Research

Use this skill when asked about "hooks", "PreToolUse", "PostToolUse", "SessionStart", "hook events", "validate tool use", "block commands", "add context on session start", or implementing event-driven automation.

Transform ambiguous requirements into precise specifications. Use before any non-trivial implementation.

Use when configuring project preferences in .c3/settings.yaml - diagram tools, layer guidance, guardrails, and handoff steps

Generate appropriate commit messages and maintain git log documentation. Use when preparing to commit changes, reviewing git history, or maintaining project change documentation. Provides commit message generation, git log maintenance, and quick command reference.

ML research for RAN with reinforcement learning, causal inference, and cognitive consciousness integration. Use when researching ML algorithms for RAN optimization, implementing reinforcement learning agents, developing causal models, or enabling AI-driven RAN innovation.

Apply systematic research methodology for multi-step research, fact-finding, web search, or verification tasks. Use when performing Brave Search, Puppeteer navigation, or synthesizing information from multiple sources.

将一条已生成的 digest/research 归档到指定 topic，并更新 topic 的 sources/timeline（M2/M3 辅助能力）。

Search the web and extract content using WebSearchAPI.ai. Use when needing real-time web data, current information, news, research, or when asked to search the internet. Supports web search, content extraction, and web scraping with advanced filtering options.

한글 기반 클로드 스킬 자동 생성 도구. 사용자가 "클로드 스킬을 만들어줘" 또는 "[요구사항] 스킬 만들어줘"라고 요청할 때 사용. Progressive disclosure 원칙을 따르는 한글 문서 구조(SKILL.md + references/)를 자동으로 생성하고, 실전 예시를 포함한 일관성 있는 스킬 템플릿을 제공.

下書きしたブログ記事の質を向上させるためのレビューアシスタント。オリジナリティ（著者固有の視点・思考プロセス）、構成の読みやすさ、事実の正確性、炎上リスク、共有価値などの観点から定量的にレビューし、具体的な良い点と改善点を指摘します。さらに、よりよい修正案も具体的に提示します。記事の下書きが完成したら、公開前に必ずこのスキルを使用してレビューしてください。レビュー完了後、問題が解決されたら、publication-preparation-assistantスキルを使用して公開準備を進めることを推奨します。

Use when working with OpenAPI Specification files to validate, create/modify paths and schemas, check references, and enforce best practices

Build 3D scenes, animations, and interactive experiences with Three.js. Use for product viewers, backgrounds, data visualization, or creative experiments.

Log a technical issue and return a reference number. Use when customer reports system errors, bugs, report generation failures, API issues, or integration problems.

Document completed development phases in IMPROVEMENTS.md with comprehensive summaries, lessons learned, patterns discovered, and Follow-up status. Ensures session work is captured for future reference and self-improvement tracking.

Enterprise-grade company research, competitive analysis, and market intelligence using Bright Data's professional web scraping and search capabilities. Use this skill when asked to research companies, conduct competitive analysis, create market reports, analyze industries, compare products/services, or gather business intelligence. Triggers include requests like "research [company]", "competitive analysis of X vs Y", "create a market report", "analyze the [industry] landscape", or "compare [products/companies]".

Security review and implementation support based on OWASP Cheat Sheet Series. Use for code review requests, security-related implementation/research, and vulnerability checks. Covers security topics such as XSS, SQL Injection, CSRF, and authentication/authorization.

Generate personalized content recommendations based on learner profiles, performance, preferences, and learning analytics. Use for adaptive learning systems, content discovery, and personalized guidance. Activates on "recommend content", "next best", "personalization", or "what should I learn next".

Use when discussing animation principles with users of unknown skill level, or when providing a balanced reference that works for any experience level

Kyle's professional background, work context, and general preferences for R development. Use this skill to understand his expertise level and tailor explanations appropriately.

Multi-agent debate with 3-phase workflow (Individual → Discussion → Synthesis)