Product Design Lab

Cross-platform executive operations skill for the IronClaw agent. The agent operates as chief of staff to a C-suite executive, coordinating across email, calendar, code, projects, and outbound partner messaging via Google Workspace, GitHub, GitLab, ClickUp, and WhatsApp. Designed for one-click deploy demos to enterprise partners (financial services, banking groups, software firms) with proper OAuth and System User credentials provisioned at deploy time. Pairs prose guidance for the LLM with deterministic Python scripts in `python_scripts/` for the canonical recurring workflows.

Captures any commitment the user makes across email, meetings, or chat. Records verbatim text, source, addressee, due date, and status into a Notion registry. Single record per invocation. The user marks done; the agent never auto-closes.

Walks the user's commitment registry and produces a digest covering what's due today, due this week, slipping (past due, status open), or stale (no status change in 30+ days). The user reviews and marks done; the agent never auto-closes.

Watches specific web pages and reports the day anything changes — pricing, job postings, product updates. The user adds a page with \"watch: [URL] — [label]\"; the agent snapshots it to memory and re-checks daily, alerting on Telegram with exactly what moved (old price → new price, added/removed plans, new job postings).

Logs the user's decisions in memory and confronts them with the outcome later, so they actually learn from their own track record instead of remembering only their wins. The user logs a decision with \"decision: [what you decided] | check in [timeframe]\"; the agent stores it and, on the follow-up date, sends the exact decision back on Telegram and asks for a verdict. Verdicts build a running track record (right / wrong / mixed) and surface patterns over time.

Microsoft 365 business workflow patterns for the IronClaw agent. Covers Outlook email, Excel data operations, Teams channel communication, Word and PowerPoint document generation, and SharePoint and OneDrive file management via Microsoft Graph.

Watches task notes that have a reminder set and holds the user accountable. At the reminder time it pings; if the task is not reported done it escalates on a cadence, logs the miss to a Bad Habits note, and ramps its tone until the user completes or reports. Intensity is configurable. Pairs with obsidian-task-ledger.

Captures a stray idea into the vault and links it to the right domain, entities, and tasks by recognizing what the user mentioned. The idea lands attached to where it belongs instead of getting lost in a daily note. Pairs with obsidian-task-ledger.

Captures brain-dumped tasks into a structured Obsidian vault as task notes whose frontmatter properties link them to domains, clients, and projects. Maintains a centralized, always-current task ledger. The agent infers the domain and entities from how the user speaks and asks rather than guesses.

Triage open GitHub pull requests across one or more repositories and produce a prioritized, bucketed review digest. Scores each PR on CI status, mergeability, staleness, size, and review state, then groups them into Blockers, Quick wins, First contributors, Aging, and Normal so the reviewer knows what to look at first instead of paging through the GitHub UI. Read-only — never comments, labels, closes, or merges.

Generates polished, on-brand HTML presentations from a content brief and hosts them in a shared Google Drive folder where reviewers open them directly in the browser. No PowerPoint, no Google Slides, no design tools required. The agent handles generation, branding, hosting, and reviewer distribution end-to-end so the author only needs to know what they want to say.

Stores messages and yearly self-interviews in memory and delivers them back to the user on Telegram on a future date they choose — months or years later — so their past self speaks to their future self, unedited. The user seals a letter with \"capsule: [message] | deliver in [timeframe]\" or runs a yearly self-interview with \"interview me\". Sealed content is never shown before its delivery date; on that date the agent sends it back verbatim.

Read and write a self-hosted WordPress + WooCommerce site over REST for Ironclaw. Manage posts, pages, media and comments (WordPress core) and products, orders and customers (WooCommerce), plus a raw wp_request passthrough to any /wp-json/* route. The host injects credentials (Application Password via Basic for WordPress, consumer key/secret via query params for WooCommerce) — the tool and LLM never see the raw secrets.

Watches Bitcoin dominance (BTC's share of total crypto market cap) and alerts the user on Telegram only when it crosses a key threshold: below 60% reads as a possible altcoin-season signal, above 65% as BTC dominance expanding. Between 60% and 65% it stays silent. Each check is logged to memory as an audit trail, and it only alerts on an actual threshold crossing, never on every run.

Watches NEAR's price across Binance, Bybit, and Coinbase and alerts the user on Telegram when the prices drift apart by ~1.5% or more — an early sign of an arbitrage gap or of trouble (paused withdrawals, broken liquidity) on one exchange. Runs every 2 hours, logs each snapshot to build a spread history, and stays silent while the exchanges agree.

Tests a market theory the user defines, automatically, over time. The user states a hypothesis like \"when ETH rises more than 3% in 24h, NEAR rises within the next 48h\"; the agent checks prices every 6 hours, logs each trigger event, and 48h later checks whether the predicted outcome held — building a confirmed/refuted tally and a hit rate. Every Sunday it sends a Telegram report with the running results and a verdict (promising / inconclusive / rejected), so a hunch becomes evidence instead of a feeling.

Checks four independent crypto macro indicators once a day — Fear & Greed Index, BTC dominance, BTC funding rate, ETH funding rate — and alerts the user on Telegram only when 3 or more point the same direction (bullish or bearish), filtering out single-indicator noise. Interprets what the aligned combination historically means and suggests a directional action. Stays silent on every other day.

Logs the trades the user tells it about and gives live P&L on demand. The user says something like \"bought 500 NEAR at $3.20\" or \"sold 200 SOL at $145\"; the agent appends it to a persistent journal in memory. On \"show P&L\" it reconstructs each open position, works out the size-weighted average entry, fetches current prices from CoinGecko, and shows cost basis, current value, and profit/loss per token and overall. The journal survives restarts.