Reproducible Launch Kit

    1

    Build launch assets from the repo through a reproducible pipeline: sourced evidence, generated storyboard, deterministic capture.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Reproducible Launch Kit

    Example session with this skill installed

    Generate a launch kit for version 2.4.0 based on the current repo. I have a 30-second budget. The last tag was v2.3.0. Use the bench/cold-start.json for metrics.

    • Read your context and instructions
    • Compiled the reproducible launch kit

    I have initialized the launch pipeline for v2.4.0. I extracted 12 new features from commits and a 14% improvement in cold-start latency from your benchmarks. The storyboard is constrained to 29.5 seconds across 5 scenes.

    Launch Kit Manifest

    ArtefactStatusPath
    Evidence LedgerGenerated (18 facts)artifacts/evidence.json
    StoryboardTimed (29.5s total)artifacts/storyboard.json
    Raw ClipsRecorded (Playwright)clips/*.webm
    Final VideoAssembled (1080p)dist/launch_v2.4.0.mp4
    Channel CopyReady (X, LinkedIn)dist/copy_drafts.txt

    Script Summary

    1. Scene 1 (0-5s): Cold start performance. Caption: "14% faster startup (240ms)."
    2. Scene 2 (5-15s): New Workspace Dashboard UI. Caption: "Unified view for all projects."
    3. Scene 3 (15-25s): Batch Processing API. Caption: "Process 1k records in < 2s."
    4. Scene 4 (25-29.5s): Outro & Version Tag. Caption: "v2.4.0 available now."

    Next steps

    • Review dist/copy_drafts.txt for the "what it does not do" disclaimer.
    • Run python scripts/claim_check.py evidence.json draft.md to validate your external blog post.
    • Inspect dist/launch_v2.4.0.mp4 to ensure the deterministic UI capture meets visual standards.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Regenerate the whole launch kit from the repo after any UI change.

    Turn a shipped project into launch assets - demo video, changelog and channel copy - through a reproducible pipeline where every scene is scripted, every capture is deterministic and every number traces back to evidence. Use when announcing a release, recording a product demo, preparing a launch, or when a demo video has to be re-recorded after a UI change.

    The pipeline is five stages with typed hand-offs: collect evidence from git, CI reports and benchmarks; gate the draft so no unsourced number survives; generate a timed storyboard under a duration budget; capture each scene with a frozen clock, a seeded random source and a pinned fixture; assemble with subtitles from the same storyboard. Any stage can be re-run alone, and two runs on the same commit produce the same assets.

    Includes an EXPERT.md reference (exact parameters, thresholds, failure diagnosis). Tested scripts: scripts/assemble.sh, scripts/claim_check.py, scripts/collect_evidence.py, scripts/record_demo.mjs, scripts/storyboard.py.

    It will not invent a benchmark, fake UI state, or write a claim you have not measured: thin evidence produces a short honest kit, not a padded one.

    Requires ffmpeg and Playwright installed. Cannot synthesize data or UI states not present in provided fixtures. Does not support video editing beyond concatenation and caption burning.

    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 any payment.

    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

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 28 days ago

    Requires

    Python
    Git

    Permissions

    Terminal / Shell
    Browser
    Read Files
    Write Files
    Listed28 days ago

    What's inside

    Frequently Asked Questions

    This skill treats marketing assets like code by creating a repeatable pipeline that links video frames and copy directly to repository data, eliminating the need to manually re-record demos every time the UI changes.

    The kit requires Python 3, Node.js (for Playwright), and ffmpeg; it is designed to run in any environment where these tools are available, including local developer machines and standard CI/CD runners like GitHub Actions.

    You receive the complete orchestration logic, including the evidence collection scripts, the deterministic recording suite, and the automated video assembly pipeline, along with documentation for integrating your specific repo data.

    Unlike manual prompting, this skill uses 'frozen clocks' and pinned fixtures to ensure every recording is bit-identical, preventing the visual jitter or timing inconsistencies typical of manual screen captures.

    The kit is designed to be framework-agnostic and works with any codebase that can export data to standard formats like JSON or JUnit XML, making it compatible with both web-based and backend-heavy projects.

    New in Workflow Automation