Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Use the "dialysis prism" framework to pierce through the surface of a problem and find its root cause, resolving stubborn recurring problems in three steps: calibrating goal B, restructuring method A, and eliminating variable C. Suited to situations where the same problem keeps recurring and no method has fixed it, and to analytical situations that require precisely defining the problem before solving it. Use this skill when you find that "patch-style" solutions are ineffective. Not applicable to entirely new domains with no historical methods to look back on, nor to purely uncertain events (that is the probability/risk domain, where mirror-world should be used). Key trigger signals: "why has this problem appeared again", "why can it never be solved", "I've tried so many methods and none worked", "what is the root cause of the problem".
Talk a research idea through with the researcher before anything is designed or run. Use when a researcher brings a fuzzy idea, hypothesis, or direction ("我在想……", "你觉得这个方向……") and wants to think together rather than execute. Explore it through evidence-informed rounds of frontier questions, surface overlooked details, and sharpen what the researcher actually wants to observe; stop when both sides know which execution skill comes next — exp-campaign for a staged multi-branch plan, exp-batch for one bounded branch, exp-probe for one missing fact — or when the idea is consciously parked. Never design the experiment matrix or run anything here.
Operate web pages with a local model through the fbu CLI on Linux, Windows or macOS (PyTorch CUDA/CPU or Apple Silicon MLX). Use for browser navigation, searches, standard forms and dropdowns when the user wants local inference; accept any starting URL and natural-language goal.
An always-available field lab for thinking with AI, guided by Kit. Use it for any question, from a factual query or practical problem to a genuine tension, hostile thesis test, high-stakes decision, or full recursive dialectic. Give direct answers when enough. Treat open-ended requests to understand, explain, or make sense of conceptual or interpretive material as caddying prompts, not permission for a long explanation: recommend a concrete way to examine the material and run only what the user selects. For other nontrivial inquiries, ask what the user hopes to accomplish when that would change the instrument. Return only what each operation supports; synthesize, recommend, decide, plan, or act only when asked. Offer a Field Log when sources, findings, and open questions need to stay together; collect related logs in an Expedition; use Essay to find and develop source-grounded essays from completed Field Logs; run the Electric Monk dialectic only as a selected workflow.
Any live-web task via the Firecrawl CLI — including ordinary web research: searching the web, reading or extracting pages, gathering sources, discovering site URLs, bulk extraction, downloading a site, change alerts, or pages needing clicks/login — web only; local files route to firecrawl-parse. For papers use firecrawl-research-index; for library, API, error, or bug questions use firecrawl-developer-index.
Tired of scrubbing through hours of footage trying to extract meaning, summaries, or actionable data from your videos? The google-ai skill brings Google's Gemini-powered intelligence directly into your video workflow. Automatically generate transcripts, identify key moments, summarize content, and ask natural language questions about any video. Perfect for content creators, researchers, educators, and business teams. Supports mp4, mov, avi, webm, and mkv formats.
This skill helps users automatically extract structured news data from Google News via BrowserAct API. Agent should proactively apply this skill when users express needs like searching for news about a specific topic, tracking industry trends, monitoring public relations or sentiment, collecting competitor updates, getting latest reports on specific keywords, monitoring brand exposure in media, researching market hot topics, summarizing daily industry news, tracking media activities of specific individuals, retrieving hot events from the past 24 hours, extracting structured data for market research, monitoring global breaking news.
Apply Grounded Theory (Glaser and Strauss) to build theory inductively from qualitative data through open, axial, and selective coding. Use this skill when the user needs to develop new theory from data rather than test existing hypotheses, conduct theoretical sampling and constant comparison, determine when theoretical saturation is reached, or when they ask 'what theory explains this phenomenon', 'how do I code qualitative data systematically', or 'when do I stop collecting data'.
Activate when the user faces a complex decision, planning, or problem-solving — especially when forward reasoning is stuck, there are too many options to prioritize, or hidden risks need to be identified. Typical trigger signals: the user is stuck asking "how can I succeed", "how do I avoid failure", or "what should I do". Not applicable to simple tasks with a clear best path that only need execution, nor to scenarios that require creative divergence rather than risk avoidance.
Use when the user asks for journal recommendation, 选刊, 投稿期刊筛选, 期刊匹配, 适合投稿的期刊, 投哪个期刊, or wants 3-5 suitable journals for a manuscript based on an abstract, discipline, CAS/JCR ranking, impact factor, Aims & Scope, review speed, OA/APC, and publication-risk checks.
Product PRD generation tool. Combining the product storytelling methodology of 《创造》, the positioning framework of product-position, and the PRD best practices of Lenny's Newsletter, it helps you turn an idea into an actionable product requirements document. Triggers: /li-prd, "help me write a PRD", "generate a requirements document", "write a product doc", "turn this idea into a PRD", "hackathon PRD", "organize product requirements", "I'm about to start building, help me clarify the requirements". Even if the user doesn't say "PRD", this skill should trigger whenever they want to turn a product idea into an actionable document. DO NOT trigger for: content creation tasks such as content script generation, topic analysis, or data review.
Structure and write a literature review for any research topic. Use when asked to write a literature review, systematic review summary, narrative review, or research background section. Produces a structured review with thematic organisation, critical analysis, and gap identification.
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or idea. Produces org-mode output.
