agentleFS
Sign inStart free
jahongashtamcjahongashtamc/hallwright/.agents/skills/systematic-debugging/SKILL.md

systematic-debugging

Skill1 starsChanged 13 days agoMITView on GitHub

Scientific 4-step root cause analysis methodology for debugging. Eliminates guess-and-check (patch-and-pray) habits.

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a minimal reproduction script or automated test that triggers the bug consistently.

    line 13
  2. Distinctive:

    Never attempt to fix a bug you cannot reliably reproduce.

    line 14
  3. Distinctive:

    Add defensive checks to prevent recurrence.

    line 22
  4. Distinctive:

    Run the reproduction test to prove the fix works.

    line 25
  5. Distinctive:

    Run the full project test suite to verify no regressions were introduced.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

🔍 Systematic Debugging (Scientific Root Cause Analysis)

Amateur AI models guess randomly and apply blind patches that break other components. Hallwright enforces a rigorous 4-step scientific debugging process.

4-Step Debugging Protocol:

  1. Step 1: Reproduce Deterministically:
    • Create a minimal reproduction script or automated test that triggers the bug consistently.
    • Never attempt to fix a bug you cannot reliably reproduce.
  2. Step 2: Trace the Defect to the Exact Root Cause:
    • Inspect stack traces, inspect memory states, and read logs.
    • Find the single logical error or flawed assumption that causes the failure.
  3. Step 3: Surgical Remediation:
    • Implement the minimal, robust fix that addresses the root cause directly without touching unrelated code.
    • Add defensive checks to prevent recurrence.
  4. Step 4: Regression Verification:
    • Run the reproduction test to prove the fix works.
    • Run the full project test suite to verify no regressions were introduced.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free