iannuttall

Generate API reference pages from source code.

Draft a customer-facing product email.

Plan and verify a database schema migration.

Audit dependency versions and licence metadata.

Review a user interface against the design system.

Summarise a production incident from an incident timeline.

Create a Relayboard release note from changes.json. Use whenever release-note.md or a product changelog entry is requested.

Read-only inspection of __APP_DISPLAY__ — config, version, and current status. Never mutates config, credentials, or releases.

Build, launch, and verify __APP_DISPLAY__ in the menu bar after a change. Confirms the running build is the one you just built.

Ship a signed, notarized, auto-updating release of __APP_DISPLAY__. Use when cutting a new version.

Use the macOS app blueprint to shape new native menu bar apps under ~/apps/macos. Use when deciding a menu bar app's data source, whether it needs the credentials/networking/oauth/icon-render modules, its distribution path (Developer ID direct vs Mac App…

Use the local `macos` CLI to scaffold, run, sign, notarize, and release native macOS menu bar apps. Triggers on creating a new menu bar app, running/building/signing a macOS app, setting up Developer ID signing or notarization, cutting a release with Sparkle…

use when user wants to enable do not disturb, go afk, not be messaged for a while, or is going into a meeting/appointment. triggers include "afk", "dnd", "do not disturb", "don't message me", "going into a meeting", "be back in", "brb".

use when writing background scripts that need to notify you on completion or failure, or when you need to wake yourself up immediately from an external trigger. triggers include "background task", "script finished", "notify on complete", "wake me when done",…

use when you need to remember something, recall past decisions, look up what the user told you before, store preferences, save important facts, or search your memory for context. triggers include "learn", "remember", "forget", "recall", "what did i say", "did…

use when you need to set a reminder, schedule a task for later, create recurring jobs, check back on something in the future, or wake yourself up at a specific time. triggers include "remind me", "in an hour", "tomorrow", "every day", "later", "follow up",…

telegram-specific inline directives you embed in your response text to react, reply-to, or control streaming. NOT a CLI tool - these are magic strings that get parsed out of your telegram response.

Reconstruct a geometric PNG (logo, icon, monogram) as a clean native SVG with exact geometry and gradients, using an analyse -> measure -> model -> check -> residuals iteration loop scored by perceptual metrics. Use when asked to vectorise, trace or convert a…

Guide a user end-to-end through setting up Chrome Web Store API release automation in any repository. Use when asked to walk someone through OAuth/CWS credential setup, refresh token creation, local/CI secret setup, version-based publish automation, and…

Find and install agent skills with `npx playbooks find skill` and `npx playbooks add skill`. Use whenever a skill needs to be discovered or installed.

Fetch any URL as markdown with `npx playbooks get`. Use whenever you need to retrieve web content from a URL to get clean markdown for analysis or quoting.

Use when an agent needs public, source-backed information about Ian Nuttall, his projects, posts, tools, or newsletter.

Draft this week's Ian's List newsletter issue from real work signals — personal research findings, Hacker News, and GitHub — then render it and stage it as a prod draft with a test send to Ian only. Use when Ian asks to draft the weekly issue, run the…

Write a complete draft blog post for ian.is from Ian's real week of work, with the topic chosen deterministically via work signals + Ahrefs keyword/AI-search opportunity. Ian reacts to a finished draft; he never picks from menus or writes from scratch. Use…

Operate the agent-first email/newsletter CLI and MCP surfaces for broadcasts, contacts, suppressions, SES sending, tracking, and marketing analytics. Use when an agent needs to inspect or manage this email platform, prepare broadcasts, send tests or due…

Generate a Product Requirements Document (PRD) as JSON for Ralph. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.

Write conventional commit messages with type, scope, and subject when the user wants to commit changes or save work.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take…

Read-only inspection of Clockwork identity, version, tasks, and release state.

Build, launch, and verify Clockwork after a code or packaging change.

Build and verify a signed, notarized, auto-updating Clockwork release.

Operate the agent-first email/newsletter CLI and MCP surfaces for broadcasts, contacts, suppressions, SES sending, tracking, and marketing analytics. Use when an agent needs to inspect or manage this email platform, prepare broadcasts, send tests or due…

Research, test, and draft a weekly Swipe issue from overlooked AI skills, prompts, workflows, tools, experiments, and business patterns. Use when running the scheduled Swipe Radar job, finding fresh issue candidates, or preparing a review-ready Swipe draft.

Use and read this skill immediately if the user request is in any way related to SEO or a site's organic search or AI search presence. That includes site audits, rankings, keyword research, competitors, backlinks, click or traffic changes, indexing problems,…

Use the Unclaimed CLI to find, refresh, filter, and price available single-word domains through RDAP, WHOIS, and optional registrar checks. Use when someone asks whether one word is available across TLDs, wants to scan the bundled word corpus, refresh stored…

Use Librarian to fetch and search up-to-date developer documentation from GitHub and websites so answers are grounded in real docs.

Read, search, triage, draft, approve, and send project email through the local Mailroom CLI or MCP server. Use when checking Mailroom inboxes, finding conversations, marking spam, preparing replies, reviewing sponsorship enquiries, or sending an explicitly…