plain-to-meta: Plain Language to Domain Meta-Knowledge Keys

    1

    Translates colloquial "plain-talk" requests into high-density professional prompts using industry-standard Meta-Knowledge.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    plain-to-meta: Plain Language to Domain Meta-Knowledge Keys

    Example session with this skill installed

    My AI-generated product images look like plastic and the movements in the video are stiff. Help me make it look like a real professional movie.

    • Read your context and instructions
    • Compiled the plain-to-meta

    I have analyzed the visual "stiffness" and "plasticity" in your current output. These are classic symptoms of neglecting physical weight and lighting physics in generated media.

    Meta-Knowledge Diagnosis & Prompt

    🔑

    Activated Meta-Knowledge Keys: Disney's 12 Principles of Animation + Cinematic Three-Point Lighting + Subsurface Scattering (SSS)
    💡

    Application of Industry Consensus: We will move away from linear motion-interpolation toward organic physics-based movement and replace flat digital textures with light-absorbing material shaders.

    🚀 Professional Prompt (Copy & Use)

    # Role: Senior Cinematographer & Technical Director
    
    ## Meta-Knowledge Keys
    Please execute this generation with strict adherence to:
    -
    

    Disney's 12 Principles: Specifically 'Squash and Stretch' and 'Anticipation'. Every movement must have a non-linear ease-in/ease-out curve to simulate physical inertia and weight.

    -

    Material Physics: Enable 'Subsurface Scattering' for skin/surfaces to eliminate the "plastic" look. Light must penetrate and diffuse within the surface rather than reflecting off a hard shell.

    -

    Lighting Hierarchy: Implement 'Three-Point Lighting' (Key, Fill, Back) with high-contrast ratios to create depth and separate the subject from the background.

    Task Specification

    Re-render the product scene focusing on the physical interaction between the object and the floor. The camera should follow a 'Parallax' movement rather than a simple pan.

    Quality Redlines

    • NO linear velocity in movements; all motion must follow arc paths.
    • NO uniform lighting; shadows must have distinct penumbras.
    • 自检标准: The object must feel like it has mass (kg) when it stops moving.

    Next steps

    1. Paste this prompt into your video generator (Sora/Runway) or image tool (Midjourney/Flux).
    2. If the motion is still too subtle, request "Exaggerated Anticipation" for the initial frame.
    3. For texture issues, add "Micro-surface roughness (Roughness Map)" to the prompt.

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

    About this skill

    This skill bridges the gap between vague, colloquial user requests and high-performance AI outputs. When a user provides "plain-talk" instructions or complains about mediocre results, the skill functions as a professional translator. It bypasses shallow prompt engineering techniques by identifying the root problem and matching it with "Meta-Knowledge Keys"—specific industry terms, academic principles, and hidden professional consensuses. By using these high-density triggers, it activates the model's underlying training in specialized domains like UI/UX, software architecture, data science, and cinematography.

    What it does

    • Root Cause Diagnosis: Strips away conversational fluff to identify the specific professional discipline where the user's pain resides.
    • Meta-Knowledge Mapping: Matches vague requests (e.g., "make it look high-end") to concrete industry standards (e.g., "Swiss International Style").
    • Professional Prompt Compilation: Generates high-density prompts using the "4-Step Core Engine" for use in external tools like Midjourney or Claude.
    • Direct Execution: Refactors code, UI layouts, or business copy by injecting expert constraints without requiring manual prompt building.
    • Socratic Refinement: Diagnoses ambiguous requests by offering multiple professional schools of thought to clarify user intent.

    How it works

    1. Intent Detection: The skill automatically selects between direct execution, prompt compilation, or diagnostic questioning.
    2. Domain Retrieval: It scans built-in reference modules covering software engineering, visual arts, business strategy, and probability.
    3. Key Synthesis: It selects up to three "orthogonal" professional keys (e.g., combining UX flow with visual hierarchy) to solve the problem from multiple angles.
    4. Final Output: Delivers either the completed task or a structured prompt including role definitions, methodology anchors, and quality redlines.

    Frameworks & tools

    The skill is grounded in foundational principles from Edward Tufte (data viz), Don Norman (design), Robert McKee (storytelling), and Martin Fowler (software architecture). It utilizes specialized reference modules for UI/UX, Vibe Coding, and animation standards.

    Why this beats prompting it yourself

    Standard prompts often fail because they lack the specific terminology needed to trigger high-dimensional model reasoning. This skill replaces "try harder" instructions with precise industry keys, resulting in significantly higher information density and output quality.

    Use cases

    • UI/UX Design: Fix cluttered interfaces using Progressive Disclosure and F-Shaped Patterns.
    • Software Engineering: Refactor spaghetti code using SOLID principles and State Management patterns.
    • Content Strategy: Transform generic marketing copy into high-conversion drafts using the PAS framework.
    • Data Analysis: Replace vague predictions with Monte Carlo simulations for quantitative accuracy.

    Known limitations

    Restricted to a maximum of three Meta-Knowledge keys per task to avoid instruction bloat. It requires clear domain context for the most accurate key matching.

    Maximum of three meta-knowledge keys per request. Explicitly avoids generic buzzwords. Requires user to specify a domain if the colloquial input is extremely ambiguous.

    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 forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 7 days ago

    • Free with an Agensi account

    Requires

    Git

    Permissions

    Terminal / Shell
    Listed8 days ago

    What's inside

    Frequently Asked Questions

    This skill acts as a professional bridge that converts vague, conversational requests into high-density prompts. It solves the problem of "mediocre outputs" by identifying the specific industry principles and academic frameworks needed to trigger an AI's expert-level training.

    The skill is designed to work with all major LLMs (like GPT-4, Claude, and Gemini) and specialized generative tools like Midjourney. It outputs both direct results and structured prompts that you can copy-paste into your preferred AI environment.

    Upon purchase, you receive the full 'plain to meta' skill package, including the core logic engine, the domain retrieval modules (UI/UX, Software, Business, etc.), and the Socratic refinement framework for diagnosing ambiguous requests.

    No complex setup is required; once added to your agent workspace, it automatically begins scanning your input for "plain-talk" patterns. It functions as a background layer that you can trigger whenever a request requires professional-grade precision.

    Yes, the developer provides periodic updates to the Meta-Knowledge mapping to include emerging industry standards, such as new 'Vibe Coding' patterns or updated software architecture principles, ensuring the skill stays current.

    To prevent 'instruction bloat' and maintain output quality, the skill limits itself to three orthogonal professional keys per task. This ensures the AI stays focused on the most impactful professional constraints without becoming overwhelmed.

    New in Prompt & Skill Engineering