Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Facilitates structured ideation sessions using proven brainstorming techniques (SCAMPER, SWOT, 5 Whys, Mind Mapping, Six Thinking Hats, Reverse Brainstorming, Starbursting, Brainwriting). Produces a brainstorming-report.md of organized ideas and actionable insights. Operates in three intents: Create (new session), Update (add techniques or deepen coverage), Validate (confirm insights align with project goals). Use when the user says: "brainstorm", "ideate", "generate ideas", "explore options", "SCAMPER", "SWOT analysis", "mind map", "Six Thinking Hats", "5 Whys", "creative session", "what if we", "let's explore", "think through possibilities", "find alternatives", or "problem-solve". This skill PLANS only — it never writes application code or runs tests.
Use when checking a radiology or medical AI study design before drafting or submission. Reviews the analysis unit, cohort logic, leakage risks, comparator, validation strategy and reporting-guideline fit. AI-vs-expert benchmarks are /design-ai-benchmarking.
Draft a professional, audience-aware email or reply with calibrated tone and a clear call to action. Use when the user needs one message, response, follow-up, support note, or meeting request; use sales-email-sequences for a coordinated multi-touch outbound campaign.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
NSFC research proposal writing assistant (research objectives, research content, key scientific questions). Triggered when the user needs to write the research content of a grant application, break down research topics, or distill scientific questions. Defaults to the General Program, and supports Key, Young Scientists, and provincial funds.
Knowledge base architecture selection, curation, and governance. Use when choosing between document-based (RAG), entity-based (graph), or hybrid KB architectures, establishing content curation workflows, implementing versioning and governance, or evaluating quality metrics. For building retrieval pipelines, use the rag-implementer skill. For building knowledge graphs, use the knowledge-graph-builder skill.
Runs systematic literature reviews by searching PubMed, arXiv, bioRxiv, and Semantic Scholar (plus web search via parallel-cli), screening studies, extracting data, synthesizing themes, and verifying citations with verify_citations.py. Produces a markdown and PDF review with a PRISMA-style flow diagram and a bibliography in APA, Nature, or Vancouver style. Use when conducting a systematic or scoping review, synthesizing research on a topic, writing the literature review section of a paper or thesis, identifying research gaps, or checking citations in a review. Not for looking up a single paper or database record; use the specific database skill instead
Converts Notion product or technical specs into implementation plans, linked tasks, and evidence-based progress updates. Use for planning or implementing a spec, creating tasks from requirements, or reconciling implementation with spec changes.
Draft performance reviews, self-assessments, peer reviews, and upward feedback in your own voice. Analyzes your contributions, emails, and meeting history via WorkIQ, then produces honest, impact-focused drafts using the STAR format. USE FOR: write my performance review, draft self-assessment, peer review, 360 feedback, annual review, mid-year review, upward feedback, write review for colleague, performance appraisal.
Before any explanation or answer, require the learner to produce a free-recall attempt and confidence rating. Use when a student wants help understanding or reviewing a topic — this skill ensures the AI works from what the learner already knows.
Search YouTube by keyword and return structured video metadata (title, URL, channel, views, duration, date) via yt-dlp. No API keys. Triggers on: "search youtube", "find youtube videos", "top youtube videos on", "trending videos on", "youtube results for", "yt search", "/yt-search".
Extract captions from a YouTube video link and convert them into a Chinese transcript. Supports auto-generated and manual captions. Use cases: (1) the user provides a YouTube link and asks to extract captions/transcript, (2) the user asks to convert YouTube video content into text, (3) the user says "help me turn this YouTube video into text" or similar. Triggers: YouTube captions, video to text, extract captions, YouTube transcript, video transcript.
Structures new and vague problems into clear intake documents. Use when the problem is not yet mature enough for the backlog, when someone brings an idea or need without defined scope, or when you need to decide what the next artifact in the flow should be.
