Summarization

Create a structured summary of conversation context when the window is filling up

Transcribe and analyze YouTube videos

Researcher role for the ikigai project

Summarize URLs, local files, and transcripts with summarize CLI when available, with provider fallback.

Count words in text. Use to determine length of a document, e.g. to determine if it needs to be summarized before further use

Generates or rewrites student reports and progress descriptions for various education levels (Early Years to Grade 7), including IEYC, Physical Education, Kindergarten, and Novel Studies. Strictly adheres to exact or range-based word counts OR specific sentence counts, incorporates evidence, handles name replacements, and maintains a professional tone.

REQUIRED for any paper explanation or synthesis. Do NOT call attach_url_files and summarize inline — always open this SKILL.md first and follow its workflow. Use when a user asks to explain, summarize, synthesize, or deep-dive into a research paper, or when given an arXiv URL, DOI, paper title, or Zotero reference. The workflow spawns synthesizer subagents, presents results in reading view, and persists to KB.

Conducts thorough landscape research, competitive analysis, best practices evaluation, and evidence-based recommendations. Expert in market research and trend analysis.

Intelligently read any URL content with auto platform detection and fallback strategies. Supports WeChat, Zhihu, Bilibili, Toutiao, Weibo, Xiaohongshu, Douyin, X/Twitter, and generic websites. Trigger words: read url, read link, read this, fetch url, grab content, ink-reader

RSS 资讯聚合工具。从全球 92 个高质量技术博客采集 AI/科技资讯，支持关键词搜索、主题分类、时间范围过滤、来源筛选，输出 Markdown 和 HTML 双格式报告。

ARGUS NANO v2.1 - Compact research skill for context-limited sessions (~3KB). FOCO: Triangulacao (Academico + Pratico + Empirico), validacao de claims, busca multi-fonte com niveis de confianca. DROID: argus-quant-researcher.md tem conhecimento COMPLETO incluindo workflows detalhados, decision trees, e exemplos extensos. Triggers: "Argus", "pesquisa", "research", "papers", "repos", "validar claim", "triangular", "deep dive", "estado da arte", "como outros fazem"

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.

Generate format-controlled research reports with evidence tracking, citations, and iterative review. This skill should be used when users request a research report, literature review, market or industry analysis, competitive landscape, policy or technical brief, or require a strict report template and section formatting that a single deepresearch pass cannot reliably enforce.

Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.

生成紧急情况下快速访问的医疗信息摘要卡片。当用户需要旅行、就诊准备、紧急情况或询问"紧急信息"、"医疗卡片"、"急救信息"时使用此技能。提取关键信息（过敏、用药、急症、植入物），支持多格式输出（JSON、文本、二维码），用于急救或快速就医。

Display a rich explanation of the current conversation. Only use when explicitly called.

Comprehensive literature deep research across any academic domain using 120+ ToolUniverse tools. Conducts subject disambiguation, systematic literature search with citation network expansion, evidence grading (T1-T4), and structured theme extraction. Produces detailed reports with mandatory completeness checklists, integrated models, and testable hypotheses. Use when users need thorough literature reviews, target/drug/disease profiles, topic deep-dives, claim verification, or systematic evidence synthesis. Supports biomedical (genes, proteins, drugs, diseases), computer science, social science, and general academic topics. For single factoid questions, uses a fast verification mode with inline answer.

Categorical Rewriting: Triad 4 (World Transformation)

Analyze computer vision or graphics papers from local LaTeX source files/directories or Markdown documents, optionally incorporating public OpenReview reviews, and write a Chinese evidence-grounded overview.md.

Interactive review sessions with academic PDFs (lectures, research papers, book chapters). Extract concepts, run Q&A sessions, generate quizzes with scoring. Preserves mathematical formulas in LaTeX format. Privacy-preserving local processing - PDFs never uploaded. Use when studying academic materials, reviewing research, or preparing for exams.

Diagnose research quality and guide systematic query expansion. Use when starting research on any topic, when stuck in research, or when unsure if research is complete.

This skill should be used when the user needs to transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration.

Extract and analyze large PDFs (1MB-50MB+) with minimal token usage through local extraction, semantic chunking, and persistent caching. Enables 12-100x faster querying for technical documents like NIST, ISO, and AWS guides.

Create shareable briefing documents from sessions, research, or learnings.

read this skill for a token-efficient summary of the crypto subsystem

访问网页（Twitter线程、文章、社交媒体等），自动截图并生成包含完整内容的文档（PPT、PDF、Word等）。适用于保存Twitter长推文、网页存档、将网页内容转换为演示文稿等场景。

This skill generates a comprehensive set of Frequently Asked Questions (FAQs) from the course description, course content, learning graphs, concept lists, MicroSims, and glossary terms to help students understand common questions and prepare content for chatbot integration. Use this skill after course description, learning graph, glossary, and at least 30% of chapter content exist.

