Works with the AI tools you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIGitHub CopilotGitHub CopilotGemini CLIGemini CLI+20 more

    Systematic Debugging

    1

    A disciplined debugging methodology that enforces root cause isolation and regression testing before applying fixes.

    $10

    Secure checkout via Stripe

    30-day refund guarantee

    Converts to your local currency at checkout

    0 installsSecurity scanned
    Systematic Debugging

    Systematic Debugging

    Example session with this skill installed

    Debug the 'order-total-mismatch' symptom. Repro: 'npm test tests/calc.test.js'. Sources: 'src/calc.js', 'src/tax.js'. Test path: 'tests/regression.test.js'. Goal: Fix rounding error in totals.

    • Read your context and instructions
    • Compiled the systematic debugging
    • Generated the document

    I have completed the systematic debugging cycle for the order-total-mismatch symptom. The root cause was isolated to a floating-point precision error during tax calculation, which has been resolved and verified.

    Debug Run Record: Order Processor

    FieldValue
    ProductOrder Processor
    Slice GoalFix rounding error in totals
    Symptomorder-total-mismatch
    Statusready

    Reproduce

    Command npm test tests/calc.test.js failed as expected.
    Failure: Expected total 100.00 but got 99.9999999998

    Isolate

    The error persists even with simplified 10% tax rates. Tracing src/tax.js showed the multiplier was applied before rounding.
    Root cause is the tax calculation utility returns raw floats to the aggregator instead of rounding to the smallest currency unit because the calculateTax function lacked a precision floor.

    RED

    Created tests/regression.test.js.
    Command npm test tests/regression.test.js failed with the precision mismatch.

    GREEN

    Applied fix to src/tax.js using Math.round.

    1. npm test tests/regression.test.js - PASS
    2. npm test tests/calc.test.js - PASS
    3. npm test (full suite) - PASS

    Next steps

    • Review the plans/debug-run.md file for the full audit trail.
    • Merge the changes in src/tax.js and the new regression test.
    • Start a new cycle if there are other symptoms in the backlog.

    systematic-debugging.pdf

    PDF · document

    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.

    What you get

    Identify the exact source of a logic error before writing a single line of fix.Create automated regression tests that prove a specific bug is gone forever.Generate a standardized debug-run log for team review and audit trails.Prevent codebase drift by refusing 'shotgun' patches and unrelated edits.

    About this skill

    The problem

    Debugging by trial and error leads to "shotgun patching" where code is modified without understanding the root cause. This results in brittle fixes, cluttered codebases, and regressions that go unnoticed until they hit production.

    What it does

    • Enforces a strict reproduce-isolate-fix-verify cycle for a single specific symptom.
    • Validates that the reproduction command actually fails before any code analysis begins.
    • Isolates the root cause into a single verifiable sentence supported by evidence.
    • Requires a failing regression test to be established before the fix is applied.
    • Verifies the fix against the reproduction loop, the new regression test, and the existing suite.

    Frameworks & tools

    This skill is framework-agnostic and works with any existing language, test runner, or shell-based build system. It uses standard file operations and shell commands provided by the environment.

    Why this beats prompting it yourself

    Standard LLM prompts often lead to premature patching or guessing. This skill forces a disciplined engineering method that forbids production changes until a root cause is proved, ensuring high-integrity fixes and automated documentation of the debug journey.

    Use cases

    • Root cause analysis for complex logic errors in backend services.
    • Fixing intermittent failures by narrowing down load-bearing environment factors.
    • Resolving regressions by isolating the specific change that introduced a bug.
    • Documenting critical bug fixes for audit trails and technical debt reviews.

    Known limitations

    Only handles one symptom per cycle. It will not install new test frameworks or handle highly flaky bugs (repro rate under 50 percent).

    How to install

    Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.

    ~30 seconds
    1. 1

      Download the ZIP

      Free skills download straight away. Paid skills unlock right after purchase.

    2. 2

      Unzip into your skills folder

      Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.

    3. 3

      Ask your agent to use it

      Restart the agent if it was already running. It picks the skill up automatically - no config needed.

    Skills folder by agent

    Click the path to copy it. Create the folder if it does not exist yet.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    30-day refund

    Not a fit? Get your money back

    Trust & safety

    Security scanned

    Verified clean 1 day ago

    • Passed all security checks, Safe to install

    Listed1 day ago

    Frequently Asked Questions