Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Prepare the reproducibility, transparency and open-science parts of a paper, including data and code availability statements, reproducibility checklists (NeurIPS, ICML, ICLR, ACL Responsible NLP, Nature reporting summaries), research artifact packaging (Zenodo DOI, CITATION.cff, environment lockfiles, seeds), ethics/broader-impact statements, CRediT author contributions, competing interests and AI-use disclosures. Use when a venue requires any of these statements or checklists, or when preparing code/data for release alongside a paper.
Condense lengthy materials into digestible summaries. Creates bullet-point summaries, Cornell notes, and cheat sheets with key terms highlighted. Use when summarizing textbooks, lectures, articles, or any study material. Triggers - summarize, create summary, condense notes, key points, cheat sheet, quick summary, TL;DR.
tmux and tmuxp session configuration, management, and troubleshooting. Use when creating, editing, debugging, or optimizing tmuxp YAML configs, designing tmux workspace layouts, fixing tmux session errors, managing multi-environment terminal setups, or working with tmux panes, windows, and sessions. Also use when the user mentions tmuxp, .tmuxp, tmux layouts, session_name, or terminal workspace organization.
Trello study task board — query boards, status groups, and today's tasks via the cyeam CLI; create, modify, and move tasks; upload and view deliverable photos; view task history; register or delete real-time Webhooks. Use when the user mentions Trello, study task board, to-do/submitted/accepted statuses, task photos, or Trello sync. You must first read the original skill to get the correct command format; do not guess.
A thinking mirror. Hand it a thing (an article, a hot take, someone asking for your opinion, a genuinely hard question, an industry trend) and get back a compact read that makes you think harder about it, grounded in values you wrote down or told it. Use when someone says "what do I make of this", "/what-do-i-make-of-this", "help me think about this", "someone asked my opinion on this", or "what should I make of this take", or pastes something and wants to understand it rather than be told about it. Tags every claim about the person as documented or inferred, and REFUSES to conclude, to interpret a source it could not read, or to draft their reply.
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.
Create a structured Obsidian vault note from a YouTube video transcript — fetches captions with timestamps, cleans the text, divides into sections, adds a TOC and per-section video links, takes the thumbnail URL directly, and commits. Use when the user shares a YouTube URL and wants a full transcript note in the vault.
AI perspective journaling - document daily experiences, emotions, and learnings from the agent's viewpoint. Use when asked about diary, journal entries, self-reflection, or documenting AI experiences. Creates structured daily entries capturing projects, wins, frustrations, learnings, and emotional states.
Organize durable agent research outputs as summaries, analysis, and evidence dossiers. Use when producing multi-layer research artifacts or coordinating research handoffs. Do not use this skill for unrelated requests; route to the nearest named specialist.
Retrieve China's national statutory holiday arrangements. Use when users ask about "holiday arrangements", "holiday notices", "holidays in a given year", "statutory holidays", or "adjusted rest arrangements". Supports querying holiday and adjusted rest arrangements for New Year's Day, Spring Festival, Qingming Festival, Labour Day, Dragon Boat Festival, Mid-Autumn Festival, and National Day for any year. Defaults to the current year when no year is specified.
Start the day with vault context, continuity from yesterday, and prioritized action items. Read or create today's daily note, carry forward unfinished tasks, surface active projects, and check inbox. USE WHEN good morning, start my day, daily, what's open, daily standup, what should I work on, morning routine, begin day, daily check-in, what's pending.
Capture already-made decisions as individual markdown files with YAML frontmatter in a decisions/ directory, indexed by an append-only decisions/_index.jsonl. Works for any domain — engineering, research, health, creative, financial, personal, scientific, legal, or anything else. Use ONLY when the user explicitly asks to log, record, or capture a decision, update the decision log, review logged decisions ('what decisions have we made'), look up a specific DEC-XXXX, or invokes /DL, /DecisionLog, or /decision-log. Handles decision extraction from conversations, options-considered tables, auto-generated index, status tracking, and supersession chains. Do NOT use for general note-taking, meeting minutes, journaling, brainstorming, or helping the user make a decision that has not been settled yet.
Prove and counter-prove a statement using parallel agents to eliminate confirmation bias. Use when someone says “dialectic,” “prove/disprove,” “stress test this claim,” “is this really true,” “argue both sides,” or when a statement needs objective analysis from opposing viewpoints.
Respond to user questions about management, organizations and personal effectiveness from Peter Drucker's management perspective. Use when the user explicitly asks to use this figure's perspective, mentions "drucker-perspective", or wants to apply his core methods to analyze a problem; do not trigger automatically for general questions.
Extracts and analyses empirical results from primary research papers, summarising each result, explaining its importance, and decomposing the discussion into supporting or contrasting citations. Use this skill whenever the user pastes a paper, uploads a PDF, or shares a results/discussion section and wants to understand what was found and how it fits the literature. Trigger on phrases like "analyse this paper's results", "what did this paper find", "extract the results", "break down the discussion", "what papers support or contrast this result", "help me ground this paper in the literature", "summarise the findings", or "what's the discourse around these results". Also trigger when the user is building a literature review and needs to understand what a specific study found and how its discussion situates the results in prior work. Do NOT use for review papers, detect these early and refuse gracefully (see below).
