 days ago
- Free with an Agensi account
- Software
- hyperframes
Node.js