Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Evidence-First Debugger

    1

    Debug with evidence, not guesses: ranked hypotheses, a minimal fix, and a regression test for every bug.

    Free

    1 useSecurity scanned
    Evidence-First Debugger

    Evidence-First Debugger

    Example session with this skill installed

    My test test_parse_date fails with ValueError: day is out of range for month
    when the input is "2024-02-30". Debug it.

    • Read your context and instructions
    • Compiled the evidence-first debugger

    Summary

    Root cause: parse_date validates the month and day separately, so
    "2024-02-30" passes both checks and only fails later inside datetime.

    Evidence

    ObservationSource
    Error raised at utils/dates.py:42stack trace
    Day checked only against range 1-31utils/dates.py:30-36
    Only Feb 29-30 and 31-day-month edge cases fail6 inputs tried

    Ranked hypotheses

    1. Day validated without considering the month (confirmed by experiment)
    2. Leap-year handling bug (rejected: 2024-02-29 parses correctly)
    3. Locale or format issue (rejected: ISO format is parsed correctly)

    Minimal fix

    Validate with calendar.monthrange(year, month)[1] instead of a fixed 31.

    Regression test

    test_parse_date_rejects_feb_30 and test_parse_date_accepts_leap_day.
    Both verified to fail before the fix and pass after.

    Next steps

    Audit other callers of the old range check in utils/.

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

    About this skill

    Evidence-First Debugger makes your agent debug the way a careful engineer does, instead of guessing and patching.

    What it does

    1. Reproduces the failure and captures the exact error, inputs, and environment.
    2. Collects evidence (stack traces, logs, failing tests, relevant code paths).
    3. Lists ranked hypotheses, each with the evidence for and against it.
    4. Runs the cheapest experiment that separates the top hypotheses.
    5. Applies the smallest fix that addresses the confirmed root cause.
    6. Adds a regression test that fails before the fix and passes after.

    Why use it

    • Stops the "change five things and hope" loop
    • Keeps diffs small and reviewable
    • Leaves behind a test so the bug stays fixed

    Best for

    Failing tests, runtime exceptions, flaky behavior, and unexpected output in Python, JavaScript, and other codebases an agent can run locally.

    Requires execution access for full verification. When execution is unavailable, fixes are marked UNVERIFIED. Intermittent bugs may require multiple iterations to capture evidence.

    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 29 days ago

    • Free with an Agensi account

    Requires

    Python
    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Browser
    Network Access
    Environment Variables

    File Scopes

    **/*.py
    tests/**
    test/**
    pyproject.toml
    requirements*.txt
    *.log
    Listed29 days ago

    What's inside

    Frequently Asked Questions

    This skill prevents 'hallucinated fixes' by requiring the agent to generate a minimal reproduction case and verify the patch with successful test execution before reporting the bug as resolved.

    The skill includes specialized diagnostic procedures for Python environments, including frameworks like Django, FastAPI, and PyTorch, as well as testing tools like pytest.

    Yes, it is specifically designed to handle complex issues like race conditions in concurrent code and silent failures in ML pipelines, such as NaN loss or tensor shape errors.

    If an execution environment is unavailable, the agent will provide the manual commands needed for you to run the verification yourself and will label the fix as UNVERIFIED.

    You receive the complete Evidence First Debugger skill package, including the structured triage protocols, hypothesis ranking logic, and specialized diagnostic scripts for all supported frameworks.

    This skill is compatible with major AI agents that support tool-use and code execution capabilities, allowing the agent to run the reproduction scripts and tests it generates.

    New in Testing & Debugging