agentleFS
karim-embarekkarim-embarek/superpowers-antigravity/skills/superpowers-systematic-debug/SKILL.md

superpowers-systematic-debug

Skill2 starsChanged 3 months agoMITView on GitHub

A 4-phase root cause debugging methodology to diagnose and fix failures without trial-and-error code guessing.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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:

    Use this skill when encountering test failures, unexpected application errors, runtime exceptions, or broken behavior.

    line 8
  2. Distinctive:

    Never guess: Every code edit during debugging must be justified by empirical log evidence or root-cause tracebacks.

    line 11
  3. Distinctive:

    Never mask symptoms: Do not swallow exceptions, return dummy nulls, or change assertion expectations to hide a bug.

    line 12
  4. Distinctive:

    Read complete un-truncated error logs and tracebacks.

    line 24
  5. Distinctive:

    Test hypotheses one by one without modifying unrelated business logic.

    line 34

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Superpowers: Systematic Debugging Skill

Use this skill when encountering test failures, unexpected application errors, runtime exceptions, or broken behavior.

Core Rules

  1. Never guess: Every code edit during debugging must be justified by empirical log evidence or root-cause tracebacks.
  2. Never mask symptoms: Do not swallow exceptions, return dummy nulls, or change assertion expectations to hide a bug.

The 4-Phase Debugging Process

graph TD
    A["Phase 1: Evidence Gathering"] --> B["Phase 2: Hypothesis Formulation"]
    B --> C["Phase 3: Controlled Isolation"]
    C --> D["Phase 4: Root Cause Fix & Verification"]

Phase 1: Evidence Gathering

  • Read complete un-truncated error logs and tracebacks.
  • Identify exact failing line, error type, and execution context.
  • Inspect state variables leading up to the failure.

Phase 2: Hypothesis Formulation

  • Formulate 1 to 3 specific, testable hypotheses for why the failure occurs.
  • Rank hypotheses by likelihood based on code inspection and error logs.

Phase 3: Controlled Isolation

  • Isolate the failing component in a minimal test or script.
  • Test hypotheses one by one without modifying unrelated business logic.

Phase 4: Root Cause Fix & Verification

  • Apply the fix addressing the root cause at the upstream source.
  • Re-run the full test suite to verify the issue is resolved and 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.