Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    prompt break

    2

    Convert short requests into structured six-part master prompts with completeness scoring and targeted gap analysis.

    $7

    /mo

    Subscription · cancel anytime

    Secure checkout via Stripe

    • Always the latest version
    • Delivered live to your agent via MCP
    • Cancel anytime, access ends at period end
    Security scanned
    prompt break

    prompt break

    Example session with this skill installed

    Turn this into a master prompt: "write a 30-day social media plan for my new vegan bakery in London with a budget of £500."

    • Read your context and instructions
    • Compiled the prompt break

    Master prompt · Completeness: 79%

    PartStatus
    ROLEassumed
    TASKfrom your input
    CONTEXTfrom your input
    REASONINGassumed
    STOP CONDITIONSassumed
    OUTPUTneeds input
    
    # ROLE
    Act as a Senior Social Media Strategist specializing in food and beverage launches. Prioritize organic engagement and community building over aggressive paid ads.
    
    # TASK
    Create a comprehensive 30-day social media plan for a new vegan bakery launch, ending with a ready-to-run execution summary.
    
    # CONTEXT
    What I know:
    - Business: Vegan bakery
    - Location: London
    - Budget: £500
    - Duration: 30 days
    - Primary Channels: [FILL IN: e.g. Instagram, TikTok]
    - Brand Voice: [FILL IN: e.g. playful, minimal, cozy]
    
    # REASONING
    The goal is to generate local awareness and foot traffic for the opening month. Explain the reasoning behind the content pillars chosen and ask first if any [FILL IN] is still open.
    
    # STOP CONDITIONS
    Consider it done only when:
    - Each of the 30 days has a specific content topic.
    - The £500 budget is allocated across specific activities.
    - A list of at least 10 local London hashtags is included.
    - The output includes a launch day countdown strategy.
    
    # OUTPUT
    A markdown table with columns for Day, Platform, Content Goal, and Budget Allocation.
    

    Answer these for a sharper prompt (optional):

    1. (CONTEXT) Which social media platforms are you focusing on?
    2. (CONTEXT) How would you describe the bakery's brand voice?
    3. (OUTPUT) Should the plan include specific caption drafts or just topics?

    You can answer any of these questions and I will update the prompt for you.

    $7/mo

    Subscription · always the latest version

    • Secure checkout via Stripe
    • Cancel anytime
    • Delivered live via MCP

    About this skill

    Writing high-quality prompts is a manual, iterative chore. This skill eliminates the guesswork by transforming vague, one-sentence requests into structured, six-part master prompts designed for high-performance AI interactions. It identifies missing data points, prevents hallucinations by marking gaps as placeholders, and applies a mathematical completeness score to every output.

    What it does

    • Structure prompts into six specific sections including Role, Task, Context, Reasoning, Stop Conditions, and Output format.
    • Identify gaps by marking missing facts with [FILL IN] markers instead of inventing details.
    • Quantify quality using a specialized formula to generate a completeness score based on user input.
    • Extract facts from the user's initial request to populate context without losing specific terminology or units.
    • Refine iteratively by generating up to six targeted clarifying questions to bridge information gaps.

    How it works

    1. Analyze input to determine the job type and domain, such as marketing, coding, or finance.
    2. Draft the master prompt by populating the six structural parts while preserving original facts.
    3. Audit completeness by tagging each section as derived from input, assumed, or needing input.
    4. Finalize output in a copy-paste ready code block alongside a status table and optional follow-up questions.

    Frameworks & tools

    This skill is framework-agnostic and works with any LLM that follows structured system instructions. It supports multilingual outputs, including specialized localization for Indonesian prompts.

    Why this beats prompting it yourself

    Writing prompts manually often leads to vague instructions and missing constraints that cause AI hallucinations. This tool enforces a rigorous six-part logic that ensures every AI task has clear stop conditions and specific reasoning, resulting in significantly higher output accuracy.

    Use cases

    • Drafting campaigns by turning a "new shop plan" into a full marketing strategy prompt.
    • Coding tasks by structuring "fix this bug" into a prompt with specific reasoning requirements.
    • Business admin by converting "make a spreadsheet" into a prompt with defined columns and data types.

    Known limitations

    This skill does not execute the tasks within the prompts; it only builds the instructions. It is limited to 5 [FILL IN] slots per iteration to prevent overwhelming the user.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.

    Does not perform the underlying task (e.g., won't write the code or plan). Limits missing facts to 5 [FILL IN] slots. Requires manual copying into other AI interfaces.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 15 days ago

    Permissions

    Write Files
    Terminal / Shell
    Browser
    Listed15 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the tedious trial-and-error of prompt engineering by converting vague requests into high-performance, six-part structured prompts. It specifically prevents AI hallucinations by identifying missing information and marking it with placeholders rather than guessing.

    This skill is framework-agnostic and compatible with any LLM, including ChatGPT, Claude, and Gemini. It is designed to work within any AI agent environment that supports structured system instructions and multilingual tasks, including specialized support for Indonesian.

    The completeness score is a mathematical audit that evaluates how much of your initial request was factual versus assumed. It helps you understand if your prompt is ready for execution or if you need to answer the generated clarifying questions to improve accuracy.

    Each purchase includes the full skill logic ready for integration into your preferred AI agent platform. You will receive the core instruction set for the six-part framework, the audit scoring system, and the automated gap-analysis module.

    To ensure clarity and prevent information overload, the skill is capped at 5 '[FILL IN]' markers per iteration. If your request is extremely broad, the skill will use targeted follow-up questions to bridge gaps over multiple steps rather than generating one overly complex output.

    New in Prompt & Skill Engineering