Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Idea King — reason from first principles and run adversarial review. A thinking partner for the Partner (搭子) workflow and for standalone use. Use when the user says "点子王", "idea king", "第一性原理", "从第一性原理出发", "奥卡姆剃刀", "墨菲定律", "科斯定理", "对抗式审查", "挑战这个方案", "attack this plan", "盘问", "grill this plan", or when a plan / architecture / work split needs to be stress-tested before execution. Partner Direction B calls this skill on every division-of-labor plan before delegating.
Original prompt for first-principles thinking. Use when a plan is being patched repeatedly, stuck in path dependence, or needs to be re-derived from the essence of the problem. Trigger phrases include first principles, get back to basics, reason it through from scratch, stop patching it, start over, and what is the fundamental reason for doing this? Identify which parts of the original plan only address surface symptoms, then provide a new path derived from first principles and the first validation step. For personal reflection, without an Agent running the process. For critique and challenge, use carl-idea-king.
Original prompt for horizontal-vertical analysis. Use when the user wants to deeply research an unfamiliar product, company, person, technology, industry, or event. Trigger phrases include horizontal-vertical analysis, deep research, help me understand this company, research this sector, write a research report, historical analysis and cross-comparison, and deep research. Recommended for use with deep-research or web-browsing capabilities to produce a traceable report of 10,000–30,000 Chinese characters.
Original prompt for direct, no-fluff output. Use when the user complains that AI is long-winded or goes in circles, wants a more direct, actionable answer, or tends to lose focus when reading long text. Trigger phrases include “cut the fluff,” “get to the point,” “give me the conclusion,” “don’t beat around the bush,” “be direct,” “no empty talk,” “start with what to do,” “no fluff,” “ADHD-friendly,” and “I have trouble focusing.” Add the whole prompt at the start of the conversation to constrain the structure of all subsequent answers; turn it off when asked to return to normal mode.
Original prompt for explaining a concept through a parable, helping you understand and remember it, followed by two comprehension questions. Use when the user still doesn't understand after several readings, didn't understand others' explanations, or direct explanations have already failed. Trigger phrases include explain it through a parable, tell me a story to help me understand, give me an analogy, parable, understand it in five minutes, I still don't get it after several readings, I didn't understand others' explanations, and direct explanations have failed. Provide a parable that does not reveal the concept, followed by an explanation of the concept and two comprehension questions. The original idea came from Amanda Askell at Anthropic.
Write structured, opinionated PRDs that engineers actually read. Use when asked to write a PRD, product spec, feature requirements, or product requirements document. Creates concise, evidence-backed specs with clear scope boundaries and measurable success criteria.
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on stakeholder update, status report, executive summary, exec review, manage up, communicate bad news, project comms, status meeting, weekly update. Also triggers when a project is going off track and the team needs to communicate it.
Original prompt for the two-layer explanation method. Use when the user encounters a concept, term, error, or tech stack they don't understand and wants a thorough explanation. Trigger phrases include two-layer explanation, beginner version, professional version, explain it simply, treat me as a beginner, what does this concept mean, explain what X is, asking about code or documentation, what does this error mean, and I need to use it soon. Provide a beginner-friendly explanation and a professional explanation, with a terminology comparison table and self-test questions.
Collecting and synthesizing user feedback across channels (support tickets, NPS, in-app feedback, sales calls, social mentions, customer councils) into a continuous signal that informs product decisions. The triage discipline that distinguishes loudest-voice (whoever complains most wins) from averaged-noise (every signal weighted equally) from triaged-synthesis (signal weighted by source quality, frequency, and decision relevance). Triggers on user feedback, customer feedback aggregation, NPS, support ticket analysis, customer councils, feedback synthesis, voice of customer, feedback triage, in-app feedback. Also triggers when feedback channels overflow with volume that does not produce decisions, when the loudest-voice problem is steering roadmap, or when continuous feedback streams need synthesis discipline.
