Works with the AI tools you already use
Claude Code
Cursor
Codex CLI
Muse
OpenClaw+21 moreClaude CodeCursorCodex CLIMuseOpenClaw
Manus
Grok
Grok Bot+18 agentsVideo Transcript Repurposing Engine
Turn SRT/VTT transcripts into source-traceable LinkedIn posts, X threads, blog content, newsletters, and timestamped Shorts/Reels clip plans through a staged repurposing workflow.
$5
Video Transcript Repurposing Engine
Example session with this skill installed
Repurpose saas-webinar.vtt into a content package for our B2B SaaS founder brand.
First clean the transcript and build a content map. Do not start writing platform posts until the strongest ideas and angles are identified.
Create
- 3 LinkedIn posts
- 2 X threads
- 1 blog draft
- 1 newsletter
- 6 short-form clip recommendations for Reels/Shorts
For every clip, give the exact start/end timestamp from the transcript and the source cue IDs.
Tone: practical, sharp, founder-led, no motivational fluff, minimal emojis.
Do not invent statistics, customer results, or quotes.
Write each asset to a separate local file and generate an asset manifest.
- Read your context and instructions
- Compiled the video transcript repurposing
- Generated the data export
Repurposing package complete
Source: saas-webinar.vtt
Transcript duration: 58m 42s
Subtitle cues: 1,106
Distinct content angles: 9
Short-form clip candidates: 6
Unclear claims flagged: 2
The transcript was processed in stages before any platform copy was generated.
Strongest content angles
- Why founder-led distribution compounds faster than campaign-only marketing
- Content creation vs. building a distribution system
- Turning customer questions into recurring content
- Why most repurposed content feels repetitive
- How to decide whether an idea deserves a standalone post
- Turning one webinar into a multi-platform content system
Each idea in content-map.json includes its original transcript cue IDs and timestamp range.
Assets generated
- linkedin/post-01.md
- linkedin/post-02.md
- linkedin/post-03.md
X
- x/thread-01.md
- x/thread-02.md
Blog
- blog/article.md
- blog/outline.md
Newsletter
- newsletter/email.md
Short-form video
- shorts/clip-plan.csv
- six timestamped editor briefs
Example clip recommendation
CLIP-03 — Stop treating repurposing as copy-paste
Start: 00:31:14.200
End: 00:32:01.840
Duration: 47.6 seconds
Source cues: C00588–C00603
Why it works
The speaker opens with a direct criticism, explains the problem through one self-contained example, and finishes with a practical reframe.
Suggested on-screen hook
“Repurposing ≠ posting the same idea everywhere.”
QA completed
- Clip timestamps validated against original subtitle cues
- No invented quotes or statistics
- LinkedIn and X use different structures
- Duplicate hooks removed
- Ambiguous transcript claims flagged
Output
deliverables/
- content-map.json
- linkedin/
- x/
- blog/
- newsletter/
- shorts/
- validation/asset-manifest.json
All assets were derived from the supplied transcript and should receive final brand/editorial review before publishing.
video-transcript-repurposing-engine.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
The problem
A 45–60 minute webinar, podcast, or interview may contain weeks of useful content—but turning it into platform-ready assets manually means rereading the transcript, finding hooks, adapting tone, locating clip timestamps, and rewriting the same ideas again and again.
What it does
Video Transcript Repurposing Engine turns one SRT or VTT transcript into a structured content system.
- Parses and cleans subtitle files while preserving timestamps
- Builds a source-grounded content map before writing platform copy
- Extracts distinct content angles instead of repetitive variations
- Generates dedicated assets for LinkedIn, X, blogs, newsletters, and more
- Finds timestamped short-form clip candidates for Reels and Shorts
- Validates clip timestamps against original transcript cues
- Writes every asset into separate local files
- Creates a manifest for source traceability and editorial QA
Why this beats prompting it yourself
A one-shot prompt like “turn this transcript into five types of content” often creates shallow, repetitive assets and loses track of where claims came from.
This skill forces a staged workflow:
Transcript → Content Map → Angles → Clips → Platform Assets → QA
Each important idea stays connected to its original transcript cues and timestamps.
Built for real content workflows
LinkedIn posts are not copied X threads. Blog articles are not stitched social captions. Short-form video recommendations include actual source timestamps so editors know exactly where to cut.
Source fidelity first
The workflow does not invent quotes, statistics, examples, customer results, or timestamps. Ambiguous claims are flagged for editorial review instead of silently strengthened.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 13 days ago
- Passed all security checks, Safe to install