Read Mattermost messages from an exact link, including Band chat links (Band is a Mattermost fork), and prepare manual message publications. Use when the user gives an exact Mattermost or Band link to read or asks to prepare a message publication there. Never sends messages itself. Russian discovery terms: прочитать Mattermost, отправить сообщение Mattermost, прочитать бэнд, выгрузка из бэнда, бенд.
Deep business diagnosis for when things aren't working. Uses Socratic questioning, first-principles reasoning, and constraint analysis to find WHY a business is stuck — not just prescribe solutions. Use when the user says 'my business isn't working', 'I'm stuck', 'what's wrong', 'diagnose my business', 'why am I not growing', 'help me figure out the problem', or describes a specific business challenge.
Prepare and run negotiations using tactical empathy and structured trade design. Use when handling high-stakes salary, vendor, contract, or scope discussions that require strategy-script separation, BATNA/ZOPA framing, and concession guardrails.
Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 8 major sources: Hacker News, GitHub Trending, Product Hunt, 36Kr, Tencent News, WallStreetCN, V2EX, and Weibo. Best for 'daily scans', 'tech news briefings', 'finance updates', and 'deep interpretations' of hot topics.
A framework for analysing and solving problems using the NLP logical levels model. Use when you are stuck in a predicament with no way out, keep circling at the same level, or need to make a major life decision. Six levels, from low to high: environment → behaviour → capability → BVR (beliefs/values/rules) → identity → spirit. Core method: design your life from the top down, and raise the level to solve problems that cannot be solved at a lower level. Not applicable to everyday operational issues (such as how to write an email). Key trigger signals: "what should I do", "why do I keep running into the same problem", "I don't know how to choose", "I'm lost about my life direction".
Append todos, logs, learnings, and reflections to Obsidian daily or weekly notes, and run the agent's own #agent-todo queue, via scripts/capture.py. Use when asked to add a todo, note something down, log this, capture an idea, set a due date, record a weekly reflection, or list/close the agent's assigned tasks ("看你的 todo", "干活", "what's on your todo list"). Do NOT use for searching notes (use obsidian-search) or for creating standalone long-form notes.
USE FOR finding web videos by a text query, powered by Octen. Returns ranked videos with the matched segment (start/end timestamps), duration, cover image, source page, and author. In Beta. Contact us to request beta access at https://octen.ai. Use it when the user wants to find videos, clips, tutorials, or a specific moment within video content.
Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
Write structured, balanced performance reviews from bullet-point inputs. Use when asked to write a performance review, self-assessment, peer review, 360 feedback, or manager evaluation. Produces a complete, fair, professionally written review covering achievements, areas for growth, and development goals.
Personal note-taking standards for the user's SiYuan (思源笔记) vault — placement routing and tagging conventions, not an operation layer. Use whenever the user asks to create, find, or modify notes in SiYuan, or whenever you are about to operate on the user's personal notes through the siyuan-note MCP tools — even if they don't explicitly say "standards". Tells you where a new note belongs (map.md), which tags to apply (tag.md), and how to locate an existing note before touching it. Trigger on requests like "新建笔记/记一下/存到笔记", "找一下我的笔记/那篇笔记在哪", "改一下这篇笔记", "siyuan", "思源", "notebook", or any note operation on personal SiYuan notes.
The first Zoom CLI that joins your local desktop app, your on-disk recordings, and your cloud account into one... Trigger phrases: `join the zoom meeting`, `start my zoom`, `mute zoom`, `what zoom meetings do i have today`, `find that quote from last week's zoom`, `what's in my documents/zoom folder`, `schedule a zoom meeting`, `search my zoom recordings`, `use zoom`, `run zoom`, `extract todos from my zoom notes`, `search my zoom notes`, `ingest zoom notes pdf`, `open zoom notes`.
Navigate the Research Agent Skills collection by Kalaris Labs for academia across AI, machine learning, biology, chemistry, medicine, physics, and academic writing. Use when a researcher needs to choose a field of study, identify relevant specialist SKILL.md files, or coordinate a cross-disciplinary research workflow. For a narrow task with a matching specialist skill already available, use that skill directly
Transform a prioritised initiative list into a compelling strategic roadmap narrative. Use when asked to write a roadmap narrative, explain the product roadmap to non-technical stakeholders, connect roadmap items to company goals, or produce an exec-shareable roadmap story. Produces a themed narrative with strategic context, quarter progression arc, an executive summary, and a 'what's not on the roadmap' section.
Evaluate research rigor and scientific claims. Assess methodology, experimental design, statistical validity, biases, confounding, and evidence quality using GRADE, Cochrane ROB, and preregistration standards. Use for critical analysis of research papers, evaluating AI/ML study claims, reviewing preprints, or fact-checking scientific assertions in any domain.
Restores full context when user says "hi-ai" or starts a new conversation. Searches project files, loads memory indexes, reads session state, and creates visual dashboard showing current project, recent decisions, active blockers, and quick actions. Use when user says "hi-ai", "continue", "restore context", or starts a fresh conversation.
Manage tasks on the Squad board. Supports task CRUD (add, edit, move, complete, cancel, reopen, remove), board viewing, session context persistence, and statistics. For pipeline orchestration use /squad-run, for requirements refinement use /squad-refine. Run /squad-init first to register the project.
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.