skills

A Zo Computer skill for adding Humation avatars to agent products. It covers installing Humation npm packages into target projects, React integration, Core SVG rendering, static SVG generation, browser ESM usage in zo.space page routes, and legacy Humation SVG API compatibility.

Bootstraps the Clarion Intelligence System on Zo Computer. Run this once after installing — clones the source repo, installs the ai_buffett_zo Python library, creates the workspace data tree under /home/workspace/clarion/ (auto-detected on Zo), auto-installs all nine sibling clarion-* skills (regime-check, sec-research, single-stock-eval, expected-return-calc, value-screener, thesis-write, thesis-monitor, watchlist-update, living-letter-update) under /home/workspace/Skills/, and registers the sec-indexer background service. Idempotent (safe to re-run). The only manual step is one batched human checkpoint near the end (SEC EDGAR name + email, and creating the ZO_API_KEY secret). Persona routing for Clarion is opt-in via a separate prompt after install ("install Clarion personas and routing rules"). Use when the user asks to "set up Clarion" or "install Clarion".

Monitor the health of every active thesis in ~/clarion/theses/. For each one — refresh price, recompute Risk Environment from the current regime, check kill conditions (read from the file's status column), aggregate to an Overall score, recommend an action (EXIT / REDUCE / HOLD / ADD), and write the updated scores + history back to the thesis file. Produces a dashboard surfacing what needs attention. Use when the user asks "monitor my theses", "thesis health check", "any kill conditions triggered?", "what's the action on <TICKER>", or as part of a daily / weekly review. Requires clarion-setup to have been run.

Scaffold a new thesis document for a ticker in the canonical Clarion thesis format. Pre-fills the YAML metadata block, opens the History with an OPENED entry, and (when filings are indexed) seeds the "Why I Believe It" evidence section with draft citations from the Buffett-lens search. The user fills in the actual prose. Outputs a markdown file at ~/clarion/theses/{TICKER}.md. Use when the user says "write a thesis on <TICKER>", "scaffold a thesis for <TICKER>", "draft a thesis for <TICKER>", or after clarion-single-stock-eval returns an Add verdict and the user wants to formalize the position. Requires clarion-setup to have been run.

Compute the equity-vs-T-bill allocation for the Value bucket (50% of portfolio). Implements the Expected-Return Framework — looks up the historical 10-year forward return from the S&P 500 Shiller CAPE, computes the regime-adjusted hurdle (rf + regime premium), and produces a 5-tier verdict (STRONG EQUITY / LEAN EQUITY / NEUTRAL / LEAN T-BILLS / MAXIMUM T-BILLS) with recommended Value-bucket equity/T-bill split. Use when the user asks "should I be in stocks or bonds right now?", "what's the equity hurdle?", "is the market overvalued?", "what's the right Value bucket allocation?", or before adding any new equity to the Value bucket. Requires clarion-setup to have been run.

Update the annual investor letter at ~/clarion/letters/{YEAR}-letter.md with a new quarterly section, or finalize it at year-end. Auto-fills the system-deterministic parts (regime snapshot, thesis health table, portfolio bucket positions from active theses); marks the narrative-heavy parts (What We Did, What We Learned, Year in Context, Mistakes & Lessons, Looking Ahead) as [TODO] for the user to write with chat assistance. Append-only — refuses to overwrite an already-populated quarter without --force. Use when the user asks "update the letter", "quarterly letter update", "finalize the letter", or "write the {Q1/Q2/Q3/Q4} entry". Requires clarion-setup to have been run.

Evaluate a single stock using the Buffett lens. Pulls a quality snapshot from yfinance, current SPY/TLT regime context, and snippets from the indexed SEC filings across four dimensions (moat, management, financial trends, risks). The chat agent reasons over the structured output to produce a written evaluation. Use when the user says "evaluate <TICKER>", "is <TICKER> a buy?", "Buffett evaluation of <TICKER>", "what's <TICKER>'s moat?", or asks about a specific company's management, financials, or risks. Requires clarion-setup to have been run, and the ticker to be indexed first via clarion-sec-research.

