breethomas
@breethomas
Public Skills
calibrate
by breethomas
Post-launch AI feature calibration workflow. Document error patterns, review eval performance, and decide on agency promotion. Based on CC/CD framework for continuous calibration of AI products.
upgrade-evals
by breethomas
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).
agency-ladder
by breethomas
Plan the v1→v2→v3 agency progression for AI features. Walk through mapping how autonomy increases over time, define promotion criteria, and generate artifacts for stakeholder alignment. Based on CC/CD framework.
four-fits
by breethomas
Find which fit is broken before you burn cash scaling. Brian Balfour's framework for validating sustainable growth readiness.
coder
by breethomas
Apply Brian Balfour's CODER framework to drive organizational AI adoption. Constraints, Ownership, Directives, Expectations, Rewards.
four-risks
by breethomas
Run Marty Cagan's Four Risks assessment on an issue (value, usability, feasibility, viability). Use when evaluating features before building.
competitive-research
by breethomas
Systematic competitive intelligence with parallel agent analysis. Analyzes competitors thoroughly and synthesizes into actionable insights.
ai-cost-check
by breethomas
Calculate AI feature costs and challenge if you actually need it. Invokes ai-cost-analyzer agent for detailed economics modeling.
context-engineering
by breethomas
"[ARCHIVED] Full 4D Context Canvas reference. For new AI features, use /spec --ai. For debugging, use /ai-debug. For quality checks, use /context-check."
pmf-survey
by breethomas
Create and analyze a PMF survey using Rahul Vohra's Superhuman framework. The magic 40% benchmark for product-market fit.
prompt-engineering
by breethomas
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 templates, or need guidance on structuring AI instructions. Also use when users provide prompts and want suggestions for improvement.
ai-health-check
by breethomas
Pre-launch health check that blocks you from shipping broken AI features. Grades 6 dimensions (model selection, data quality, cost, monitoring, failure UX, optimization).
build-judge
by breethomas
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 before completing error analysis (/upgrade-evals).
generate-test-data
by breethomas
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).
eval-rag
by breethomas
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.
prd-writer
by breethomas
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.
agent-workflow
by breethomas
Expert system for designing and architecting AI agent workflows based on proven Meta methodologies. Use when users need to build AI agents, create agent workflows, solve problems using agentic systems, integrate multiple tools into agent architectures, or need guidance on agent design patterns. Helps translate business problems into structured agent solutions with clear scope, tool integration, and multi-layer architecture planning.
workspace-calibration
by breethomas
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.
lno-prioritize
by breethomas
Find out if you're spending time on the wrong things. Categorize backlog by Leverage/Neutral/Overhead and challenge your time allocation.
shape-up
by breethomas
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 coaching PMs on shaping.
strategy-session
by breethomas
Your product soundboard. Work through product decisions conversationally - Claude gathers context, challenges assumptions, captures decisions, and creates Linear issues.
now-next-later
by breethomas
Generate a Now-Next-Later roadmap using Janna Bastow's framework. Communicates sequence and certainty without false dates.
project-health
by breethomas
Deep-dive health check on a single Linear project. Produces assessment with 7 dimensions - On Track / At Risk / Stalled.
pm-frameworks
by breethomas
Expert knowledge of proven product management frameworks for discovery, growth, measurement, planning, and AI-era practices.
ai-debug
by breethomas
Diagnose why an AI feature is underperforming, hallucinating, or behaving inconsistently. Uses 4D audit to work backwards from symptoms to root cause.
spec
by breethomas
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.
growth-loops
by breethomas
Find your growth loop or stay stuck in linear acquisition hell. Identify viral, content, network, and paid loop opportunities using Elena Verna's framework.