Verification + citation workflow. Use whenever the user asks you to look up information, mentions latest/today/real-time, requests news/weather/prices/scores, or whenever you plan to reference external facts. Requires source links and (when relevant) local published/updated time. NEVER fabricate.
現在のブランチに関連するPRのレビューコメントを取得する。このスキルは、ユーザーが「PRレビュー」「レビューコメント」「PR feedback」「review comments」と言ったとき、または現在のPRに対するレビューを確認したいときに使用する。
Bilimsel metod, hipotez, kanıt değerlendirme, bias analizi. ⚠️ Araştırma/analiz için kullan. Mimari karar için → ultrathink-core.
Brave Search API via curl. Use this skill for privacy-focused web, image, video, and news search with no tracking.
News briefing + verification workflow. Use when the user asks for news, headlines, daily briefing, “today's news”, “latest updates”, breaking news, or requests specific current numbers/events that require reliable sources and timestamps. Requires source links + local published time; NEVER fabricate.
Review legal documents as an experienced attorney. Analyzes contracts, ToS, privacy policies, NDAs, and corporate docs section-by-section. Identifies risks, gaps, and unfavorable terms with specific replacement text for problematic clauses.
Analyze and optimize E-E-A-T signals (Experience, Expertise, Authority, Trust) for content credibility.
Build and measure topical authority through comprehensive coverage, content mapping, and competitor analysis.
Content optimization workflow covering keyword integration, semantic enhancement, structure optimization, and AI extractability. Use for improving existing content for both search engines and LLMs.
Write well-structured articles with outline-first workflow. Includes sentence variation, readability guidelines, and formatting best practices.
Create SEO-optimized content that ranks AND reads like a human wrote it. Takes a target keyword/cluster and produces publication-ready articles. Includes AI-detection avoidance patterns and E-E-A-T signals.
Optimize content structure and framing for AI citation. Covers trust formats, extractability, and fact-density.
Teaches effective documentation search using the blz CLI tool. Use when searching documentation with blz, looking up APIs, finding code examples, retrieving citations, or when questions mention libraries, frameworks, "how to", or documentation topics. Covers BM25 full-text search patterns, citation retrieval, and efficient querying.
Detect human-oriented content in LLM artifacts. Flags attribution, personas, redundant explanations, marketing language, and decorative elements that waste tokens without improving LLM behavior.
Frame press releases for AI/LLM citation and authority building using research-based positioning.
Create llms.txt files that help AI systems navigate and understand your site structure for better citations.
Web search via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
This skill should be used when researching best practices, evaluating technologies, comparing approaches, or when "research", "evaluation", or "comparison" are mentioned.
This skill should be used when synthesizing multi-source research, presenting findings with attribution, or when "report", "findings", or "synthesis" are mentioned.
Search arXiv preprint repository for research papers in physics, mathematics, computer science, quantitative biology, finance, and statistics. Use when finding academic papers, preprints, ML research, scientific publications. Triggers: arxiv, preprint, research paper, academic paper, scientific literature.
Evaluate LLM outputs with multi-dimensional rubrics, handle non-determinism, and implement LLM-as-judge patterns. Essential for production LLM systems. Use when testing prompts, validating outputs, comparing models, or when user mentions 'evaluation', 'testing LLM', 'rubric', 'LLM-as-judge', 'output quality', 'prompt testing', or 'model comparison'.
Research scope too big? This skill decomposes large questions into independent parts, spawns parallel researchers, and synthesizes findings. Essential when comprehensive research would overflow a single context window.
