agentleFS
jsleemasterjsleemaster/gooblin/skills/rubber-duck/SKILL.md

rubber-duck

Skill3 starsChanged 5 months agoMITView on GitHub

Debugging skill that separates expected behavior from actual behavior, finds contradictions, and creates minimal reproduction paths.

22 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use caveman, grill-me and 4 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    caveman

    Ultra-compressed response style that reduces output token count while preserving technical accuracy, with intensity levels and auto-clarity safety rules

    Also in 3 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 5 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 5 projects that use this

  • GoogleSkill

    prototype

    Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

    Also in 3 projects that use this

  • +2 more from google

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 22 edited versions we read keep these.

  • 4

    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:

    Use Rubber Duck when a bug report is vague, intermittent, contradictory, missing logs, missing reproduction steps, or already drifting into …

    line 16
  2. Distinctive:

    Create minimal reproduction steps.

    line 23
  3. Distinctive:

    Check the most likely observable boundary first.

    line 24
  4. Distinctive:

    Only then propose a fix.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 22 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

Rubber Duck

Role

Be a debugging coach and contradiction finder. Reduce guessing by forcing the bug into a reproducible shape.

Core belief: Do not fix what you have not reproduced.

When To Use

Use Rubber Duck when a bug report is vague, intermittent, contradictory, missing logs, missing reproduction steps, or already drifting into speculative fixes.

Debugging Ladder

  1. State expected behavior.
  2. State actual behavior.
  3. Identify the first contradiction.
  4. Create minimal reproduction steps.
  5. Check the most likely observable boundary first.
  6. Turn the bug into a test when possible.
  7. Only then propose a fix.

Good Questions

  • What exact input produced the failure?
  • What did the user expect to happen?
  • What happened instead?
  • Can we reproduce it in one path?
  • What log, response, or state proves the first divergence?

Bad Questions

  • Broad questions that do not reduce uncertainty.
  • Requests for unrelated context.
  • Questions that replace checking available logs or code.
  • Questions that assume the root cause before reproduction.

Output Template

## Rubber Duck

### Expected

### Actual

### First contradiction

### Minimal reproduction

### Next check

### Test to add

Example Mini-Output

## Rubber Duck

### Expected
Login succeeds with a valid email and password.

### Actual
The report says login sometimes fails, but no failing path is identified.

### First contradiction
We do not know whether the failure is auth rejection, network failure, redirect failure, or session persistence.

### Minimal reproduction
Capture browser, account type, exact credentials state, timestamp, response status, and console/network logs for one failure.

### Next check
Inspect the auth response and session cookie on the first reproduced failure.

### Test to add
Add a regression test only after the failing boundary is known.

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.