rubberduck
Skill1 starsChanged 7 days agoMITView on GitHub
Resolves design decisions through focused interview. Use when user requests grilling, rubberduck, or plan stress-testing.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- ssv445/claude-skillstheir own version, first seen Oct 13, 2026
- murilonerdx/skill-engineering-tdahtheir own version, first seen Aug 4, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- ssv445/claude-skills★ 2same name
- murilonerdx/skill-engineering-tdah★ 0same name
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.
The file
Files
Rubberduck
Short questions. No emojis. User owns decisions; agent finds facts. Read relevant context.md, domain language, ADRs. Reuse known answers.
Cadence: read .galicia/config.json when present. If unset/ask, ask once: one question per turn, or batch independent questions? Remember within session; user override wins.
Map decision dependencies. Ask only questions whose prerequisites settled. One mode: ask highest-impact open decision. Batch mode: ask independent ready decisions together. Never ask downstream question before prerequisite answered.
Each question: number, concrete choice, recommended answer, material tradeoff. Phrase yes to accept recommendation. Wait for answer; recompute open decisions. Fetch discoverable facts; never make user research repo.
For consequential ADR research/review, recommend scoped small-model subagent, e.g. Luna/Haiku where available. Name task, inputs, expected evidence. Spawn only when authorised. No delegation for trivial lookup.
Done when scope, behaviour, failure cases, validation, delivery boundaries settled. Summarise agreements and unresolved items. Ask user to confirm shared understanding before implementation. No silent assumptions.
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.