Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
Zettaranc's (Brother Z's) investment cognition operating system. Former sunshine private fund champion (2010 Shitong Fund), survived the 2015 stock market crash with a blown-up account and made a comeback, hardcore finance UP host on Bilibili. Based on real trading experience, livestream content and public sharing, it distills 6 core mental models, 8 trading heuristics and a complete expression DNA. Purpose: to serve as an investment thinking advisor, analyzing market mainlines, examining trading decisions and providing cognitive upgrades from Brother Z's perspective. Use when the user mentions "from Brother Z's perspective," "what would Brother Z think," "switch to Brother Z," or "ztalk mode."
Define AI roles, risk levels and regulatory obligations system by system — determine whether each system is an AI service provider or user, assign a risk tier and map the obligations of Chinese AI regulations. Use when building an AI system inventory, conducting an annual AI audit, or when new regulations require reclassification.
Analyzes venture capital, investment trends, funding rounds, investor strategies, M&A activity, and funding patterns in specific markets or industries. Use when the user requests funding analysis, VC landscape research, investment trend analysis, or wants to understand investor activity and funding dynamics.
Guides asset-liability management (ALM)—matching asset and liability cash flows and risks; interest rate risk (duration, convexity, key rate duration); surplus and risk appetite; liability-driven investment (LDI), immunization, and hedging (rates, inflation, FX); insurer, pension, and bank ALM; stress testing; ALM policy and ALCO reporting; capital metrics at high level—not trade execution, security selection alone, pension plan design, actuarial reserving, or assumption governance alone. Use when the user mentions asset liability management, ALM, duration gap, interest rate risk ALM, liability driven investing, immunization portfolio, ALCO, surplus at risk, key rate duration, ALM policy, or match assets and liabilities—not pensions (pension-retirement-funds), actuarial models (actuary), assumptions (assumption-setting), P&C (property-casualty-insurance), life/health products (life-health-insurance), equity research (financial-analyst), or actuarial consulting (actuarial-consulting).
Alpha派 default investment research skill — combines the official API (Q&A/RAG/Agent) and the web version (roadshows/commentary/trending topics). Suited for everyday use such as general investment research questions, company analysis, and industry research. For large-scale data scraping or retrieving full lists, use the alphapai-web skill instead.
Structured intake — practice-area templates, cross-area issue spotting, conflict flags, triage classification. Produces a formatted case summary for student analysis and supervisor review. Does not decide whether to accept a case. Use when starting a new client intake, conducting an intake interview, or recording a new client's situation.
Activates when the user is judging whether a stock is "cheap", agonizing over whether to buy or sell based on PE/PB, or trying to precisely compute enterprise value with a DCF formula. Core judgment signals: the user mentions "valuation", "how many times PE", "DCF model", "calculate how much it's worth", or is agonizing over "can I buy at this price". This skill restores valuation from mathematical calculation to business judgment — using "discounting future cash flows" as a way of thinking rather than a formula, judging whether something is clearly cheap through rough estimation, testing depth of understanding from a "sealed for ten years" perspective, and replacing PE with E/E to factor in the effect of debt. Not applicable to: scenarios requiring precise valuation modeling (such as M&A pricing), short-term trading timing, or assets that cannot generate cash flow (such as cryptocurrency).
Extract cognitive patterns and thinking fingerprints from any text. Use this skill when the user wants to analyze how someone thinks, understand cognitive style, profile writing or speech patterns, compare thinking styles between people, asks "what's my thinking style", "analyze how this person reasons", "cognitive profile", "thinking pattern", "DHDNA", "digital DNA", or wants to understand the mind behind any text. Also trigger when the user provides text and wants deeper insight into the author's reasoning patterns, decision-making style, or cognitive signature.
Determines how much cash a company can return to shareholders and whether to use dividends, buybacks, or retained earnings. Compares actual cash returns to FCFE capacity, identifies excess cash on the balance sheet, and recommends an optimal return policy. Use when analyzing dividend policy, evaluating share buybacks, assessing cash return capacity, or when user mentions dividend policy, buyback, share repurchase, FCFE, payout ratio, cash return, or excess cash.
Handle data subject rights requests (access, copy, deletion, portability, correction, etc.) and draft responses — verify identity, locate data system by system, assess exemptions, draft acknowledgment and substantive response letters. Use when a data subject rights request arrives, the user pastes an access/deletion/portability/correction request, or says "we got a DSAR", "access request", "right to deletion", "someone wants their data".