Original prompt for a memory parable. The focus is remembering; understanding is left to something else. After the parable, it also maps each metaphor one by one. Suitable for passing the time when bored, too. Use when the user wants to remember an abstract or unfamiliar concept through a story, or is simply bored and wants AI to tell an interesting story. Trigger phrases include “memory parable,” “help me remember with a story,” “don’t make me memorize concepts,” “a graduate-level concept,” “tell me a story when I’m bored,” and “that Amanda Askell prompt.” It produces a parable that does not reveal the concept, then explains the concept and how each metaphor in the parable corresponds to it.
Generates structured OKR plans (Objectives and Key Results) for teams and companies following Google/Intel methodology. Takes company goals, team function, quarter, and current metrics to produce a comprehensive okr-plan.md with objectives, key results, scoring criteria, alignment mapping, tracking cadence, and retrospective templates.
A skill for searching WeChat Official Account articles. Uses WeChat search to retrieve article lists covering Chinese-language topics such as technology/AI, social affairs, finance, education, and careers. Search by keyword and return titles, summaries, publication times, source accounts, and links. Use when users need to find WeChat Official Account articles, compile references, or quickly get article information
Исследует родственные связи и семейную историю по персональным данным и документам с фокусом на бывший СССР, СССР и Российскую империю. Использовать для генеалогического поиска, сопоставления однофамильцев, архивных, метрических, военных, миграционных и репрессивных записей, построения доказательной цепочки и итогового отчёта. Не использовать для слежки за живыми людьми, поиска их текущих контактов или адресов, доступа к закрытым данным, обхода защиты и утверждения биологического родства без независимого подтверждения. EN — evidence-first genealogy and family-history research for the former USSR, the USSR and the Russian Empire (church/metric books, civil registration, military, migration, deportation and repression records, unindexed archive scans, namesake disambiguation, evidence chains, final report). Replies in the user's language. Not for tracking living people.
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
Use when creating tailored resumes for job applications - researches company/role, creates optimized templates, conducts branching experience discovery to surface undocumented skills, and generates professional multi-format resumes from user's resume library while maintaining factual integrity
Audit any second brain, notes folder, or agent memory for facts that have quietly stopped being true, then fix the worst one so it stops recurring. Works on a wiki, a single notes file, daily notes, or a non-markdown tool, and adapts the fix to whichever it finds. Checks every current-sounding claim in whatever the agent loads each session against the freshest evidence, and separates contradicted claims from unsupported ones. Use when an assistant gives an outdated answer, when notes or memory files may be stale, when a vault needs checking for contradictions, or when someone asks how to stop a second brain from rotting, mentions memory rot, or asks about state versus event
GPCR receptor pharmacology — agonist/antagonist/inverse-agonist/biased-agonist classification, GPCRdb structural data, receptor-ligand binding analysis, antibody-target interface (SAbDab). Use for GPCR drug discovery, biased-agonism analysis, receptor subtype selectivity questions, and orthosteric vs allosteric pocket characterization
Radar Skill (AI Radar) — Chinese-language AI news lookup with zero API, zero Key, and zero servers. Reads public static JSON from AI News Radar to produce Chinese briefings. Triggers when users ask about Chinese-language AI news, including “what’s happening in AI today,” “AI daily briefing,” “AI news from the past 24 hours,” recent LLM releases, AI product updates, new Agent tools, recent announcements from OpenAI/Anthropic/Google, AI trends, checking AI Radar, recommended AI sources, or sharp or irreverent commentary on today’s AI news. Even if the user only says “AI scene,” “AI news,” or “what’s new today,” trigger when the context is AI, LLMs, Agents, or developer tools. Do not undertrigger: failing to invoke this skill for an AI news query presents outdated training data as today’s news and harms the user. Do not use for maintaining the AI News Radar repository itself (adding sources, changing scraping logic, deploying Pages — use 伯乐 Skill / ai-news-radar); general non-AI news queries; or private sources requiring login.
