breethomas

breethomas/bette-think

Skill Claude CodeCodex

Expert knowledge of proven product management frameworks for discovery, growth, measurement, planning, and AI-era practices.

breethomas/bette-think

Skill Claude CodeCodex

Create and analyze a PMF survey using Rahul Vohra's Superhuman framework. The magic 40% benchmark for product-market fit.

breethomas/bette-think

Skill Claude CodeCodex

Full 5-stage PRD framework for complex features. Use for deep PRD work via /spec --deep full-prd. For quick feature specs, use /spec --feature instead.

breethomas/bette-think

Skill Claude CodeCodex

Deep-dive health check on a single Linear project. Produces assessment with 7 dimensions - On Track / At Risk / Stalled.

breethomas/bette-think

Skill Claude CodeCodex

Expert prompt optimization system for building production-ready AI features. Use when users request help improving prompts, want to create system prompts, need prompt review/critique, ask for prompt optimization strategies, want to analyze prompt effectiveness, mention prompt engineering best practices, request prompt…

breethomas/bette-think

Skill Claude CodeCodex

Pattern recognition across your product decisions. Analyzes saved strategy sessions to surface themes, recurring risks, and suggested next steps.

breethomas/bette-think

Skill Claude CodeCodex

Shape work using the Shape Up methodology (Ryan Singer, Basecamp). Walk through the 4-step shaping process to create pitches ready for betting. Distinguishes between established product mode (fixed time, variable scope) and new product mode (looser constraints). Use when planning cycle work, writing pitches, or…

breethomas/bette-think

Skill Claude CodeCodex

Write specifications at the right depth for any project. Progressive disclosure from quick Linear issues to full AI feature specs. Embeds Linear Method philosophy (brevity, clarity, momentum) with context engineering for AI features. Use for any spec work - quick tasks, features, or AI products.

breethomas/bette-think

Skill Claude CodeCodex

Start AI evals without overengineering. Create your first 20 test cases in a spreadsheet using PM-Friendly Evals approach.

breethomas/bette-think

Skill Claude CodeCodex

Your product soundboard. Work through product decisions conversationally - Claude gathers context, challenges assumptions, captures decisions, and creates Linear issues.

breethomas/bette-think

Skill Claude CodeCodex

Analyze Linear workspace health and usage patterns before jumping into backlog work. Like a pre-flight check for a new PM joining a team or organization.

breethomas/bette-think

Skill Claude CodeCodex

Build an LLM-as-Judge evaluator for one specific failure mode. Binary pass/fail only. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness) and cannot be checked with code. Do NOT use when the failure can be checked with regex, schema validation, or execution tests. Do NOT use…

breethomas/bette-think

Skill Claude CodeCodex

Evaluate RAG pipeline retrieval and generation quality separately. Measure Recall@k, Precision@k, MRR, NDCG@k for retrieval. Assess faithfulness and relevance for generation. Use when the AI feature uses retrieval (search, knowledge base, document QA). Do NOT use for non-RAG AI features.

breethomas/bette-think

Skill Claude CodeCodex

Create diverse synthetic test inputs using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do NOT use when you already have 100+ representative real traces (use stratified sampling instead).

breethomas/bette-think

Skill Claude CodeCodex

Systematic error analysis on real AI traces. Read traces, judge pass/fail, let failure categories emerge from data, compute failure rates, decide what to fix. Use when you have 50+ test cases or are seeing production failures. Do NOT use when you have fewer than 20 test cases (use /start-evals first).