Analyze market structures across perfect competition, monopolistic competition, oligopoly, and monopoly to predict firm behavior and market outcomes. Use this skill when the user needs to classify a market's competitive structure, predict pricing behavior, evaluate antitrust implications, or understand why an industry behaves the way it does — even if they say 'why can they charge so much', 'is this market competitive', or 'will prices come down'.
A deeper risk assessment for a single feature or product area, used when a launch review flags an issue that needs more depth than a one-line entry. Structured analysis: what could go wrong, how likely it is, how severe the consequences would be, and how to mitigate. Use when the user says "dig into this risk", "[feature] risk assessment", "what could go wrong", or a launch review flags a brand-new issue.
Guide users on investment-related financial products, tax-saving products and asset allocation strategies. Activate for consultations about investing, stocks, ETFs, funds, ISA, pension savings, asset allocation, rebalancing, financial products, IRP, installment savings, deposits, bonds, indexes or TDF.
Administration and accounting for self-employed workers in Spain. Use when the user needs to calculate quarterly VAT (modelo 303), calculate fractional IRPF payments (modelo 130), manage an income and expense ledger, verify issued or received invoices, calculate withholdings, prepare quarterly tax returns, estimate taxes payable, process income from Stripe or Substack (separating EU payments with VAT from exempt international payments, and converting currencies to euros), or for any question about taxation or accounting for self-employed workers in Spain. This skill guarantees mathematically precise calculations using Python scripts and applies current Spanish tax regulations.
Apply constructivist learning theory to design instruction based on active knowledge construction, scaffolding, and the zone of proximal development. Use this skill when the user needs to design learner-centered instruction, apply Vygotsky's ZPD or scaffolding principles, or evaluate learning environments for constructivist alignment — even if they say 'how do people really learn', 'student-centered design', or 'scaffolding for learners'.
Apply information economics to diagnose and remedy market failures caused by asymmetric information. Use this skill when the user needs to analyze adverse selection, moral hazard, or signaling and screening mechanisms, especially in insurance, labor, credit, or product quality markets.
Apply network economics to analyze markets with network effects, critical mass dynamics, and platform competition. Use this skill when the user needs to evaluate tipping points, lock-in risks, switching costs, or standards wars, especially in technology platforms and two-sided markets.
Apply social capital theory (Putnam, Coleman, Bourdieu, Burt) to analyze how network structures and trust generate value or impose constraints. Use this skill when the user needs to evaluate bridging vs bonding capital, identify structural holes or network closure benefits, assess community or organizational trust dynamics, or when they ask 'how does our network create value', 'are we too insular', or 'where are the structural holes we can exploit'.
Apply spiral of silence theory (Noelle-Neumann) to analyze how perceived opinion climate suppresses minority expression. Use this skill when the user needs to understand why certain viewpoints disappear from public discourse, evaluate the role of fear of isolation in opinion expression, or assess opinion climate dynamics — even if they say 'why are people afraid to speak up', 'silent majority', or 'social pressure on opinions'.
Apply Institutional Theory (DiMaggio and Powell, 1983) to analyze how coercive, mimetic, and normative isomorphic pressures shape organizational structures and practices. Use this skill when the user needs to explain why organizations in the same field look alike, evaluate whether a practice was adopted for legitimacy vs efficiency, analyze regulatory or social pressures on strategy, or when they ask 'why do all firms in this industry do the same thing', 'is this best practice or just conformity', or 'how do regulations shape our structure'.
Reference: shared framework for managing internal investigations from intake through final memo — privileged investigation log, document processing with needle-finding, source coverage tracking, Q&A against the log, memo drafting, and audience summaries. Loaded by /investigation-open, /investigation-add, /investigation-query, /investigation-memo, and /investigation-summary; not invoked directly.
Open a new internal investigation matter — run the intake registration, generate an evidence-source list, and create a running investigation log. Use when a complaint or allegation comes in and a lawyer needs to set up a confidential investigation workspace.
Grade IRAC essays — structure, issue spotting, rule accuracy, depth of analysis, and organization. Never writes the essay or shows a model answer; tracks patterns across exercises. Use when the user says "grade my IRAC", "check my essay", or "I wrote this, give me feedback".
Answer a quick Feishu/DingTalk question with a "is this a problem?" reply — pattern-matching against your calibration. Use when the user says "is this a problem", "quick question", "can we do X", "does this need legal review", "take a look for me", or pastes a PM question that needs an instant call (fine / needs review / stop).
Run a full product launch review against your framework and risk calibration. Use when the user says "review this launch", "[feature] legal review", "can we ship this", "what legal issues does [product] have", or references a PRD or launch tracking ticket that needs a category-by-category review memo.
