Skill UI

Build a production-ready behavior tree runtime with Blackboard, action/condition leaves, and composites. Implement Utility AI using response curves and action evaluators. Create hybrid agents combining both for complex NPC decision-making beyond simple FSMs. Suitable for game development and AI system architecture.

This skill verifies completed work against acceptance criteria using a three-stage pipeline. It performs mechanical checks like linting and testing, semantic reviews for compliance, and multi-model consensus when uncertain. It supports automated fix loops and ensures code quality beyond simple test passing, providing proof of completion.

Restructures any vague build, research, or legal-drafting request into a highly structured IRAC (Issue, Rule, Analysis, Conclusion) prompt. This method optimizes output quality for frontier models by forcing the definition of constraints, underlying rules, required reasoning, and precise deliverables, moving beyond simple prompting.

This skill analyzes various legal AI outputs, such as memos, contracts, and reports, to assess their structural integrity and legal robustness. Inspired by Minimum Description Length (MDL), it audits for unnecessary complexity, overly verbose caveats, hidden legal uncertainties, or inefficient workflow design, ensuring the resulting output is as concise and simple as legally safe.

This tool provides a statistically rigorous framework for analyzing a user's private LinkedIn post performance data. It moves beyond simple averages, utilizing median/MAD and permutation testing to determine if observed patterns are genuine or statistical noise. It guides users through three steps: descriptive analysis, pattern mining, and sizing future A/B experiments, ensuring hypotheses are testable and avoiding over-conclusion. Works only with your own exported data.

This framework moves beyond simple storage solutions (like vector databases) to treat memory as a complex metabolic system. It provides tools and methodologies to audit, price, and govern an agent's memory, focusing especially on the forgetting policy. Key functions include cost profiling (construction vs. query energy), classifying stored records (fact/skill/log), and ensuring a mandatory forgetting policy to prevent state bloat and maintain performance.

Master the art of deterministic procedural generation for game content. This skill covers core algorithms like seeded RNG, Perlin/Simplex noise for heightmaps and terrain, weighted loot table selection, and dungeon layout generation (BSP, random walk). It allows developers to create vast, complex, and reproducible worlds from simple rules and a single seed, perfect for roguelike or survival genres.

This meta-skill automates the entire short-drama production pipeline, starting from a simple topic. The workflow analyzes the request to infer render style, character identity, and shot count. It first drafts a detailed, shot-by-shot shooting script and pauses for user review. After approval, it generates a universal cast reference image, per-shot composition images, and corresponding video clips. Crucially, it maintains character and scene consistency by anchoring every video to both the reference image and the composition image. Finally, it adds title/ending cards, burns subtitles, and de...

A comprehensive guide for implementing, gating, and managing feature flags within the Webiny system. Learn how to integrate simple boolean flags or complex nested groups, and apply checks at the API, admin UI, and configuration levels, ensuring robust feature rollout and kill switches.

Build a small native interface using the project's Expo configuration. Useful for React Native projects that need a simple native UI scaffold with minimal setup.

A set of behavioral guidelines derived from Andrej Karpathy's observations to help users writing, reviewing, or refactoring code with Large Language Models (LLMs). It guides developers to avoid overcomplication, make surgical changes, explicitly surface assumptions, and define verifiable success criteria, promoting clean, simple, and robust code development.

A meta-skill that evaluates task complexity and dynamically selects appropriate specialized skills for AI agents. It prevents overuse of tools on simple tasks, tracks successful skill combinations via memory, and coordinates execution across multiple domains to solve complex problems efficiently.