More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    nogyaan

    1

    Studio-grade video ad director that orchestrates cinematic scripts and SOTA diffusion prompts via an interactive DP suite.

    Free

    Security scanned
    nogyaan

    nogyaan

    Example session with this skill installed

    use nogyaan to direct a dev-product-launch ad for "GitStream", a tool that automates PR reviews, focusing on developer burnout. preset-dev-product-launch.

    • Read your context and instructions
    • Compiled the nogyaan
    • Generated the image

    The nogyaan Workflow: Stop Prompting, Start Directing

    AI video models like Kling, Runway Gen-3, and Sora are incredibly powerful, but the current workflow is fundamentally broken. If you ask a standard AI chat to "write a video script," it dumps a massive paragraph that mixes three camera cuts, two locations, and a voiceover into a single shot.

    The result? The camera spins wildly, the actor’s face melts, and their clothes change in every single clip.

    nogyaan fixes this by flipping the workflow. It is an open-source MCP server that turns Claude into your personal Director of Photography. You stop writing heavy technical prompts, and you step into the Director's Chair. You make the creative choices; nogyaan handles the brutal camera physics.

    Here is what it feels like to use it.

    Step 1: The Writers' Room (Branch & Prune)

    You start by giving Claude a simple brief: your product and your goal.
    Instead of spitting out a generic 4-scene script, Claude pitches you 3 distinct opening scenes.

    • Option 1: A heartfelt, emotional hook.
    • Option 2: A gritty, high-contrast thriller vibe.
    • Option 3: A fast-paced, kinetic edit.

    You simply reply with a single keystroke: 1, 2, or 3.

    The Magic: The moment you make your choice, nogyaan physically deletes the rejected ideas from the state machine. This keeps your context window perfectly clean so Claude never hallucinates rejected ideas into your later scenes.

    Step 2: Locking the Cast & Set

    Once your story is locked, nogyaan asks you to lock your visual assets.
    It tags your primary character as @CHAR_01, your background as @BG_01, and your product as @PROD_01.

    Instead of typing out the character's description over and over, nogyaan generates a strict, highly detailed prompt for Midjourney or Flux. You use this to generate your "Base Image," which ensures your actor looks exactly the same from Scene 1 to Scene 4.

    Step 3: The Director's Suite (The Secret Sauce)

    This is where standard prompt engineering fails, and where nogyaan shines. For every scene in your locked story, Claude acts as your Director of Photography and pitches you 3 ways to shoot it:

    • The Auteur: Slow, methodical, cinematic lighting.
    • The Kinetic: Fast push-ins, dynamic movement.
    • The Theatrical: Dramatic, high-contrast staging.

    You press a single number to pick the vibe. nogyaan takes your choice and instantly compiles a dense, copy-paste ready "SOTA (State of the Art) Payload" for Kling or Runway.

    It forces two strict physical rules into the prompt:

    1. Single-Vector Cameras: It strips out multiple cuts. The camera is forced to move on one axis (e.g., "slow continuous dolly push-in"), which stops the AI video model from morphing the environment.
    2. The Temporal Handshake: It maps the physical room. The exact physical exit-frame of Shot 1 is hardcoded as the entry-frame for Shot 2. This creates an Ingress/Egress match-cut, allowing your clips to stitch together seamlessly in the edit.

    Step 4: The Live Blueprint & Export

    When you finish making your choices, you are not left scrolling through a messy chat log.

    nogyaan automatically updates a premium, monochrome Director's Workbench running locally on your machine at http://localhost:4321.

    • On the left, you see your locked story and global themes.
    • On the right, you see your copy-paste ready SOTA payloads with your asset tags clearly highlighted.

    Screenshot 2026-11-06 170928


    With one click, you can

    Export to PDF. nogyaan bypasses screenshots and generates a native, selectable-text PDF Blueprint. You can share this flawless Director's Treatment with clients, or open it on your iPad while you drop the prompts into Runway.

    Screenshot 2026-11-06 182734

    The Bottom Line

    You shouldn't be typing out "35mm anamorphic, slow pan left, shallow depth of field" while trying to figure out a good story. nogyaan separates the art from the physics. You bring the human taste. The machine does the technical heavy lifting.