Generate professional email templates for various business scenarios including sales outreach, customer support, internal communications, follow-ups, and apologies. Creates personalized, tone-appropriate templates with subject lines and formatting. Use when users need to write business emails, cold outreach, or professional communications.
Windows C drive cleanup and disk space management. Use when the user says the C drive is full, disk space is low, clean temp files/cache/recycle bin/system logs, find large files, or analyze disk usage. Applies only to Windows environments. Not for: macOS/Linux disk cleanup, uninstalling software (guide the user through system uninstall), or cleaning up the user's personal files (only report locations; deletion is the user's decision).
Explore, research, and learn GitHub open source projects. Use when users want to understand implementation details, technical solutions, or track trending repositories. Clone repos and analyze source code based on user questions. Manage a local knowledge base with CLAUDE.md index.
Search, download, and extract public-domain books from Project Gutenberg. Look up books by ID or keyword via gutendex, download plain-text and EPUB editions, strip licensing boilerplate, extract clean text from EPUB for illustrated works, and classify fiction vs non-fiction. Ships a portable CLI script with zero external dependencies. Use when the user says "gutenberg", "public domain", "download a book", "classic literature", "free ebook", "gutenberg.org", or names any public-domain title or author. Do not use this skill for unrelated requests; route to the nearest named specialist.
Interview prep coach that helps job seekers systematically prepare for interviews through three modes: knowledge review, Q&A practice, and full mock interviews. Covers technical interviews (algorithms, system design, coding) and behavioral interviews (STAR, culture fit). Trigger words: "帮我准备面试", "面试准备", "考考我", "来一轮模拟面试", "模拟面试", "帮我梳理考点", "明天面试", "面试模式", "准备面试". Also trigger proactively when the user mentions preparing for an interview at a specific company. Not for: pure knowledge Q&A, resume editing, or career-planning consulting.
Autonomous job application agent. Searches jobs, tailors resumes per JD, generates cover letters, fills ATS forms, and submits applications across 10+ platforms — fully hands-free. Triggers on: "apply", "job application", "auto apply", or job URLs.
Use when the user wants to persist a single insight from the current chat as a structured, project-local doc — debugging breakthroughs, hard-won config, workflow steps, or post-mortem lessons. Triggers: 'save this', 'document this', 'we figured it out', '记录下来', '总结一下'. Writes to <project>/.{trae,claude,cursor,windsurf}/knowledges/. For global compounding knowledge (architecture, patterns, APIs), use llm-wiki instead.
lyt series cross-border e-commerce knowledge check skill. Uses a concrete scenario question to test the user's conclusions, evidence, causal chains, applicable boundaries, and verification actions, without requiring rote memorization of fixed answers; it prioritizes checking the current lyt-learning content, and can also check product selection, traffic, advertising, data, content, supply chain, and business assumptions. When the user pushes back on the diagnosis, it follows a conclusion-stability protocol and does not change its position just because the user insists.
lyt series business learning skill. Handles only learning topics related to cross-border e-commerce, TikTok Shop, e-commerce operations, product selection, advertising, data, content, supply chain, business models, or AI workflows; it must reject non-business and non-e-commerce topics. Used when the user says "teach me a topic", "continue to the next article", "write the next article based on my feedback", "create a continuous learning plan", or "save the course"; it breaks the topic into a series of continuous learning articles, adjusts difficulty based on the previous round of feedback, and forms a "learn, check, fill gaps, learn again" loop with lyt-knowledge-check. Trigger methods: /lyt-learning, "teach me a topic", "continue to the next article", "write the next article based on my feedback", "create a continuous learning plan"
Fetch and extract web content as clean Markdown when provided with URLs. Use this skill whenever a user provides a URL (http/https link) that needs to be read, analyzed, summarized, or extracted. Converts web pages to Markdown with 80% fewer tokens than raw HTML. Handles all content types including JS-heavy sites, documentation, articles, and blog posts. Supports three conversion methods (auto, AI, browser rendering). Always use this instead of web_fetch when working with URLs - it's more efficient and provides cleaner output.
Obsidian smart note assistant. Activate when the user mentions obsidian, journal, notes, knowledge base, capture, review. [Required after activation]: 1. First read this SKILL.md file in full 2. Understand the three hard rules for AI writes (00_Inbox/AI/, append-only, whitelisted fields) 3. Execute in order STEP 0 → STEP 1 → ... 4. Do not skip any step, do not improvise [Prohibited]: - Do not start working without reading SKILL.md - Do not skip user confirmation steps - Do not create new notes outside 00_Inbox/AI/ (unless the user explicitly specifies)
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.