More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Hire Trace: Rootcause, debug by hypothesis

    1

    Trace stops the guessing: he states the symptom, ranks the hypotheses, proves the top one, then applies the smallest fix that touches nothing else.

    Free

    1 useSecurity scanned
    Hire Trace: Rootcause, debug by hypothesis

    Hire Trace: Rootcause, debug by hypothesis

    Example session with this skill installed

    Rootcause: "TypeError: Cannot read properties of null (reading 'map')" in ProductList.tsx. It happens when the search returns no results.

    • Read your context and instructions
    • Compiled the hire trace
    • Generated the UI component

    I have analyzed the ProductList.tsx error. The issue stems from an unhandled empty state in the search result handler.

    SYMPTOM
    TypeError in ProductList.tsx when a search query returns no results, causing the component to crash while trying to map over a null data object.

    HYPOTHESIS
    Most likely: The API returns null instead of an empty array when no products match, but the UI expects an array.
    Evidence: Line 24 attempts products.map() without a null check or default value.

    VERIFICATION
    Reading src/components/ProductList.tsx...
    Confirmed: Line 24 is products.map(p => <Card key={p.id} ... />).
    Checked src/api/products.ts: The fetchProducts function returns null on a 404 search status.

    FIX

    // src/components/ProductList.tsx:24
    - {products.map((product) => (
    + {products?.map((product) => (
    

    WHY
    Uses optional chaining to prevent the crash when products is null. This is the minimum change required to restore stability without altering the API or component structure.

    Next steps

    1. Apply the optional chaining fix to ProductList.tsx.
    2. Verify the fix by performing a search that returns no results.
    3. Consider adding a "No results found" empty state UI.

    ProductList.tsx

    TSX · React component

    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

    Meet Trace, the Thousand-Eyed Wolf of MAJITOPIA. His skill, Rootcause, is free: add him to your party and every bug gets a verified root cause before anyone touches the code.

    Stop wasting time on guess-and-check refactors that break unrelated features. This skill enforces a disciplined debugging protocol that prioritizes verification over hasty code changes. It prevents the common AI tendency to rewrite entire files when a single line is at fault.

    What it does

    • Symptom analysis isolates what happened versus what was expected before proposing any code changes.
    • Hypothesis ranking generates multiple potential causes backed by evidence to avoid narrow focus.
    • Verification gating requires active confirmation of a bug via logs, tests, or file inspection before a fix is allowed.
    • Minimum-change diffs ensures only the necessary lines are touched, preventing "while I was there" scope creep.
    • Safety checks evaluate whether a proposed fix will impact unrelated code paths or break existing functionality.

    How it works

    1. Input symptom by providing an error message, stack trace, or description of unexpected behavior.
    2. Review hypothesis to see the most likely cause and the evidence supporting that theory.
    3. Confirm verification as the skill reads files or runs tests to prove the bug exists where suspected.
    4. Apply fix using a surgical, minimum-scope code diff provided in the standardized output format.

    Frameworks & tools

    Works with any language or framework, including React, Node.js, Python, Rust, and Go. It is particularly effective in environments with complex state or nested API responses.

    Why this beats prompting it yourself

    Generic prompts often lead to "try this" cycles that bloat your codebase. This skill forces a diagnostic pause and enforces a strict pre-action gate that standard LLM instructions lack.

    Use cases

    • Fixing TypeErrors like undefined properties in API response handlers.
    • Debugging failing tests where the root cause is not immediately obvious from the runner output.
    • Resolving logic bugs where code runs without crashing but produces incorrect data.

    Known limitations

    Requires access to the codebase and relevant logs or error messages to be effective. It does not perform architectural refactoring or library migrations.

    Requires source code access and specific error context. Does not handle large-scale architectural refactoring.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Read Files
    Write Files
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    Unlike standard LLMs that often suggest wide-scale refactors, this skill enforces a strict verification gate that prevents any code changes until the bug is proven through logs or tests.

    This skill is language-agnostic and works with any framework, including React, Python, and Rust, as long as your agent has access to the codebase and terminal output.

    You receive the complete debug protocol and logic gates designed to be integrated into your agent's workflow, along with documentation on how to trigger the diagnostic steps.

    The skill requires the agent to have read access to your source files and the ability to view error logs or test results to accurately rank its hypotheses.

    Yes, 'maji debug' is optimized for large-scale projects where surgical precision is required to avoid breaking complex, interconnected dependencies or state management logic.

    New in Testing & Debugging