    1793982007557-9p6w.png

    PNG · 1536×1024

    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

    Producing high-fidelity video ads requires bridging the gap between creative storytelling and technical diffusion physics. This skill acts as an Executive Creative Director and DP, orchestrating the entire production pipeline from initial brief to SOTA video prompts without the typical wall-of-text fatigue. It solves the problem of "prompt drift" and disjointed scenes by enforcing strict temporal handshakes and spatial anchoring between shots.

    What it does

    • Multi-Framework Directing adapts scripts for Indian D2C emotional storytelling, high-craft developer product launches, or high-retention TikTok UGC.
    • Decision Branching manages narrative flow through a 1/2/3/R protocol, ensuring user control at every plot twist and scene catalyst.
    • Interactive DP Suite pitches three distinct visual personas (Auteur, Kinetic, Theatrical) for every shot before compiling technical payloads.
    • SOTA Physics Compilation generates dense diffusion prompts for Kling, Runway, and Sora with single-vector camera movements and spatial anchoring.
    • Asset Locker Management persists character, background, and product consistency throughout the entire DAG session.

    How it works

    1. Intake Gate: Provide the brand name, product details, and emotional objective to initialize the campaign brief.
    2. Core Theme Selection: Choose from three abstract creative premises to lock the campaign's visual and emotional DNA.
    3. Narrative Branching: Progress through a 4-act structure (Setup, Catalyst, Twist, Climax) using single-keystroke inputs.
    4. Shot Direction: Review three human-readable visual pitches per shot and select one to generate the technical diffusion payload.

    Frameworks & tools

    Built for modern video diffusion workflows including Kling 3.0, Veo 3.1, Runway Gen-4.5/Gen-3, and Sora. It utilizes MCP tools for state persistence and a local director's treatment dashboard.

    Why this beats prompting it yourself

    Writing prompts for video is prone to character drift and impossible camera compound moves that break diffusion models. This skill enforces "temporal handshakes" where every shot's ending frame matches the next shot's start, ensuring professional continuity that manual prompting can't maintain.

    Use cases

    • D2C Brand Films: Creating emotional Hinglish-based narratives for the Indian market.
    • SaaS Product Launches: Directing cinematic "developer cinema" that visualizes technical pain points and solutions.
    • Social Ad Testing: Rapidly generating multiple high-hook UGC variations for vertical video platforms.

    Known limitations

    Requires specific MCP tool connectivity for state persistence. Does not support compound camera movements (e.g., pan-then-tilt) to maintain diffusion stability.

    Requires MCP tool support for state persistence. Limited to single-vector camera moves per shot. Mandatory intake flow requires three specific brand details to start.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Requires

    Cloudflare
    Anthropic
    OpenAI
    Googleapis
    Gstatic
    Tailwindcss
    Unpkg
    nogyaan
    Node.js
    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables
    Browser

    Allowed Hosts

    fonts.googleapis.com
    fonts.gstatic.com
    cdn.tailwindcss.com
    unpkg.com
    cdnjs.cloudflare.com
    api.anthropic.com
    api.openai.com
    Listedtoday

    What's inside

    Frequently Asked Questions

    nogyaan eliminates "prompt drift" by enforcing strict temporal handshakes and spatial anchoring between shots, ensuring your characters and environments remain consistent across the entire video sequence.

    The skill is optimized for top-tier diffusion models including Kling 3.0, Runway Gen-3/4.5, Veo, and Sora, providing technical payloads specifically tuned for their unique physics engines.

    The 1/2/3/R protocol is an interactive branching system that lets you steer the narrative flow, select visual personas (Auteur, Kinetic, or Theatrical), or regenerate options with single-keystroke inputs.

    You receive the full director's suite agent, access to the multi-framework directing styles (Indian D2C, SaaS, UGC), and the Asset Locker management system for session persistence.

    Yes, nogyaan requires specific Model Context Protocol (MCP) tool connectivity to enable state persistence, allowing the agent to remember your product and character details throughout the scriptwriting process.

    The skill includes an "Intake Gate" where you can specify brand voice and emotional objectives, including specialized frameworks for Hinglish-based emotional storytelling tailored for the Indian D2C market.

    New in Image & Video

    Free