AI Prompt Optimizer & Engineer

    1

    Transforms rough task ideas into structured, production-ready prompts for specific AI models.

    $5

    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 CLIDeepSeekDeepSeekMuseMuse+22 more

    AI Prompt Optimizer & Engineer

    Example session with this skill installed

    Refine this task: "Write a Python script to clean a CSV file." Target model: Claude 3.5 Sonnet.

    • Read your context and instructions
    • Compiled the ai prompt optimizer

    I have engineered a structured prompt for Claude 3.5 Sonnet to handle CSV cleaning tasks with high reliability.

    Engineered Prompt

    ROLE
    You are a senior Python developer specializing in robust, memory-efficient data engineering and pandas-based ETL pipelines.

    CONTEXT
    You are writing a Python script to clean a raw CSV file. The script needs to be production-ready, handling common data quality issues like missing values, incorrect types, and malformed rows. The user will provide a CSV schema or sample data.

    INSTRUCTIONS

    1. Import necessary libraries, prioritizing pandas for data manipulation and logging for error tracking.
    2. Load the CSV file at [FILE_PATH] using appropriate encoding and error handling for malformed lines.
    3. Identify and handle missing values based on the strategy: [MISSING_VALUE_STRATEGY].
    4. Validate and convert columns to the following data types: [COLUMN_TYPES_MAP].
    5. Remove duplicate rows and strip whitespace from all string-based columns.
    6. Implement a basic logging system to report the number of rows processed and any dropped records.
    7. Export the cleaned dataframe to a new CSV file at [OUTPUT_PATH].

    CONSTRAINTS
    Use Python 3.10+ syntax. Prioritize vectorized pandas operations over loops. Avoid hardcoding file paths; use the provided placeholders. Do not use generic try-except blocks without specific logging. Ensure the code is PEP 8 compliant.

    OUTPUT FORMAT
    A single, self-contained Python script (.py) including:

    • Import block
    • Configuration constants
    • A clean_data() function
    • A main execution block with basic CLI feedback

    EDGE CASES

    • If the CSV is empty, the script should log a warning and exit gracefully instead of crashing.
    • If a column specified for type conversion is missing, the script must raise a specific KeyError with a helpful message.
    • If the file encoding is not UTF-8, use chardet to detect the encoding before reading.

    Next steps

    1. Copy the prompt into a new Claude chat.
    2. Replace the [BRACKETED] placeholders with your specific file paths and cleaning rules.
    3. Run the generated code against a sample of your dataset.

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

    About this skill

    The problem

    Writing reliable prompts is time-consuming and often results in inconsistent AI outputs. Most users struggle to define clear constraints, leading to hallucinations or generic responses that require constant manual correction.

    What it does

    • Standardizes rough ideas into structured six-part production-ready prompts.
    • Builds model-specific instructions for ChatGPT, Claude, Gemini, or Midjourney.
    • Generates unambiguous numbered instructions and concrete constraints to prevent AI filler.
    • Identifies and handles potential edge cases for the target prompt to ensure reliability.
    • Includes bracketed placeholders for variable data to make prompts reusable.

    Why this beats prompting it yourself

    It replaces trial-and-error with a proven engineering framework. Instead of guessing how to structure a system prompt, you get a copy-paste deliverable that enforces strict boundaries and clear output formats, significantly reducing model drift.

    Use cases

    • Creating robust system prompts for LLM-powered applications.
    • Refining vague team requests into technical prompts for specific models.
    • Building reusable prompt templates for high-volume content workflows.
    • Engineering precise image generation prompts with defined styles and framing.

    Known limitations

    Requires a basic description of the task to function effectively. Will ask one clarifying question if the input is too vague to act upon.

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

    Requires a task description. If the input is extremely vague, the agent will ask a clarifying question rather than guessing. Defaulting to model-agnostic if no specific AI model is provided.

    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 2 months ago

    Permissions

    No special permissions declared or detected

    Listed2 months ago

    What's inside

    Frequently Asked Questions

    This skill takes a brief, rough task description and expands it into a professional, six-part structured prompt designed to minimize hallucinations and maximize output consistency.

    The skill is optimized to generate specific instruction sets for major models including ChatGPT, Claude, Gemini, and image generators like Midjourney.

    No technical setup is required; once you add the skill to your agent, you simply provide a task idea, and it immediately outputs a formatted, copy-paste ready prompt.

    You will receive the full Prompt Optimizer skill logic and a framework that generates reusable templates with bracketed placeholders for your future data variables.

    If your initial input is too vague, the skill is programmed to ask exactly one targeted clarifying question to ensure the final output meets production-grade standards.

    New in Prompt & Skill Engineering