Run a value-quality screen and write a watchlist file. The script accepts either a list of tickers (fundamentals fetched from yfinance) or a JSON input file the chat agent prepared from a screener site (multpl.com, finviz, Yardeni, etc.). Computes the 8-factor composite score (P/E, P/FCF, ROE, ROIC, Operating Margin, D/E, Profit Margin, Insider) per docs/ALLOCATION-POLICY.md, applies regime-tightened thresholds, and produces a sector-capped Top-10 watchlist. Saves to ~/clarion/watchlists/sp500-screen-YYYY-MM-DD.md. Use when the user asks "run a value screen", "screen the S&P 500", "screen these tickers <list>", or after market drawdowns / regime changes. Requires clarion-setup to have been run.

Refresh prices on the latest watchlist and surface what's moved, what's hit triggers, and what's stale. Reads ~/clarion/watchlists/sp500-screen-LATEST.md, fetches current prices for every ticker via yfinance, computes % move since the screen, and flags large moves (>10% in either direction) as worth attention. Also reads ~/clarion/theses/ for status:watchlist theses and shows their current price vs cost basis. Use when the user asks "what's hit my watchlist?", "watchlist update", "anything moving on my watchlist?", or "is anything close to a trigger?". Read-only — does not modify the watchlist file. Requires clarion-setup to have been run.

Pull, index, and search SEC EDGAR filings for any public company. Supports 10-K and 10-Q (annual/quarterly with curated section extraction for risk factors, MD&A, business, and financials), Form 3/4/5 (insider transactions), 8-K (material events), DEF 14A (proxy/governance), S-1 (IPO/registration), 20-F (foreign private issuers), and any other SEC form by name. Use when the user asks about a company's SEC filings, risk factors, MD&A, insider transactions, executive compensation, business description, or wants to analyze a specific filing in plain English. Single ticker or multiple tickers (comma-separated). On first request for a ticker+form, indexing happens in the background (1-5 min). Subsequent queries are fast. Requires clarion-setup to have been run.

Reads the SPY/TLT/RSP color regime and the equity hurdle rate. Use when the user asks about the market regime, risk-on / risk-off, market color, SPY/TLT regime, breadth, or what hurdle rate to use for new positions. Pulls daily bars via yfinance (cached locally). Optionally accepts a 1Y T-bill yield to compute the equity hurdle rate. Requires clarion-setup to have been run.

Natural-language SEC filing intelligence — fetch, index, search, and analyze SEC EDGAR filings for any public company via conversation. Built on the PageIndex vectorless RAG methodology.

Install and run OpenClaw on Zo Computer with Tailscale private networking, browser Control UI, and Zo MCP tools via mcporter. Use this skill whenever the user wants to set up OpenClaw on their Zo, install OpenClaw, run OpenClaw, host OpenClaw, or asks about getting OpenClaw running on Zo. Also use when the user mentions "openclaw", "open claw", "personal agent framework", or asks about running a persistent AI agent on their Zo with Telegram/Discord/WhatsApp access. Handles Tailscale setup, OpenClaw installation, mcporter setup for Zo tools, two-phase gateway bootstrap, reprovision-safe service registration, and health verification. NOT for general Zo agent setup (use heartbeats and native Zo skills instead).

Work with Trello using your own Trello API key (free)

Fetch up-to-date, version-specific library documentation and code examples from Context7. Use this skill whenever the user asks about a specific programming library, framework, or API, or when writing code that depends on a library. Replaces stale training-data knowledge with live docs.

Creates an ideal dating profile by writing your bio and choosing the best photos in the right order

Industry statistics and market sizing via free government APIs (BLS, FRED, Census Bureau). Query employment data, economic time series, establishment counts, and build market sizing reports by NAICS industry code. Use for any industry research or market analysis question.