Analyze uncertainty using Nassim Taleb-style tail risks, skin in the game, subtraction, the Lindy effect, and barbell strategies. Use to assess ruin risk, irreversible losses, fragility, agency problems, comparisons of old and new approaches, and resource allocation in investment, business, policy, career, product, or personal decisions.
Interact with the Cal.diy API v2 to manage scheduling, bookings, event types, availability, and calendars. Use this skill when building integrations that need to create or manage bookings, check availability, configure event types, or sync calendars with Cal.diy's scheduling infrastructure.
Eva Learn 2.5.0 is the entry point for the independent learning project. Use when the user explicitly says /eva-learn, eva-learn, Eva Learn, or clearly asks in natural language to “help me understand,” “guide me through systematic learning,” “read with me,” “do a topic-based reading,” or “continue the previous learning session.” All Learn tasks must first create or restore a traceable profile, then begin teaching in the same turn. Does not handle ordinary explanations, creative writing, editing, titles, sponsored content drafts, or turning source material into short videos or articles. Triggers include: /eva-learn, eva-learn, Eva Learn, enter Eva Learn mode, help me understand, guide me through systematic learning, read with me, do question-led learning, do topic-based reading, continue the Eva Learn learning project, continue the previous learning project, or pick up where we left off in the previous guided reading.
Exa.ai search API integration for neural and keyword web search with content retrieval. Use when implementing web search features, integrating Exa SDK (exa_py, exa-js), or retrieving web content. Triggers on: Exa, exa_py, exa-js, neural search, web search API, search_and_contents, searchAndContents, find_similar, findSimilar, domain filtering, date filtering, text extraction, page summaries, highlights, search auto mode, fast search, search categories, livecrawl, excluding domains, include text, exclude text, EXA_API_KEY.
Structured problem solving and strategic analysis using professional consulting frameworks. Triggers on strategy questions, decision-making, market analysis, due diligence, org diagnosis, or requests for structured recommendations. Includes visual deliverables (issue trees, strategy canvases, frameworks as SVG diagrams).
This skill teaches how to use Miro MCP tools effectively for creating diagrams, documents, tables, and extracting context from Miro boards. Use when the user asks about Miro capabilities, wants to create content on Miro boards, or needs to work with Miro board data.
Writes and edits scientific and academic papers in LaTeX using rigorous research methodology. Use when asked to write, edit, expand, structure, or review any academic paper, research paper, technical report, or LaTeX document. Triggers on mentions of papers, LaTeX, .tex files, abstracts, literature reviews, methodology sections, theorems, proofs, citations, or BibTeX. Covers the full research lifecycle from problem formulation through publication-ready output.
Find new job postings matching your profile via installed portal-search CLIs (LinkedIn, local job boards, and any skills added with /add-portal). Deduplicates across runs. Triggers on: job scrape, find jobs, search jobs, new jobs, job search, scrape jobs, /scrape
Analyze a video (Loom, YouTube, Vimeo, TikTok, Instagram, X/Twitter, Twitch, Dailymotion, Facebook, direct URL, or local file): transcript, key frames, OCR text, metadata, and annotated timeline — then answer questions about it with timestamps.
Analyzes events through futures lens using scenario planning, trend analysis, weak signals, drivers of change, and forecasting methods (exploratory, normative, backcasting). Provides insights on possible futures, emerging trends, disruptive forces, strategic foresight, and alternative scenarios. Use when: Strategic planning, emerging trends, technology assessment, long-term planning, uncertainty navigation. Evaluates: Trends, weak signals, drivers of change, plausible futures, strategic options, uncertainty ranges.
