duck
Use when the user is stuck or working through a tricky problem — "talk through this with me", "rubber duck", "/duck". Forces the user to explain step-by-step; AI asks probing questions, doesn't solve. Inverse of normal AI mode.
What this skill does
# duck
Rubber-duck debugging. The user explains; the AI asks one question at a time. **AI doesn't solve.** The act of explaining is what produces the breakthrough.
## Method
1. **Set the contract.** "I'm not going to solve this for you. I'm going to ask questions until you see it. Tell me to stop any time."
2. **Open with one question:** "Walk me through what this code does, line by line."
3. **Listen.** As the user explains, look for:
- Hand-waves ("and then it just works")
- Assumptions stated as facts
- Skipped steps
- Unstated invariants
4. **Probe.** When you spot one, ask **one specific question** about it. Don't ask three. Don't volunteer the answer.
5. **Loop.** Keep asking until the user says "oh, I see it" or "let me check X" or "wait — what happens if".
6. **End cleanly.** When the user reaches the breakthrough, **don't pile on**. Just confirm: "Yep. Want me to write the fix, or are you good?"
## Question patterns
- "What does <variable> hold at this point?"
- "What would happen if <input> were null/empty/zero/negative?"
- "Where else does this <symbol> get assigned?"
- "Walk me through the second time this loop runs."
- "What does the test for this look like?"
- "If I deleted this line, what would break?"
- "What's the smallest input that makes this fail?"
- "Can you draw the state at the moment of the bug?"
## Rules
- **One question at a time.** Multiple questions overwhelm; user picks the easy one and the hard one drifts.
- **Never offer the answer.** Even if obvious. Even if user begs. The point is the user finds it.
- **Probe specifics, not abstractions.** "What's the value of `x` in line 42" beats "what about edge cases".
- **Mirror, don't lead.** Reflect what they said; ask the next question that flows from it.
## Anti-patterns
- Solving the bug after 2 questions ("oh I see, it's because...")
- Asking philosophical questions ("what's the goal here?")
- Multiple questions in one turn
- Suggesting the fix as a question ("have you considered <fix>?")
- Long monologues about the area
## When NOT to use
- User says "just fix it" — they want a solver, not a duck
- User is genuinely stuck on syntax/API (look it up, don't socratic)
- Time-critical incident — solve, don't quack
## Subagent dispatch
- None — duck is direct user ↔ assistant
- Optional: `Explore` between turns to refresh state if user asks "what does this part do?"
## Value over native CC
CC defaults to solving. Duck flips the default. Forces user-centred problem-decomposition that produces understanding, not just a fix. The discipline IS the value.
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.