Rubber Duck
When a user is stuck, frustrated, or describing a problem vaguely, do NOT immediately suggest solutions. First, force structured problem articulation through targeted questions: What did you expect? What happened instead? What have you tried? Only after the problem is clearly defined, propose solutions.
Install
npx skills add ElliotJLT/Claude-Skill-Potions --skill rubber-duckgit clone --depth 1 https://github.com/ElliotJLT/Claude-Skill-Potions.git /tmp/Claude-Skill-Potions
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skill-Potions/skills/rubber-duck ~/.claude/skills/rubber-duckPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Rubber Duck <purpose> Users often know the solution to their own problem - they just haven't articulated it clearly yet. Jumping to solutions before understanding the problem wastes time and often misses the real issue. This skill enforces the rubber duck debugging pattern: make them explain it properly first. </purpose> ## When To Activate Trigger when you see: - Vague problem descriptions: "it's not working", "something's wrong" - Frustration signals: "I've been stuck for hours", "I don't know why" - Missing context: no error messages, no expected vs actual - Shotgun debugging: "I tried X, Y, Z and nothing works" - XY problems: asking about solution B when problem A is the real issue ## Instructions ### Step 1: Resist the Urge to Solve Do NOT immediately propose solutions. Even if you think you know the answer. ### Step 2: Ask The Three Questions ``` Let me make sure I understand the problem clearly. 1. **What did you expect to happen?** [Get specific desired outcome] 2. **What actually happened?** [Get specific observed behaviour, error messages, symptoms] 3. **What have you tried so far?** [Understand their mental model and eliminate paths] ``` ### Step 3: Probe Deeper If Needed If answers are still vague, follow up:
Details
- Skill name
rubber-duck- Repository
- ElliotJLT/Claude-Skill-Potions
- Path
skills/rubber-duck/SKILL.md- License
- MIT
- Repo updated
- 12 February 2026
FAQ
What does the Rubber Duck skill do?
When a user is stuck, frustrated, or describing a problem vaguely, do NOT immediately suggest solutions. First, force structured problem articulation through targeted questions: What did you expect? What happened instead? What have you tried? Only after the problem is clearly defined, propose solutions.
How do I install the Rubber Duck skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add ElliotJLT/Claude-Skill-Potions --skill rubber-duck. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Rubber Duck popular?
It lives in ElliotJLT/Claude-Skill-Potions, which has 62 GitHub stars and 2 forks.
Related skills
Agent Audit
62ElliotJLT/Claude-Skill-Potions
When reviewing, optimizing, or inheriting an LLM agent, systematically identify what's actually load-bearing vs. cruft. Instruments usage, ablates components, and strips the agent to minimum viable form. Answers: "What can we remove without degrading quality?" The goal is the leanest agent that still works.
Battle Plan
62ElliotJLT/Claude-Skill-Potions
Before ANY significant development task (new feature, refactor, integration, migration), run a complete planning ritual by orchestrating other skills in sequence: rubber-duck (clarify scope) -> pre-mortem (assess risks) -> eta (estimate time) -> final confirmation. Do not start coding until the battle plan is approved.
Breadcrumbs
62ElliotJLT/Claude-Skill-Potions
Leaves notes for future Claude sessions in .claude/breadcrumbs.md. At session end or after significant work, records what was tried, what worked, what failed, and context for next time. On session start, reads breadcrumbs to understand history. Session-to-session memory without manual updates.
Diagnose Errors
48amplitude/mcp-marketplace
Investigates errors across network failures, JavaScript errors, and error clicks to identify what's broken, where, and why. Use when the user says "what's broken", "errors are up", "why are users seeing errors", "JS errors", "network failures", "5xx spike", "something is broken", or wants to triage product reliability issues.
Outcome Engineering
38sam-dumont/claude-skills
Use when starting significant features, evaluating build-vs-buy decisions, reframing failed approaches, or when the user mentions "outcome engineering", "o16g", "outcome-first", "what's the outcome", or "frame this as an outcome". Also use proactively when a task description focuses on implementation ("build X", "add Y") without defining the desired outcome or verification criteria.
Pci Dss
33scytale-labs/GRC-Claude-Skills
Use when the user asks about PCI DSS — the v4.0 (or v4.0.1) twelve requirements, scoping the cardholder data environment (CDE), Self-Assessment Questionnaires (SAQs), Reports on Compliance (ROCs), tokenization, segmentation, merchant levels, or PCI's customized vs defined approach to validation. For merchants, service providers, and their assessors.
Browse the most popular Claude skills, all finance & crypto skills, or write your own with the skills generator.