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
- Osipchuk/agent-skillstheir own version, first seen Nov 8, 2026
- vidluther/skillstheir own version, first seen Oct 31, 2026
- damacus/agent-skillstheir own version, first seen Oct 29, 2026
- oneafrikan/the-gridtheir own version, first seen Oct 20, 2026
- kirodotdev/KiroCrewtheir own version, first seen Oct 19, 2026
- The-Artificer-of-Ciphers-LLC/skills-from-the-artificertheir own version, first seen Oct 14, 2026
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.
MicrosoftSkillcaveman
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
GoogleSkillgrill-me
A relentless interview to sharpen a plan or design.
Also in 5 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 5 projects that use this
GoogleSkillprototype
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
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- kirodotdev/KiroCrew★ 4.8ksame name
- thoughtbot/rails-consultant★ 29same name
- jim60105/copilot-prompt★ 22same name
- stevepolitodesign/skills★ 10same name
- The-Artificer-of-Ciphers-LLC/skills-from-the-artificer★ 6same name
- jmcelreavey/devhub★ 5same name
- Osipchuk/agent-skills★ 5same name
- oneafrikan/the-grid★ 4same name
- stormlightlabs/thunderus★ 4same name
- dfrysinger/skills★ 3same name
12 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/gooblin.mdcCursor rule
- clipperSkill
- gooblin-coreSkill
- gooblinSkill
- ground-controlSkill
- yak-shaverSkill
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
- Distinctive: line 16
Use Rubber Duck when a bug report is vague, intermittent, contradictory, missing logs, missing reproduction steps, or already drifting into …
- Distinctive: line 23
Create minimal reproduction steps.
- Distinctive: line 24
Check the most likely observable boundary first.
- Distinctive: line 26
Only then propose a fix.
“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.
Files
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
- State expected behavior.
- State actual behavior.
- Identify the first contradiction.
- Create minimal reproduction steps.
- Check the most likely observable boundary first.
- Turn the bug into a test when possible.
- 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 addExample 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.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
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.

