Skill UI

Specialized skill to rewrite and humanize AI-generated natural language files (like notes or documentation). It removes common 'AI-isms' such as sycophantic openings, stock vocabulary, over-explaining, and excessive signposting. Users can choose between a fast, deterministic regex cleanup or a deep LLM rewrite (default mode) using Claude to enhance burstiness and match a natural human voice, all while strictly preserving code blocks, URLs, and headings.

A professional layout template designed for publishing long-form articles, newsletters, or essays on platforms like Substack, Medium, or WeChat Official Accounts. It mimics a high-end magazine style, featuring distinct sections for hero images, structured text blocks, styled quotes, and code snippets to enhance readability and visual appeal.

A sophisticated presentation template designed for technical content, mimicking the clean, professional aesthetic of GitHub blogs or product changelogs. It features a dark GitHub-dark background, vibrant purple and blue radial ambient lighting, a multi-color gradient title, and dedicated GitHub-style code blocks. Perfect for tech talks, deep-dive tutorials, and developer documentation.

A structured presentation deck designed for rigorous review of safety incidents, security risks, and policy compliance. It utilizes distinct visual cues, including hazard stripes, L1/L2/L3 severity tiers, and dedicated code blocks for policy review (e.g., YAML). Ideal for red team exercises, post-incident reviews, and high-stakes technical briefings.

A specialized presentation deck template designed for internal engineering talks, technical conferences, and deep-dive knowledge sharing. It features a professional GitHub-dark theme, JetBrains Mono coding font, and a structured layout including Cover, Agenda, main content slides (with code blocks), demo slides (terminal screenshots), and Q&A sections.

A comprehensive three-column layout template designed for high-readability technical documentation, such as API references, tutorials, and guides. It features a sticky side navigation, main article body with support for code blocks and callouts, and a scroll-spy Table of Contents (TOC). Includes search and version control.

A structured, horizontal-swipe presentation template designed for comprehensive weekly team reporting. This deck systematically covers key operational areas, including features completed (Shipped), ongoing project progress (In flight), major roadblocks (Blocked), performance metrics (KPIs), and actionable items requiring support (Asks). It is ideal for standardizing weekly status updates and executive reporting.

A Claude Code Stop hook that mechanically blocks session completion until deterministic quality checks pass: rationalization regex warnings, stale learning-library detection via file mtime, and disk-space thresholds. Enforces learning-capture habits with zero AI inference.

An automated verification system designed for critical healthcare application deployments (EMR/EHR). This harness enforces stringent patient safety standards by running multiple mandatory test gates, including Clinical Decision Support System (CDSS) accuracy, Protected Health Information (PHI) leakage prevention, and data integrity checks. A single failure in critical gates automatically blocks deployment, ensuring regulatory compliance and optimal patient safety in the CI/CD pipeline.

This skill generates the critical Client Validation Document (Part 5), serving as the definitive checkpoint where raw, unbiased v1 research findings are formally presented to the client. It structures complex findings into actionable blocks, forcing client decisions (ACCEPT, REJECT, EDIT, or DEFER) on strategic implications. This ensures all subsequent project phases are aligned with confirmed business consensus.

This comprehensive guide details the rigorous process of preparing a double-blind academic paper for its final, public, dual-published status across ACM and IEEE platforms. It systematically covers de-anonymization (restoring names, affiliations, and acknowledgments), ensuring all rebuttal promises are met within strict page limits, and managing complex metadata requirements (ORCID, CCS concepts, rights blocks). It serves as a final production checklist for authors.

A comprehensive guide for designing, auditing, and reporting advanced statistical and causal inference experiments. It emphasizes moving beyond simple accuracy metrics to quantify uncertainty, model robustness, and causal mechanisms. Covers metrics like coverage, KL divergence, and regret, and outlines best practices for seeding, compute fairness, and creating standardized reporting blocks (e.g., UAI standards).