Search and retrieve Japanese laws and regulations via the official e-Gov Law API V2 (no auth required). Supports law name search, article retrieval, amendment history, and full-text keyword search. Useful for legal research, compliance checks, contract review, and any task involving Japanese statutes (民法/Civil Code, 会社法/Companies Act, 個人情報保護法/APPI, 労働基準法/Labor Standards Act, etc.). 日本の法令をe-Gov法令API V2経由で検索・取得するスキル。法令名検索、条文取得、改正履歴、キーワード検索に対応。Use this skill when researching Japanese laws, regulations, or legal texts.
Plan weekly family meals based on fridge contents and a budget. Generates a 7-day dinner plan, identifies what to buy vs. what's already in the fridge, and saves the plan. Triggers on: /meals plan, /meals show, /meals pref, weekly meal planning requests, 'what should we eat this week', dinner ideas for the family.
Receive and verify Notion webhooks. Use when setting up Notion webhook handlers, debugging Notion signature verification, completing the verification_token handshake, or handling workspace events like page.content_updated, page.properties_updated, comment.created, or data_source.schema_updated.
Leverage Perplexity CLI for web research, deep reasoning, and independent validation. Use when you need current/external knowledge, want a second opinion before decisions, or want to delegate complex analytical thinking to specialized reasoning models. Complements (not replaces) standard web tools. Can be invoked directly or spawned as a subagent.
Transcribe audio to text with ElevenLabs Scribe and Whisper models via inference.sh CLI. Models: ElevenLabs Scribe v2 (98%+ accuracy, diarization), Fast Whisper Large V3, Whisper V3 Large. Capabilities: transcription, translation, multi-language, timestamps, speaker diarization, audio event tagging. Use for: meeting transcription, subtitles, podcast transcripts, voice notes. Triggers: speech to text, transcription, whisper, audio to text, transcribe audio, voice to text, stt, automatic transcription, subtitles generation, transcribe meeting, audio transcription, whisper ai, elevenlabs stt, scribe, eleven labs transcribe
Use when user wants to read/search/send/analyze Telegram messages via tgcli CLI. Trigger on requests about channel/chat history, digests/news, mentions, files, topics, contacts, groups, tags, media downloads, multi-account profiles, and archive/sync status. Also covers group admin (join requests, rename, members, invite links, join/leave). For edit/delete/reactions, use telegram-mcp instead.
Shell history management with Atuin. Use when configuring shell history, setting up history sync, searching command history, importing history from other shells, troubleshooting atuin issues, or optimizing history workflows. Covers installation, sync setup, search modes, statistics, and self-hosting.
GitHub Projects management via gh CLI for creating projects, managing items, fields, and workflows. Use when working with GitHub Projects (v2), adding issues/PRs to projects, creating custom fields, tracking project items, or automating project workflows. Triggers on gh project, project board, kanban, GitHub project, project items.
Use LLM as a simulator of expert debates and opposing viewpoints instead of getting a single sycophantic answer. Use this skill when the user needs to make an important decision, wants to stress-test an idea, needs devil''s advocate analysis, wants to avoid confirmation bias, or says "argue against this", "what are the counterarguments", "simulate experts", "debate this", "challenge my thinking". Based on Karpathy 31k-like post.
Explain concepts, formulas, mechanisms, and principles until they can be recognized, derived, and transferred: use plain Chinese to connect concrete situations, criteria for judgment, how they work, and the conditions under which they hold. USE WHEN the user invokes ljg-explain, says "explain it in plain terms", "explain this concept or formula thoroughly", "Feynman-style explanation", "ELI5", or wants to understand a topic from scratch and apply it to new situations. NOT FOR pure polishing or translation, full-length reading companions, interpretation of an entire book or paper, or requests for only a formal proof or operating steps.
Paper X-ray. Extracts what the paper says (problem-perspective-result) and what it means for lijigang (cognitive delta cards in ASCII art). Use when user shares an arxiv link, paper URL, PDF, or asks to analyze a research paper. Usually called via ljg-xray router. Do NOT use for blog posts or non-academic articles (use ljg-xray-article instead).
Agent-callable Microsoft Outlook tools — read and search mail, send/reply/forward, organize messages and folders, manage calendar events, and manage contacts. Use when the user mentions Outlook, Microsoft 365 mail/calendar/contacts, or wants to send, read, search, or organize email, schedule events, or look up contacts — even if they don't name Outlook explicitly.
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.