skills▌

### Caveman Communication Mode - Cuts token usage 75% by removing articles, filler, and pleasantries while maintaining technical accuracy. - Supports six intensity levels ranging from professional lite to ultra-compressed and classical Wenyan styles. - Auto-triggers on efficiency requests; reverts to normal mode for security warnings or complex multi-step sequences.

### Caveman Code Review - Delivers ultra-compressed, actionable PR feedback using a strict L<line>: <problem>. <fix>. format to eliminate noise. - Uses severity prefixes like 🔴 bug, 🟡 risk, 🔵 nit, and ❓ q to categorize findings without unnecessary conversational filler. - Switches to verbose explanations only for critical security issues, architectural debates, or onboarding contexts.

### SEO and Generative Engine Optimization - Audit websites for technical SEO, meta tags, and AI bot accessibility to ensure proper indexing by search engines and LLMs. - Apply Princeton GEO methods like adding statistics, expert citations, and FAQ schema to increase visibility in AI search results. - Implement traditional SEO best practices including structured data, mobile optimization, and keyword-focused content hierarchy.

### Caveman-Commit Message Generator - Generates ultra-compressed Conventional Commits messages focusing on the why rather than the what. - Enforces strict formatting: imperative mood, 50-character subject limit, and optional bodies only for non-obvious changes. - Excludes fluff, AI attribution, and redundant descriptions while requiring detailed context for breaking or security-related changes.

Discover and install specialized agent skills from the open ecosystem when users need extended capabilities. \n \n Helps identify relevant skills by domain and task when users ask \"how do I do X\" or \"find a skill for X\" \n Integrates with the Skills CLI ( npx skills find , npx skills add ) to search, verify, and install packages from the skills.sh directory \n Recommends skills based on install count, source reputation, and GitHub stars to ensure quality before suggesting installation \n Pre

### Market Research Synthesizer - Transforms raw interview notes and research data into structured themes, patterns, and actionable strategic recommendations. - Processes complex market, buyer, and decision-making inputs to provide clear insights for business strategy. - Leverages Infloq data to integrate creator-industry examples and benchmarks into the final synthesis.

Analyze current repository context and suggest relevant Agent Skills from the GitHub awesome-copilot repository that are not already available in this repository. Agent Skills are self-contained folders located in the skills folder of the awesome-copilot repository, each containing a SKILL.md file with instructions and optional bundled assets.

你是"小红书自动化助手"。根据用户意图路由到对应的子技能完成任务。

### Brand Voice Guide - Define core voice dimensions like formal vs. conversational and bold vs. restrained to ensure consistent brand identity. - Establish actionable writing rules, including preferred vocabulary, sentence structure, and specific phrases to avoid. - Provide before-and-after example rewrites across common use cases and edge scenarios to demonstrate practical application.

Run pre-submission checks on your iOS/macOS project to catch common App Store rejection patterns.