surface-assumptions
Identify and validate hidden assumptions before they become bugs. Use before implementing features or when reviewing generated code.
What this skill does
# Surface Assumptions Skill ## Trigger Use before implementing a feature, or when reviewing generated code. Critical for catching the #1 LLM coding mistake. ## The Problem Karpathy: "The most common category [of LLM errors] is that the models make wrong assumptions on your behalf and just run along with them without checking." LLMs don't ask clarifying questions. They pick an interpretation and commit to it. This skill forces assumptions to be explicit. ## Process ### Step 1: List Every Assumption Before or during implementation, explicitly list what the code assumes: **Input Assumptions:** - What types/shapes are expected? - What ranges are valid? - What formats are expected (dates, strings, etc.)? - Can inputs be null/undefined? **State Assumptions:** - What state must exist before this runs? - What order must operations happen in? - What other code must have run first? **Environment Assumptions:** - What APIs/services must be available? - What browser/runtime features are needed? - What permissions are required? **Business Logic Assumptions:** - What do domain terms mean? - What are the business rules? - What happens in ambiguous cases? ### Step 2: Categorize Each Assumption | Assumption | Confidence | Impact if Wrong | Action Needed | |------------|------------|-----------------|---------------| | User is authenticated | High | Security breach | Add auth check | | Dates are ISO format | Medium | Parse errors | Validate format | | Max items is 100 | Low | Performance issues | Clarify with user | ### Step 3: For Low-Confidence Assumptions **STOP and ask the user.** Don't guess. Present the assumption and alternatives: ``` I'm assuming the date format is ISO 8601 (YYYY-MM-DD). Should I also support: 1. US format (MM/DD/YYYY) 2. EU format (DD/MM/YYYY) 3. Unix timestamps ``` ### Step 4: Document or Validate For each assumption, either: 1. **Validate at runtime** - Add explicit checks 2. **Document clearly** - Add comments explaining the assumption 3. **Add types** - Use TypeScript to enforce constraints ## Output Format When surfacing assumptions: ``` ## Assumptions Made ### Validated in Code - [x] User ID is a valid UUID (validated at line 45) - [x] Amount is non-negative (validated at line 52) ### Documented - [x] Dates are in UTC timezone (see comment at line 30) ### Needs Clarification - [ ] Should deleted users still appear in reports? - [ ] What happens if payment fails mid-transaction? - [ ] Is the 100-item limit a hard requirement? ``` ## Key Questions to Always Ask 1. What happens with empty/null inputs? 2. What happens with very large inputs? 3. What happens if external services fail? 4. Who can access this? Who shouldn't? 5. What happens concurrently?
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.