AI-powered diary generation for agents - creates rich, reflective journal entries (400-600 words) with Quote Hall of Fame, Curiosity Backlog, Decision Archaeology, and Relationship Evolution. Generates personal, emotional entries from the agent's perspective. Works best with Claude models (Haiku, Sonnet, Opus).

read this skill for a token-efficient summary of the catchup subsystem

read this skill for a token-efficient summary of the scp subsystem

Context management system for solving compaction problems. Provides TLDR summaries, conversation tracking, and efficient post-compaction recovery. Triggers on "/baton".

read this skill for a token-efficient summary of the overlay subsystem

Extract structured knowledge from source material. Comprehensive extraction is the default — every insight that serves the domain gets extracted. For domain-relevant sources, skip rate must be below 10%. Zero extraction from a domain-relevant source is a BUG. Triggers on "/reduce", "/reduce [file]", "extract insights", "mine this", "process this".

AI session compression techniques for managing multi-turn conversations efficiently through summarization, embedding-based retrieval, and intelligent context management.

Analyzes events through journalistic lens using 5 Ws and H, investigative methods, source evaluation, fact-checking, newsworthiness criteria, and ethical journalism principles. Provides insights on story angles, information gaps, credibility, public interest, and media framing. Use when: Breaking news, information verification, source analysis, story development, media criticism. Evaluates: Factual accuracy, source credibility, completeness, newsworthiness, bias, public interest.

Verified information generation and validation

精确复现特定作者的中文写作风格。适用于：(1) 以该风格从零生成文章，(2) 将AI风格或其他风格的文章改写为该风格，(3) 在同一次任务里对草稿做终稿打磨/精修（保持作者笔力，不得改成中性说明书），(4) 审阅文章是否符合该风格，(5) 结构保真地将非简体中文翻译为简体中文（保留原始结构与不可改动片段，如人名/专名、代码、代码块、URL 等；不擅自增删）。核心特征：半文半白的用词、长短交替的句式节奏、类比先行的论证方式、冷面热心的情感表达、第一人称介入的立场标定；并在不破坏作者习惯的前提下，清除显眼的 AI 写作痕迹（24 项检测）。触发词：写作、改写、风格、润色、重写、精修、再优化、二稿、终稿、最终版、翻译、译、translate、翻成、译成、转为简体。

Unified speech-to-text skill. Use when the user asks to transcribe audio or video, generate subtitles, identify speakers, translate speech, search transcripts, diarize meetings, or perform any speech-to-text task. Also use when a voice message or audio file appears in chat and the user's intent to transcribe it is very clear.

Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections. Covers identity, chemistry, pharmacology, targets, clinical trials, safety, pharmacogenomics, and ADMET properties. Use when users ask about drugs, medications, therapeutics, or need drug profiling, safety assessment, or clinical development research.

Parse, extract, and format transcripts (VTT, SRT, plain text) into structured Markdown packets with action items, decisions, questions, and topics. v2.0 uses hybrid Python+LLM architecture for VTT files. Integrates with ps-critic for quality review.

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).

Generate daily summary report from GitHub Commits, PRs, and Reviews

Guide for reading, interpreting, and applying statutes, regulations, and rules in legal and compliance contexts. Use when the user asks about (1) how to read and interpret statutes, regulations, or rules, (2) statutory interpretation methods and canons of construction, (3) understanding legislative intent, (4) applying statutes to specific legal situations, (5) extracting requirements from legal text, (6) distinguishing between different types of legal requirements, or (7) cross-jurisdictional compliance analysis.

Conduct enterprise-grade research with multi-source synthesis, citation tracking, and verification. Use when user needs comprehensive analysis requiring 10+ sources, verified claims, or comparison of approaches. Triggers include "deep research", "comprehensive analysis", "research report", "compare X vs Y", or "analyze trends". Do NOT use for simple lookups, debugging, or questions answerable with 1-2 searches.

Based on the context, write a summary of changes, what's left, production readiness, tests run, and APIs/packages used.

Scrapes content based on a preset URL list, filters high-quality technical information, and generates daily Markdown reports.

Transform long-form content into 15+ platform-ready assets. One article becomes threads, carousels, audiograms, video scripts, quizzes, discussion prompts, and more.

Islamic and Sufi wisdom - Tawhid unity, surrender navigation, 99 Names positions, dhikr practice, fana/baqa dissolution

Transform any book (PDF/ebook) into an interactive visual learning website with Mermaid diagrams, concept maps, and guided learning paths. Use when user says "create visual companion", "book to website", "visualize book", or "learning companion from book".

Fetch transcripts from YouTube videos for summarization and analysis.