More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Generative Image, Video and Media

    1

    This pack targets: Build image, video, avatar, dubbing and 3D pipelines with provenance and deepfake detection.

    $5.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Generative Image, Video and Media

    Generative Image, Video and Media

    Example session with this skill installed

    Fictional studio "Lumen Harbor Studio" must deliver a 30-second vertical (9:16) product teaser for an invented reusable water bottle, "Tidewell". Five shots, hosted video API for generation, local upscaling, delivery to social platforms. Budget ceiling invented at 40 currency units.

    • Read your context and instructions
    • Compiled the generative image video

    Video Pipeline Plan and Run Log

    Deliverable spec: 30 s / 9:16 / 30 fps / 1080x1920 / H.264
    Shot table

    | Shot | Back end | Takes | Chosen | Status |
    | S1 bottle on counter | hosted API, start frame = product photo | 3 | take 2 | pass |
    | S2 pour into glass | hosted API | 3 | take 1 | pass |
    | S3 hand lifts bottle | hosted API | 3 | none acceptable (hand morphs) | retry 1 of 2 |
    | S3 retry | hosted API, reframed to avoid hand | 3 | take 3 | pass |
    | S4 lid close macro | hosted API | 3 | take 2 | pass |
    | S5 logo end card | composited in editor, not generated (text legibility) | 0 | n/a | pass |

    Stage graph: keyframe -> generation -> selection -> upscale (chosen takes only) -> conform -> audio -> single encode -> QC.
    Job log: 16 jobs submitted, 1 retry on S3, spend 31 of 40 units (invented figures), no job exceeded the timeout.
    QC results: duration 30.0 s ok; fps 30 ok; black frames none; audio sync ok; loudness checked against platform target; continuity: bottle color drifted slightly in S4, fixed by color match.
    Provenance and disclosure: provider watermark retained, not claimed as ours; C2PA manifest with created action added at export; visible label placed in first second because content depicts a synthetic scene presented as product footage; legal position to be confirmed by producer against current regulation text.
    Delivery manifest: final.mp4, shot table, prompts, model/version per shot, cost log.

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

    About this skill

    The problem

    Studios and technical creators often need a repeatable process, not a one-off prompt. This pack targets: Build image, video, avatar, dubbing and 3D pipelines with provenance and deepfake detection.

    What's inside (10 skills, suggested learning order)

    1. Image Generation with Diffusion Models — Generate images via diffusion.
    2. ComfyUI and Diffusion Pipelines — Build image generation workflows.
    3. LoRA Training for Images — Customize styles and characters.
    4. Generative Video Pipeline Engineering — Orchestrate video models, upscaling and post-production in pipelines.
    5. AI Video Dubbing and Localization — Translate and dub content.
    6. Digital Avatars and Virtual Humans — Create synthetic presenters.
    7. 3D Models and AI 3D Generation — Generate 3D assets.
    8. AI for Augmented and Virtual Reality — Immersive experiences.
    9. Deepfake Detection — Identify synthetic media.
    10. Watermarking and Content Provenance — Implement C2PA and traceability.

    Why a skill pack instead of a one-off prompt

    Each skill gives the agent a defined trigger, step-by-step procedure and output format, so results are consistent across sessions and easier to review.

    How to use

    1. Install the pack in your SKILL.md-compatible agent.
    2. Ask for the task in plain language (for example: "generate images via diffusion").
    3. Review the output against the skill's quality checks before using it.

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

    Outputs are drafts that need human review; they are not professional, legal or financial advice. Tools, APIs and prices change; check current vendor documentation before relying on version-specific details. Quality depends on the context you give the agent (data, requirements, constraints). Instruction-only skills: they produce documents and plans, not running software.

    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

    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 8 days ago

    Permissions

    No special permissions declared or detected

    Listed8 days ago

    What's inside

    Frequently Asked Questions

    10 skills, each with SKILL.md and references/sources.md: Image Generation with Diffusion Models; ComfyUI and Diffusion Pipelines; LoRA Training for Images; Generative Video Pipeline Engineering; AI Video Dubbing and Localization; Digital Avatars and Virtual Humans; 3D Models and AI 3D Generation; AI for Augmented and Virtual Reality; Deepfake Detection; Watermarking and Content Provenance.

    Studios and technical creators.

    Agents that read the SKILL.md format. See the Compatibility note for what was actually tested.

    New in Image & Video