More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Video Transcript Carousel Post Architect

    1

    Turn long-form video transcripts into concise LinkedIn/Instagram carousel drafts with hard slide-length limits, source traceability, and designer-ready visual directions.

    Free

    1 useSecurity scanned
    Video Transcript Carousel Post Architect

    Video Transcript Carousel Post Architect

    Example session with this skill installed

    Turn founder-webinar.vtt into an 8-slide LinkedIn carousel.

    Audience: B2B founders and growth teams.

    Goal: teach one practical lesson from the video and end with a “Save this” CTA.

    Rules

    • do not summarize the whole webinar;
    • choose one strong thesis;
    • extract only the best supporting ideas;
    • keep slide copy extremely concise;
    • use hard character limits;
    • cite the source cue IDs for every slide;
    • add one concrete designer direction per slide;
    • do not invent statistics, virality claims, or results.
    • Read your context and instructions
    • Compiled the video transcript carousel
    • Generated a 4-slide presentation

    Carousel architecture complete

    Transcript duration: 47m 18s
    Source cues processed: 864
    Chosen angle: Why most repurposed content feels repetitive
    Hook framework: Contrarian
    Slides: 8
    Slides requiring review: 0

    Slide 1 — Hook

    Most repurposed content fails before the writing starts.

    You are trying to keep too many ideas.

    Designer direction:
    Large headline. Show a messy transcript stack collapsing into one clean card.

    Source cues: C00421–C00435

    Slide 2 — Problem

    A transcript is not a carousel.

    Video can carry context. A carousel has to earn every swipe.

    Designer direction:
    Split-screen: dense transcript on the left, one clean card on the right.

    Slide 3 — Insight

    Choose one thesis first.

    Pick the single idea worth remembering. Everything else either supports it or gets cut.

    Designer direction:
    Highlight one sentence while fading five secondary notes.

    Slide 8 — CTA

    Turn one video into one sharp idea.

    Use the transcript as source material—not as the final structure.

    CTA: Save this for your next carousel.

    Validation

    • Slide count: PASS
    • Headline limits: PASS
    • Body limits: PASS
    • CTA limit: PASS
    • Source cues: PASS
    • Designer directions: PASS
    • Duplicate headlines: PASS
    • Unsupported hype: PASS

    Files generated

    • content_angle_map.json
    • carousel_draft.md
    • carousel_slides.csv
    • designer_brief.md
    • validation_report.json
    • summary.json

    video-transcript-carousel-post-architect-deck.pptx

    PPTX · 4 slides

    Generated

    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

    The problem

    Long-form videos are packed with useful ideas, but turning them into a strong LinkedIn or Instagram carousel requires more than summarization.

    Transcript-first workflows often create dense slides, weak hooks, repeated ideas, and design briefs that are painful to execute.

    What it does

    Video Transcript Carousel Post Architect converts raw VTT, SRT, TXT, or Markdown transcripts into a visual-first carousel draft.

    • Parses and cleans long-form transcripts
    • Identifies the strongest single content angle
    • Extracts source-grounded “eureka” points
    • Maps the idea into a fixed slide architecture
    • Enforces hard character limits by slide type
    • Generates designer instructions for every card
    • Preserves source cue IDs for traceability
    • Detects duplicate slides and unsupported hype
    • Exports both Markdown and CSV-ready slide structures

    Why this beats prompting it yourself

    A generic prompt tends to summarize the transcript.

    This skill forces a staged workflow:

    Transcript → Angle → Eureka Points → Slide Architecture → Draft → Design Direction → Validation

    The result is built for visual storytelling, not for reproducing a spoken monologue on cards.

    Hard limits by design

    Every slide is validated against configured editorial limits for headlines, body copy, and CTA length.

    Built for real content teams

    Each slide includes headline, body, CTA, visual direction, layout hint, source cue IDs, and validation status so it can move directly from strategist to designer.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for LinkedIn.

    Does not generate image files. Requires VTT/SRT/TXT/MD inputs. Accuracy of source cues depends on the quality of timestamps in the provided transcript.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 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

    1 use

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Software
    Python

    Permissions

    Terminal / Shell
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Unlike generic AI summaries, this skill enforces strict character limits and visual-first layouts, ensuring your slides are designed for readability rather than being overloaded with text.

    The skill outputs structured Markdown and CSV files, which are designed for easy import into design tools like Figma or Canva, as well as project management platforms.

    Yes, the skill is specifically engineered to process VTT, SRT, and TXT files, using timestamps to ensure every slide is accurately grounded in your original video content.

    You receive the complete agentic workflow, including the multi-stage logic for transcript parsing, angle mapping, and slide architecture, ready to deploy in your preferred AI environment.

    While it identifies the best 'eureka' moments and provides layout hints, this skill focuses on editorial structure and copywriting; it does not generate the final image files or graphics.

    The architect supports standard LinkedIn and Instagram carousel frameworks, typically ranging from 6 to 12 slides, optimized for the specific engagement patterns of each platform.

    New in Social Media

    Free