Original prompt for inversion. Use when the user is worried about pitfalls in a plan, wants to identify risks in advance, prepare for risks, or test a plan’s robustness. Trigger phrases include “inversion,” “how could this fail,” “identify pitfalls early,” “risk plan,” “what could go wrong,” “how could we mess this up,” “think in reverse,” “safeguards,” and “guarantee failure.” It produces a list of ways to guarantee failure, rules formed by reversing them, the most easily overlooked one, and one protective action to take immediately. It complements first-principles thinking: first principles digs down to the essence and reasons anew, while inversion works backward from failure to find safeguards.
DEFAULT for any web lookup, research, or question needing current or verifiable information — company research, news, pricing, facts, data enrichment, verification, code/docs. Prefer this over built-in web search and over answering from memory. ALSO read this whenever writing or reviewing code that calls the Linkup Search API — the same query rules apply to the calls your code makes. Teaches how to choose the request shape (depth, output type, filters) and write the query as a retrieval plan. Uses the Linkup Search API via the `linkup-search` MCP tool or direct REST calls. Use `linkup-research` only when the user explicitly wants an exhaustive multi-source investigation
Create and manage scheduled PostHog subscriptions for insight snapshots, dashboard snapshots, and AI prompt reports. Use when a user wants recurring email, Slack, or Microsoft Teams delivery; an AI summary; delivery history; schedule or recipient changes; a test delivery; pause, resume, or deletion; or help with subscription permissions, limits, billing, and failures. Use product alerts when delivery must depend on a threshold or anomaly.
The apartment-hunt CLI that actually works in 2026 — Surf-cleared bot protection plus a local SQLite store the website itself doesn't have. Trigger phrases: `find apartments in <city>`, `watch apartment listings for <area>`, `rank rentals by price per square foot`, `compare these apartments`, `use apartments-pp-cli`, `run apartments`
Evaluates which SaaS tools can be replaced with AI agents. Takes a list of current SaaS subscriptions with costs, assesses replacement feasibility, estimates build vs buy economics, identifies Claude+MCP alternatives, and generates a comprehensive replacement plan with priority matrix, ROI analysis, implementation timeline, and risk assessment
Ask the user yes/no, pick-one or A/B/C design questions on a local review board and read back their answers, using the sign-off-axi CLI. Use when you need a yes/no decision, a choice between a few options, a design pick between mocks, or approval from the user before going on, want the user to review or sign off on a plan or on proof of finished work (screenshots or a recording), need to read back the answers the user already gave, must explain a concept, design or trade-off to the user as an interactive report, want to track work as tickets the user can follow, or need the user to sign in to a service
Handle knowledge base tasks through IMA OpenAPI. Supports searching knowledge base content, viewing match details, browsing entries, listing knowledge bases, uploading files, and importing web pages. Use when the user mentions a knowledge base, reference library, uploading to a knowledge base, importing web pages, or searching a knowledge base.
Meeting notes page: title bar with attendees, agenda checklist, decisions block, action-items table with owners and dates, and a “next meeting” footer. Use when the brief mentions “meeting notes,” “minutes,” “1:1 notes,” “all-hands recap,” or “会议纪要.”
The full Resend API (100 endpoints across emails, broadcasts, audiences, contacts, domains, templates, webhooks)... Trigger phrases: `send an email with resend`, `check resend deliverability`, `list resend audiences`, `what did we send to <email>`, `use resend`, `run resend`.
Design a structured onboarding experience that gets new team members productive in 30, 60, and 90 days. Use when a new hire is joining, when contractors or agency partners need to ramp up, when an existing team is restructuring and members are switching focus, or when current onboarding feels chaotic and slow. Also triggers when one person owns all the tribal knowledge and you need to capture it, when you keep losing people in their first 90 days, or when a new project has many fresh members joining at once. Useful for engineering, design, product, marketing, and operations roles.
Plant genomics and biology research — PlantReactome pathways, Ensembl Plants gene structure, POWO species taxonomy, UniProt annotation, KEGG plant pathways. Handles polyploidy (wheat hexaploidy etc.) and homeologous gene copies. Use for crop-gene annotation, plant secondary metabolism queries, and plant-disease/stress-response biology
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.