Assumption Check — Testing skill for Claude Code
Surfaces the 5 riskiest untested assumptions in a feature or product bet, ranks them by risk, identifies the cheapest validation test for each, and produces a 3-day test plan for the single most dange.
How to install Assumption Check
Installs to ~/.claude/skills/varunk130-ai-builder-decision-analyst-assumption-check/SKILL.md
mkdir -p ~/.claude/skills/varunk130-ai-builder-decision-analyst-assumption-check && curl -fsSL https://raw.githubusercontent.com/varunk130/AI-Builder-Decision-Analyst/HEAD/skills/assumption-check.md -o ~/.claude/skills/varunk130-ai-builder-decision-analyst-assumption-check/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Assumption Check does
name: assumption-check description: Surfaces the 5 riskiest untested assumptions in a feature or product bet, ranks them by risk, identifies the cheapest validation test for each, and produces a 3-day test plan for the single most dangerous assumption. Use before committing engineering resources to any new feature or initiative.
Assumption Check — Hidden Risk Surfacer
This skill identifies what you're implicitly betting on and haven't validated. It does NOT evaluate whether the idea
Alternatives in Testing
- Brainstorm Experiments Existing — Design experiments to test assumptions for existing products 7.8k ★
- Loki Grill — Interrogate a spec with Loki's Devil's-Advocate grill before building, and summarize the hardest questions it 1.1k ★
- Spec-Flow Agents — Spec-Flow coordinates multiple coding tools through a single shared canon 73 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Bos Ideate
Phase 3 — generate distinct solution options, select the bet, write kill criteria, and design the cheapest tes
Discovery Experiment
Map the assumptions behind an idea and design the cheapest test that would actually change your mind, with the
Smart PR
Generate a structured PR description from the current branch diff. Run after /self-review passes. Produces tit
Illustration
Design and spec an illustration system or single illustration. Picks style, voice, format (SVG / Lottie / PNG)
Stat Research Pipeline
Open-source AI skills for AI-assisted statistical research workflows: assumption checks, test selection, model
Swift Crap Check
Agent skill that ranks Swift functions by the CRAP metric - cyclomatic complexity weighted against test covera
Related Agents
Assumption Challenger
Adversarial review. Extracts unstated assumptions, ranks them by blast radius, and designs the cheapest test t
Assumption Mapping
Use when the user needs to identify and prioritize risky assumptions in a product idea, feature, or strategy.
Adversarial Tester
Collegium spec reviewer — finds what will break. Identifies failure scenarios, edge cases, lifecycle state lea