Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Use to assemble a product roadmap for a GitHub repository — or a multi-repo product (an org or a set of repos as one product) — derived from issues and PRs via a reasoning graph. Triggers: «собери роадмап из issues/PR», «роадмап по продукту», «что в этом репо делать дальше», roadmap from repo/github, roadmap for my org, multi-repo roadmap, quick roadmap, product-roadmap. Plays the maintainer: the verified ground of the present, a weighed backlog as шабда, directions (bianhua), graph+markdown+HTML rendering. Composes iskronify, intake and assembly. Requires the gh CLI and iskron_* tools.
Fetch the citation graph for a research paper via OpenAlex. Returns the papers it cites (references - what preceded it) and the papers that cite it (citations - what built on it). Accepts OpenAlex work ID, DOI, arXiv ID, PMID, or OpenAlex/DOI URL. No API key required. Use when the user says "what does this paper cite", "who cites this paper", "references of", "citation graph", "papers that built on", or "trace this idea backward/forward".
Connect to the Zhihe AI legal LLM platform for legal research. Use this skill when the user needs to research legal questions, look up laws and regulations, search for similar cases, or obtain legal research reports. A Zhihe AI platform membership account is required.
Agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.
This skill retrieves and displays work items assigned to the user in Azure DevOps, organized by type and sorted by recently changed. It prompts for a project name or lists available projects if not provided, then fetches work item details and displays them in a formatted table with clickable links.
Capture confidence ratings before and after a learning attempt to identify overconfidence and underconfidence patterns. Use when a student wants to understand how well they actually know something versus how well they think they know it.
Use when user requests deep analysis, thorough thinking, or detailed breakdown of a problem. Triggered by phrases like: 帮我深入思考, 请仔细分析, 帮我详细拆解, 请梳理一下思路, 仔细考虑, 深入理解, 详细分析, or similar expressions indicating need for systematic thinking. The skill applies ReAct-Plan framework: interleaving chain-of-thought reasoning with explicit global planning, dynamic prediction, and reflection to overcome myopic behaviors.
Monitors external trends across PESTLE dimensions, detects weak signals of emerging change, develops scenario-based futures, and sets adaptive signposts for early warning. Use when scanning external trends for strategic planning, detecting early indicators of change, planning scenarios for multiple futures, setting signposts and indicators for early warning, or when user mentions environmental scanning, horizon scanning, trend analysis, scenario planning, strategic foresight, or futures thinking.
Capture technical breakthroughs and transform them into actionable, reusable documentation. Use this skill when the user has achieved a significant technical insight, solved a hard problem, discovered a non-obvious solution, or wants to document a breakthrough moment. Also trigger when the user mentions "eureka", "breakthrough", "document this insight", "capture this discovery", or wants to turn a technical win into reusable knowledge.
Write the domestic and international research status and development trends analysis plus literature review for an NSFC proposal. Invoke when the user asks to write an NSFC literature review, 国内外研究现状, 文献综述, 文献评述, or section 1.2 of an NSFC proposal.
Writing assistant for the research methods, technical route, and innovative features sections of NSFC grant applications. Building on the user's existing research ideas, it provides academic phrasing, logical refinement, and standardized presentation of the research methods, technical route, and innovative features. Triggers when the user needs to write the research methods, technical route, innovation, and features of an NSFC application.
Generate standardized legal research reports, suitable for case retrieval, statute retrieval, similar-case analysis and other legal research scenarios. Use when the user needs industry or professional analysis, prediction of judgment outcomes, verification of the validity of legal bases, confirmation of the legal basis for requests and defense claims, or analysis of judicial practice trends. Supports litigation strategy assessment, trial preparation, compliance review, legal training and other legal practice scenarios.
Drill open decisions one at a time — present the most important decision not yet clarified, give the top four choices, state a preference, ask the user. Use when the user says "next decision", "one decision at a time", or a plan has several unresolved choices. Differentiator: forward-looking; the decisions skill is retrospective (choices already made). Can be invoked with /next-decision.
Pull long-form podcast transcripts as speaker-labeled markdown — cookie-first across the four major paid... Trigger phrases: `pull this podcast transcript`, `get the transcript from this URL`, `summarize this Dwarkesh episode`, `what did Senra say about`, `bundle these episodes for me`, `grep my podcast cache`, `use podcast-goat`, `run podcast-goat`.