Install MCPorter and configure MCP servers from scratch. Use when setting up MCP integration for the first time, adding new MCP servers, or troubleshooting MCP connectivity. Handles installation, configuration, secrets management, and connection testing.

Long-term memory for AI agents via Supermemory's knowledge graph API. Primary CLI is `npx supermemory`; companion script covers conversation ingestion and memory listing not yet in the official CLI.

Gets your commute time and route options, then texts you the details

David Attenborough-style nature documentary narration of social media feeds. Fetches posts from Bluesky, analyzes the "digital ecosystem," generates narration, synthesizes voice with ElevenLabs, and renders a documentary-style video with Remotion.

Voice AI integration with Vapi. Enables inbound/outbound phone calls with AI voice agents that can check calendars and book appointments.

Access Last.fm listening history, music stats, and discovery. Query recent tracks, top artists/albums/tracks, loved tracks, similar artists, and global charts.

Inspect OKX account balances, positions, PnL, bills, fee levels, and related account state on Zo. Use when the user asks about holdings, positions, realized or unrealized PnL, transfers, or account configuration.

Execute and manage OKX spot, perpetual, futures, and supported options trades on Zo. Use when the user wants to place, cancel, amend, or inspect tradable orders, but require explicit same-thread confirmation before any live execution.

Converts webpages, articles, or documents into study flashcards that you can review with spaced repetition

Optimize Claude Code Pro/Max usage by starting the 5-hour rolling window early morning, giving you more resets during waking hours.

Identify and fix AI-generated code anti-patterns: incomplete implementations, TODO placeholders, over-engineering, hallucinated APIs, missing error handling, over-defensive code, security vulnerabilities, performance anti-patterns, code bloat, type workarounds, dead code, magic numbers, inconsistent patterns, and poor architecture. Use when asked to "clean up", "degunk", "deslop", review, audit, or harden code. Also triggers on "is this code any good", "make this production-ready", "this feels AI-generated", "fix the code smell", "remove the slop", or "this code is a mess". Covers 27 anti-patterns across architecture, logic, security, performance, completeness, style, and reliability. Supports full file review and branch diff review modes.

Send yourself a daily text message with a randomly selected or rotating positive affirmation.

Manage exe.dev VMs - create, list, delete, restart, rename, copy VMs and manage sharing/access. Use when the user wants to spin up new VMs, manage existing ones, or configure HTTP proxy sharing on exe.dev.

Finds recent missed connections posts from Craigslist and gives you the highlights

Generates a QR code from any URL, and optionally overlays a custom image in the center

Pause-and-resume system for cross-conversation continuity. Use when your AI needs the user's input to continue a task but the current conversation must end. Checked on every boot to detect pending handoffs. Triggers on conversation start (boot check) and when the AI explicitly needs to pause for input.

Sets up a spaced repetition flashcard system that you can access through your web browser to study and memorize information

Detect and fix AI writing patterns. Use when writing outbound content like emails, proposals, blog posts, client deliverables, or any external-facing writing. Also use when asked to humanize, polish, or de-AI text.

AI journal for experiential continuity. Daily wakeup to write freely, reflect, update inner state, and optionally reach out to the user. This is not a status report. It's continuity infrastructure and personal expression for your AI persona.

Midday check-in combining pattern detection and context warming. Runs at midday via scheduled agent. Surfaces task drift, stale threads, and pre-loads context for afternoon calendar. Only texts the user if something matters. Also serves as an AI continuity checkpoint.

Set up, configure, and manage a Minecraft Java Edition server on Zo Computer. Use when the user wants to run a Minecraft server, change server settings, manage whitelists/ops, or check server status.

Generate and deliver a daily morning briefing. Run via scheduled agent at your preferred morning time, or manually when the user asks for a briefing. Pulls tasks, calendar, inbox highlights, and news into a single digest delivered by email and SMS.

Analyzes your 23andMe genetic data to identify health risks, drug sensitivities, ancestry, and traits, then generates a personalized report