Skill UI

This skill implements advanced 'Gatekeeper' logic to optimize AI agent performance in long-running workflows. It prevents context window bloat by sharding metadata, allocating token budgets, and enforcing Atomic Precision to deliver purely functional, filler-free responses. Ideal for complex coding, multi-step reasoning, and large document analysis where conciseness is critical.

This skill generates a concise and enforceable security policy document for applications handling sensitive data. It creates a single coherent Blue Book using MUST, SHOULD, and CAN language, defining explicit assumptions, scope, and security gates. The workflow includes gathering context, drafting the policy, enforcing guardrails against secrets, and performing quality checks on threat models and data handling rules.

This skill optimizes content for search engine featured snippets and SERP features. It formats text into concise answers, lists, and tables to secure position zero results. Ideal for SEO strategies, FAQ optimization, and structured data markup to improve visibility.

Rewrites the last response to be simpler and shorter while preserving all key decisions, action items, and substance. Useful when the user requests a TLDR, a condensed version, or a compressed answer without losing important details.

This tool extracts key information from PDF files and generates a concise bullet-point summary. It reads the document text, identifies main topics, and returns 3-5 essential points to help users quickly understand the core content without reading the entire document.

Generate structured changelogs from git history. Groups commits by time period, classifies features, fixes, refactors and breaking changes, and writes concise user-facing release notes with migration hints.

Megacave is a skill that makes the AI respond in Classical Chinese (文言文) while keeping technical terms verbatim. It reduces word count, uses classical grammar and particles, and persists until explicitly disabled. Suitable for users who want concise, classical-style responses in technical discussions.

Ultracave is a communication mode that strips all fluff from technical responses. It uses sentence fragments, one word per fact, and preserves code, commands, and paths verbatim. This style ensures maximum compression while maintaining technical substance. It persists throughout the session until explicitly disabled. Ideal for developers needing precise, concise information without unnecessary explanations.

This tool creates concise competitor summary reports based on provided names, URLs, and evidence. It organizes observations on positioning, audience, and offerings, then provides actionable implications. Ideal for SEO analysis and market research where competitor data is available. It validates input facts and avoids fabrication, ensuring results are grounded in supplied evidence.

Optimize target questions and existing passages for featured snippets with clear structure, factual scope, and concise rationale.