Generate speaker notes and talking points for conversational, off-the-cuff delivery. Creates scannable prompts designed for riffing — not scripts to read. Use when asking "write speaker notes for...", "talking points for...", "what should I say on this slide...", or when preparing to present a deck live.
Group recent conversations into overall requests, review each one's progress from memory, link each to the owner goals it serves, and write the build story, so My Work shows progress meters, shipping velocity and learned working preferences. Use when asked to "group requests", "group by overall request", "review request progress", "refresh progress", "build story", "shipping velocity", or "how do I like to work with agents".
Analyzes an AI/ML publication — paper, preprint, article, technical blog post — and extracts what an enterprise AI engineer should do about it. Use when someone supplies a URL or document on RAG, embeddings, fine-tuning, prompt engineering, agents, or LLM deployment and asks "review this paper", "what do you make of this", "is this worth adopting", or "summarise the method and its limits". The subject matter must itself be machine learning.
Turn a recurring chore into a Superset automation — drafts the agent prompt, confirms schedule and target, creates it with the CLI, and reviews the first run together. Use when the user wants a scheduled or recurring agent, a daily/weekly job, or to automate a repeating task with Superset.
Helps engineering managers work effectively with Software Architects, Staff Engineers, and Principal Engineers — covers the EM's side of the relationship (responsiveness, proactive consultation, giving credit), how to advocate for architect time, pre-consultation preparation, and the two architecture team models (Centralized vs. Decentralized). Use when the user says "architect," "staff engineer," "principal engineer," "technical design review," "working with senior technical people," "getting architecture help," or "how do I get more architect time." Do NOT use for managing staff/principal engineers who report directly to you (use `managing-high-performers` or `delegation`).
Huang Shu's private advisory board — a business decision brain trust of 12 top thinkers. Uses a structured advisory board process to let different cognitive frameworks collide and yield the best decision. Trigger scenarios: the user says "开私董会", "请智囊团", "帮我决策"; the user says "私董会：[议题]" or "这个事情让大佬们聊聊"; the user uses the /私董会 or /advisory-board command; the user faces a major business decision requiring multi-perspective analysis. Non-trigger scenarios: simple operational questions (how to publish, how to lay out); purely technical questions (code debugging); everyday content creation (use article-writer / topic-partner); personal emotional support (use life-coach).
Use when calling the Atlassian Cloud REST API directly — Confluence Cloud v2 (pages, spaces, search) or Jira Cloud v3 (issues, JQL search, comments) — to perform operations programmatically, including writes such as creating a Confluence page. Calls REST with curl (no SDK, no pip), authenticating with a Cloud email + API token. Constructs any of the 800+ endpoints from a bundled OpenAPI spec via an endpoint index + a $ref-resolver, with per-API patterns (base URL, pagination, errors, rate limits) and the ADF / storage rich-text formats handled explicitly. Consumes caller-injected credentials (base_url, email, and a token resolved by variable name) — it does not provision or resolve them; the token value is read only by curl, never printed.
Routing front door for a structured, human-in-the-loop deep-research workflow (Weizhena/Deep-Research-skills) — turn a topic into an extensible outline, fan out parallel web-search agents to investigate each item into validated JSON, then render a complete markdown report. One skill, 4 reference pipelines: outline (research / add-items / add-fields), deep (parallel per-item investigation + field-coverage validation), report (TOC + per-field markdown), web-search (research agent + 5 routed source modules). Plugin: npx skills add https://github.com/akillness/jeo-skills --skill deep-research
Get web data now — fast, incremental, immediately responsive to what the user needs. The only way Claude can access live websites. USE FOR: - Fetching any URL or reading any webpage - Scraping prices, listings, reviews, jobs, stats, docs from any site - Running Extraction Templates — reusable, site-specific structured scrapers - Running Web Search Agents — open-ended research, enrichment, and dataset building with citations - Discovering URLs on a site before bulk extraction - Calling public REST/XHR API endpoints - Web search and research (8 focus modes) - Bulk crawling website sections Must be pre-installed and authenticated. Run `nimble --version` to verify (>= 1.2.0).
Prepares meeting agendas, internal pre-reads, and decision briefs using Notion context and relevant research. Use for meeting preparation, recurring meeting context, or updating meeting outcomes; use knowledge-capture for a standalone record of an existing discussion.
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.