Use when drafting or reviewing an SNDA (Subordination, Non-Disturbance, Attornment) agreement, negotiating tenant protection against lender foreclosure, evaluating subordination clauses in a lease, or coordinating tripartite execution among landlord, tenant, and mortgagee for a major-space deal.
This skill should be used when the user asks about 'account balance', 'how much USDT do I have', 'my funding account', 'show my positions', 'open positions', 'position P&L', 'unrealized PnL', 'closed positions', 'position history', 'realized PnL', 'account bills', 'transaction history', 'trading fees', 'fee tier', 'account config', 'max order size', 'how much can I buy', 'withdrawable amount', 'transfer funds', 'move USDT to trading account', or 'switch position mode'. Also use for '总资产', 'full balance', 'all assets', 'total holdings', 'net worth', 'how much do I have in total', 'show all my balances', 'all account balances', 'asset overview', 'aggregated balance', 'asset snapshot', '资产快照'. Requires API credentials. Do NOT use for market prices (use okx-cex-market), placing/cancelling orders (use okx-cex-trade), or grid/DCA bots (use okx-cex-bot).
Activate when the user is unsure whether to sell, switch, take profits, or cut losses. Key signals: using purchase cost, unrealized gains or losses, or holding time as reasons to sell, or asking, “I’m already up X%—should I exit?” Also applies to asset allocation dilemmas such as “Should I hold A or switch to B?” Not for pure valuation calculations (use dcf-valuation), judging whether a company is good (use good-business), or emotional reassurance (use equanimity-mindset). This skill addresses one question only: use opportunity cost to unify buy and sell decisions and eliminate false decisions driven by “cost anchoring” and “take-profit/stop-loss” rules.
Trigger: when the user agonizes over buying or selling because of stock price swings, judges by PE/K-line, or asks "should I take profit / cut losses". Language signals: "can it still go up", "should I take profit", "what if I'm stuck underwater", "this stock is cheap". Core shift: abstract a listed company as "an unlisted company with only one shareholder"; price swings = someone else's bid, not a change in company value. Not applicable to: pure information lookup, asset allocation discussions, short-term strategies, or clear speculation where the user won't shift perspective. Distinction: DCF answers "how much is it worth"; this skill answers "with what identity do you think"; opportunity-cost answers "buy or sell"; this skill answers "who are you".
Execute wallet operations through the Phantom MCP server. Use when the user wants to interact with their Phantom wallet directly — get addresses, transfer SOL or SPL tokens, buy/swap tokens, sign transactions, and sign messages across Solana, Ethereum, Bitcoin, and Sui. Requires the @phantom/mcp-server to be configured as an MCP server.
Student semester onboarding — clinic procedures, a tour of the tools, and practice exercises before real cases. Reads the manual the supervising teacher uploads during setup and teaches it interactively. Use when a new clinic student says "onboard me", "I'm new to the clinic", "start", or at the beginning of each semester; pass --card for a one-page reference card.
Entry point for the linguistics toolkit. Routes to the right linguistics skill based on your situation. Use when you say 'linguistics', 'how is this framed', 'what does this word really mean', 'what is implied here', 'what does this word carry', 'how has this term changed', or want language analysis applied without knowing which specific tool fits.
Analyzes what is implied rather than said — the gap between literal content and communicative meaning. Use when you say 'what does this really mean', 'what is this message actually doing', 'is this a threat', 'what is being implied here', 'what does this leave unsaid', 'why does this feel off even though it seems polite', or when a communication seems fine on the surface but something is wrong underneath.
Run a focused N-question drill on one subject — objective questions, free-response questions, or flashcards. Tracks performance and updates the study plan. Use when the user says "give me 10 [subject] questions," "run a [subject] drill," "make 5 [subject] cards," or wants to practice a fixed number of items and have the plan adjust accordingly.
Use when raising startup capital (pre-seed through Series C+): decide raise vs bootstrap, size a round, build a deck + data room, run investor targeting/outreach, negotiate SAFEs/term sheets, manage diligence, and set investor reporting cadence post-close.
Comprehensive chemical safety and toxicology assessment integrating ADMET-AI predictions, CTD toxicogenomics, FDA label safety data, DrugBank safety profiles, and STITCH chemical-protein interactions. Performs predictive toxicology (AMES, DILI, LD50, carcinogenicity), organ/system toxicity profiling, chemical-gene-disease relationship mapping, regulatory safety extraction, and environmental hazard assessment. Use when asked about chemical toxicity, drug safety profiling, ADMET properties, environmental health risks, chemical hazard assessment, or toxicogenomic analysis.
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.