Skill UI

This domain-agnostic skill ranks impediments, risks, and gaps by using a specialized value-stream scoring model. It evaluates countermeasures based on four criteria: Return on Investment (ROI), Cost to Implement, Ease of Deployment, and Risk Factor. A proprietary formula calculates a final Priority score (1-100), allowing users to quickly determine the optimal sequence for remediation, improvement backlogs, or triage items.

This skill executes a corpus benchmark to verify the performance and cost claims of the cost booster system. It runs local booster tests against optional baselines like Gemini or Anthropic models. Results are persisted to JSON files for verification gates before releases. It checks win rates and escalation rates to ensure quality improvements and validate upstream tags.

This comprehensive tool analyzes the entire customer conversion funnel to pinpoint drop-off points, identify bottlenecks, and determine the root causes of underperformance (e.g., messaging, UX, targeting). It benchmarks current rates against industry averages, models improvement scenarios with projected revenue impact, and provides statistically validated, prioritized action plans to maximize overall conversion rate.

A comprehensive guide for structuring high-level theoretical computer science papers for top-tier conferences like ICALP. It dictates how to present the model, state the theorem, demonstrate the improvement over prior bounds, and manage proof complexity within strict page limits, ensuring maximum clarity and verifiability for expert reviewers.

This guide details how to structure a scholarly response document after receiving major revisions for a theoretical model. It emphasizes that the response must argue from substantive theoretical improvements—by adding derivations, simulations, or clarifying scope—rather than merely defending the original wording. It provides a rigorous, point-by-point framework for authors addressing critical academic feedback.

This guide assists researchers in evaluating the fit of their manuscripts for the journal Scientific Decision Making. It covers journal scope, required methodologies (e.g., system modeling, policy evaluation), structural improvements, common formatting pitfalls (footnotes, Arabic numerals), and cross-journal selection criteria to maximize acceptance chances.

Master comprehensive evaluation strategies for LLM applications, covering automated metrics like BLEU and ROUGE, human evaluation dimensions, and LLM-as-Judge patterns. This skill helps measure performance, compare models, detect regressions, and validate prompt improvements. Includes Python implementation examples for metrics and evaluation suites.