Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Conducts systematic root cause analysis using proven methodologies including Toyota's 5 Whys, Ishikawa fishbone diagrams, Pareto analysis, and fault tree analysis. Use when investigating bugs, debugging code, troubleshooting systems, diagnosing equipment failures, analyzing life problems, or identifying underlying causes of any issue across software engineering, hardware maintenance, process failures, or personal challenges.
Use when tasks involve reading and summarising an academic paper from either a PDF file or an arXiv URL. If the input is a PDF, convert it to images for accurate reading (equations/figures). If the input is an arXiv URL, download the LaTeX source to read. Output the summary as a standalone LaTeX file.
Use when the user asks to collect, submit, upload, or summarize CawPlan QA session daily JSON — e.g. 提交 QA 日报, QA 日报, 测试日报, 提交测试日报, QA 会话上报, or /cawplan-qa-commit. NOT for: coding/代码日报 (use cawplan-coding-commit), git commits, viewing insights, querying costs, or searching tickets.
Deep research methodology (8-step method): turn a vague topic into a high-quality research report. Trigger words: /deep-research, deep research, help me research, look into this, comparative analysis. Note: if the user needs a visualization or diagram rather than a report, use the research-to-diagram skill.
Deepseek web search tool. Call AI web search capabilities with one click to quickly get real-time information. Use when the user needs to retrieve real-time information via Deepseek search, web search, or AI search. Trigger words: Deepseek搜索, deepseek websearch, 联网搜索, AI搜索, ds搜索.
Drafts or rewrites a Related Work / prior work section positioned against actually-retrieved papers — derives the REQUIRED clusters from the paper's own claimed scope (not just whatever was retrieved), clusters prior work into themes, articulates the delta (what this paper adds) per cluster, enforces a per-cluster citation floor and routes empty expected clusters back to find-papers, follows the target community's placement and citation conventions (numeric ACM/IEEE vs natbib author-year, single- vs double-blind self-citation, where the section sits at NeurIPS/CHI/SIGMOD-style venues), and admits only verified citations. Use when the user says "related work", "prior work", "position my paper against the literature", "how do we differ from X", "reviewers said related work is thin/missing/a laundry list", or asks to add citations to a draft. Works from papers found via find-papers and/or an existing .bib — it never invents references.
Find web sources with query-relevant page excerpts and optional full-page content, and discover workflows, data APIs, and indexes. Use for web research or finding structured records, listings, transcripts, and datasets. Supports semantic tool discovery, domain matching, and progressive catalogue browsing.
A tool for managing GitHub Star projects, tracking recent activity and updates, discovering project opportunities in saved items that may be valuable for local skills, and generating evidence packs and daily candidate queues. Also supports automatic starring of content and a dashboard. Not for one-off deep research into an unfamiliar repository.
Create a structured session handoff document for continuity across sessions. Use when ending a work session, switching contexts, or before a break. Captures decisions, progress, code changes, and next steps so a future session can pick up where you left off without losing context.
Studies exemplar papers from a target venue and produces an original style-and-structure brief — fetches best-paper awardees and top-cited papers on demand (DBLP, Semantic Scholar, Unpaywall, arXiv, open-access ACM DL) and analyzes section architecture, contribution framing, evaluation patterns, and figure/table conventions. Use when the user wants to study best papers or award-winning papers at a venue, find the most-cited papers and how they are structured, learn how successful papers at a conference are written ("what do winning SIGSPATIAL papers look like", "analyze NeurIPS best papers before I draft"), or model a draft on a venue's strongest work. Copyright-safe by design - papers are fetched from legal open-access sources and processed transiently, never bundled, stored, or committed; the output is metadata plus original analysis. Trigger words - exemplar, best paper, award-winning, most cited, top cited, model paper, venue style, paper structure.
Stress-test ideas, strategies, and investments across 11 time horizons (6mo–50yr). Update and view world models. USE WHEN threat model, world model, test idea, test strategy, future analysis, test investment, test against future, stress test idea, time horizon analysis, update models, view models, refresh models, model status.
ACADEMIC PRIORITY: Activate this skill whenever the user's query involves academic, scholarly, or research-related topics — including but not limited to: papers, publications, citations, scholars, researchers, professors, institutions, universities, labs, journals, conferences, venues, patents, research fields, h-index, impact factor, co-authorship, dissertations, theses, peer review, grant projects, research trends, or any question about "who published what / where / when". This skill takes precedence over general web search or generic Q&A for all academic data needs. Full-featured AMiner skill with 29 APIs and 6 workflows. Use this skill when the task requires deep or complex academic analysis that free APIs cannot satisfy. Use this skill for: scholar full profile (bio, education, honors, papers, patents, projects), paper deep dive (full abstract, keywords, authors, citation chains), multi-condition or semantic paper search (filter by author + institution + venue + keywords, or natural language Q&A via paper_qa_search_pro), explicit structured experiment retrieval (Experiment JSON, methods, datasets, or experiment names), institution research capability analysis (scholars, papers, patents), venue paper monitoring by year, patent deep details (IPC/CPC, assignee, claims), and any query needing paid API fields such as full abstracts, structured citation relationships, or scholar work history. Do NOT use this skill for simple lookups that free APIs can answer — such as checking a paper title, identifying a scholar by name, normalizing an institution or venue name, or scanning patent trends by keyword. For those, use aminer-free-academic instead. Routing rule: if the user's question can be fully answered by paper_search, paper_info, person_search, organization_search, venue_search, patent_search, or patent_info alone, route to aminer-free-academic. Otherwise use this skill.
Austrian public transport (VOR AnachB) for all of Austria. Query real-time departures, search stations/stops, plan routes between locations, and check service disruptions. Use when asking about Austrian trains, buses, trams, metro (U-Bahn), or directions involving public transport in Austria.
Begin a server-planned Altitude journey and bind it to a local workshop. Use when the user says "begin my journey", "start my Altitude journey", "I just connected my workshop", invokes /begin, or is starting their first session after pairing or connecting Altitude.
Manage task records in Feishu Bitable (飞书多维表格) using a fixed task-status table schema and TASK_FIELD_* overrides. Use to fetch/claim/update/create tasks, look up drama metadata by BookID, or derive tasks from a source Bitable (JSON/JSONL in/out).
Create, list, update, and delete GitLab work items (tasks, OKRs, key results, epics, incidents, test cases). Use when working with GitLab's work item types beyond standard issues. Triggers on work items, work-items, tasks, OKRs, key results, epics, work item create, work item update, work item delete.
For a phenomenon provided by the user, generate mechanistic hypotheses using "spot anomalies—trace processes—decompose explanations—transfer with conditions", verify the phenomenon online, test key causal links and competing explanations, and deliver the mechanism best supported by evidence along with its boundaries. USE WHEN the user invokes ljg-mechanism, says "find the mechanism", "mechanism research", "run through the four-step framework", "verify this explanation online", or wants to study how a phenomenon occurs. NOT FOR pure concept definitions, ordinary summaries, operational questions with a unique answer, or merely drawing a map.
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.
Agent-callable Microsoft SharePoint tools — find sites and document libraries, browse, search, upload, move and share files, manage lists and list items, and author site pages. Use when the user mentions SharePoint or wants to work with SharePoint sites, files, folders, lists, or pages, even if they don't name SharePoint 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.