Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    program logic model

    1

    Logic models often suffer from broken causal chains, orphaned activities, and unlinked outcomes that make program evaluation impossible.

    $1.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    program logic model

    program logic model

    Example session with this skill installed

    Validate this logic model for the Youth Employment Program. We have staff and funding. Activities are job coaching and resume workshops. Outputs are 1:1 sessions. Outcomes are increased employment.

    • Read your context and instructions
    • Compiled the program logic model

    The logic model for the Youth Employment Program has been structured and validated. The analysis identified the link between staff resources and service delivery, though some long-term outcomes remain unmapped.

    Program Logic Model — Youth Employment Program

    1. Program mandate

    To increase employment rates among local youth through targeted skills development and coaching.

    2. Logic model structure

    Inputs (Resources)

    IDNameCategoryLinks
    I1StaffstaffA1, A2
    I2FundingfundingA1, A2

    Activities

    IDNameInput IDs
    A1Job CoachingI1, I2
    A2Resume WorkshopsI1, I2

    Outputs

    IDNameActivity IDs
    OUT11:1 SessionsA1, A2

    Outcomes

    IDNameLevelOutput IDs
    OC1Increased Employmentshort_termOUT1

    3. Coverage analysis

    MetricValue
    input_coverage1.0
    activity_coverage1.0
    output_coverage1.0
    overall_coverage1.0
    chain_score0.85

    4. Orphan elements

    None detected.

    5. Validation status

    • is_complete: true
    • has_orphans: false
    • has_circular_references: false
      Note: Causal pathways require validation.

    6. Assumptions and external factors

    • Local economic conditions remain stable (External Factor).
    • Participants are willing to engage in workshops (Assumption).

    7. Interpretation and items for review

    The structure is sound with high coverage across all levels.

    Information gap — organizational validation required for medium and long-term outcome definitions, as only short-term employment increases are currently mapped.

    Causal pathways are hypotheses requiring empirical validation.

    Next steps

    1. Define medium-term outcomes such as career advancement or wage growth.
    2. Link the current short-term outcome (OC1) to a long-term outcome.
    3. Verify the external factor regarding economic stability with local labor data.

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

    About this skill

    Logic models often suffer from broken causal chains, orphaned activities, and unlinked outcomes that make program evaluation impossible. This skill provides a rigorous structural audit of program logic models to ensure every resource, activity, and output leads to a defined outcome.

    What it does

    • Causal mapping links inputs to activities, outputs, and multi-level outcomes.
    • Structural validation detects circular references and broken linkages in the program theory.
    • Orphan detection identifies specific elements that lack forward or backward connections.
    • Coverage scoring computes quantitative metrics for input, activity, and output alignment.
    • Multi-language support processes requests in both English and French (e.g., modèle logique).

    How it works

    1. The user provides program data including mandate, resources, and intended outcomes.
    2. The agent structures this data into a schema-validated request.json file.
    3. A deterministic script processes the model to compute structural integrity and coverage.
    4. The agent generates a report containing the logic model tables, metrics, and identified gaps.

    Frameworks & tools

    The skill utilizes a custom Python-based validation engine to process JSON schemas and compute linkage metrics. It adheres to standard program evaluation methodologies for inputs, activities, outputs, and outcomes.

    Why this beats prompting it yourself

    Generic prompts often hallucinate missing links or ignore orphaned elements to make the model look "complete." This skill uses a deterministic script to ensure metrics and gap analyses are mathematically accurate and strictly based on provided data.

    Use cases

    • Auditing a new public program design for structural completeness.
    • Identifying gaps where staff or funding do not link to specific activities.
    • Mapping deliverables to short, medium, and long-term outcomes for reporting.
    • Validating existing documentation for "orphan" activities that contribute to nothing.

    Known limitations

    This skill performs structural validation only and does not assess the quality, feasibility, or empirical truth of the causal claims. It cannot be used for cost-effectiveness analysis or budget allocation.

    Structural validation only. Does not verify empirical truth of causal links. Requires specific program elements (inputs, activities, etc.) to function. No impact or cost-effectiveness analysis.

    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

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed today

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Environment Variables
    Listedtoday

    What's inside

    Frequently Asked Questions

    The skill identifies 'orphaned' elements—activities or resources that aren't linked to any outcome—and detects broken causal chains or circular logic that often go unnoticed in manual reviews.

    Unlike generic prompts that may 'hallucinate' missing links to appear helpful, this skill uses a deterministic Python engine to provide mathematically accurate gap analysis and coverage metrics based strictly on your data.

    Yes, the skill fully supports both English and French, allowing you to validate models and generate reports in either language, including terminology specific to 'modèle logique' frameworks.

    You will receive the core logic model agent, the proprietary Python-based validation engine, and standardized JSON schemas for structuring your program data.

    The skill focuses on structural integrity (the 'plumbing' of your logic model) and does not evaluate whether your program goals are realistic, feasible, or cost-effective.

    The skill is designed to be compatible with any AI agent platform that supports Python-based tool execution and JSON file handling.