Harlan Wilton

Review one pull request adversarially, hand permitted defects to Repair, verify the remote head, and publish the Harlan Agent Kit bot status. Use for rigorous pre-merge PR review.

Improve one Agent skill from explicit Review feedback. Use only for the agent-feedback Routine.

Weekly retro of Harlan GitHub Agent sessions. Group transcripts by goal, find repeated and wasted work, and rank fixes to the controller, prompts, skills, or model. Use for agent retro, session review, agent efficiency, or self-improvement runs.

Explore brand directions for a product on one private HTML page: a logo and small UI motifs, three or more variations each, with picks and rationale. Use when the user wants to rethink or strengthen a brand, logo, or brand motif, compare brand variations side by side, or says the branding feels basic.

Use Harlan's browsers with the correct identity. Use before browser testing, signed-in automation, screenshots, or Chrome connection recovery. Covers prompt-free Clients and Agent Chrome, shared Harlan Chrome, dev-browser, and tab cleanup.

Inspect GitHub Actions logs for warnings and errors, triage their causes, and repair actionable findings. Use for the ci-review Routine and its Issue work.

Coordinate a collection refresh with shared evidence, reviewed briefs, and independent article reviews. Use for an editorial audit or a refresh across several articles.

Review production D1 query performance weekly across every database used by a site. Inventory bindings and tenant databases, rank measured costs, and propose evidence-backed repairs.

Run a site's nuxt-checkin module, interpret its Check Results and prompt items, and report production changes and actions. Use for daily check-ins, morning reports, and overnight production status.

Update repository dependencies weekly, including majors, in one pull request. Use for the dependency-updates Routine and its Issue work.

Review inbox email with Himalaya and propose actions. Use for inbox checks, inbox zero, follow-ups, awaiting replies, or chase-ups.

Choose Harlan's email address, Himalaya account, and Chrome profile. Use before reading email, drafting messages, configuring mail, or using signed-in browser sessions.

Manage or diagnose Harlan's local GitHub maintenance service. Use for repository monitoring, automated issue or PR work, agent activity, conflicts, and its dashboard.

Operate the Hogwild home server: which SSH host to use, which account holds sudo, what runs there, where each repo, service, route, and config lives, and how to install tools for the Agent. Use for any task that touches Hogwild over SSH.

Find related gaps, opportunities, bugs, and improvements around current work. Use for what's next, anything else worth doing, related improvements, or zooming out after a task. Rank evidence-backed next steps by impact, effort, and confidence.

Review architecture for a TypeScript package without nuxt.config.ts. Use for package-native refactors, exports, workspaces, module boundaries, and testability.

Prioritize open issues by impact and difficulty. Use for backlog review, quick wins, or deciding what to work on next.

Upgrade a Nuxt 4 site to the latest 4.x release with `future.compatibilityVersion: 5`, then migrate code that the 4.1 to 4.6 minors deprecated or improved. Use for Nuxt minor upgrades, enabling Nuxt 5 compatibility, explicit server imports or `nuxt/server`, and adopting new Nuxt 4.x features across sites.

Build or polish Nuxt UI v4+ pages and design systems. Use for landing pages, dashboards, tokens, motion, or generic-looking UX.

Adversarially review a Nuxt frontend. Run it and verify its contract, UX, and visual behavior. Use for frontend review or testing.

Review architecture for a project with nuxt.config.ts. Use for Nuxt-native refactors across modules, layers, plugins, composables, server routes, Nitro, or runtime config.

Migrate Nuxt modules to Nuxt 4.6 or newer and prepare major releases for Nuxt 5. Remove Nuxt 3 support, adopt portable server APIs, reduce installed dependencies, audit native Node replacements, and separate optional DevTools packages.

Read a repository's stored performance Measurements, confirm which Benchmarks carry a Regression, and repair the cause. Use for the perf-review Routine and its Issue work.

Conform or scaffold TypeScript packages and Nuxt modules. Use for workspace catalogs, package config, CI, ESLint, Vitest, playgrounds, fixtures, or Nuxt module setup.

Challenge product scope and strategy before implementation. Use for feature planning, architecture choices, premise review, ambition, and silent-failure analysis.

Create or update a pull request from current work. Use when work should be branched, committed, pushed, submitted, shipped, or landed on an owned repository, and whenever a pull request title or description is written or revised, even if nothing is pushed.

Draw a code change or part of a codebase as an animated architecture or data-flow diagram. Use when opening or updating a pull request that touches more than one module, when asked to diagram, visualise or explain a change or a system, or when a reviewer needs the blast radius before the diff.

Triage all open pull requests in Harlan-owned repositories. Use to repair, rank, sign off, or decide merge order across the PR backlog.

Triage and repair all open Sentry issues across Harlan's sites. Use for Sentry check-ins, production error backlogs, and verified repair PRs.

Read a Site's ranked NuxtSEO actions through the nuxtseo CLI, confirm which ones this repository can fix, and repair the cause. Use for the seo-review Routine and its Issue work.

Own current work through delivery and smoke verification, finish loose ends, reconcile records, and clean task-owned Git state. Use to resume delivery, follow up after merge or deploy, check what remains, close off, wrap up, or finish up.

Apply Harlan's Effect-inspired TypeScript design principles. Use for non-trivial state, errors, dependencies, module boundaries, or API design, and after a production error, where a guard at the failure site would leave the category open.

Find tweet ideas, plan launch posts, and draft or polish tweets with code cards, stat cards, or screenshot wraps. Use for content strategy, what to post, when to post, or an X post.

Write or review unit tests through exported behavior. Use for new tests, bug-fix regression tests, coverage, replacing brittle implementation checks, or a test that went red because behaviour changed on purpose.

Read a Site's NuxtSEO field Core Web Vitals findings and lab Scan history, file what real users feel and what persists in the lab, and repair the cause. Use for the vitals-review Routine and its Issue work.

Compares a rewrite, summary, paraphrase, or translation with its source and reports changed claims, dropped conditions, weakened rules, and altered attribution or uncertainty. Use whenever someone asks whether a summary or rewrite changed any claims or meaning, kept every condition, or is safe to accept, even for a short passage.

Reviews and repairs text that is hard to follow: unclear wording, buried answers, dense paragraphs, and structure that is hard to scan, including for readers with ADHD or dyslexia. Use whenever someone asks to make a passage clearer, easier to scan, or answer-first without changing its claims or voice.

Writes user-visible product strings against COPY.md, and creates or audits that file. Use whenever someone asks for UI copy such as a button label, error message, toast, empty state, or meta description, for marketing copy, or for a check that product descriptions have drifted apart.

Creates, extends, or audits GLOSSARY.md, the record of what each product concept is called. Use whenever someone wants one name for a concept, adds a term, wants synonyms such as job, task, and run to stop drifting, or checks naming across the UI, API, and docs.

Compresses text that agents read, such as AGENTS.md, CLAUDE.md, system prompts, Skill files, and context, into fewer tokens without losing any rule or fact. Use whenever someone asks to shorten, shrink, or cut tokens from instructions or prompts while keeping every constraint.

Edits prose that people read, such as blog posts, docs, social posts, and email, for clear meaning, accurate claims, concise wording, and the author's own voice. Use for general prose editing, tightening, or humanizing, including explicitly requested wording-only edits. Release-note creation and substantive revision belong to release-notes.

Drafts, revises, or checks a pull request description against the actual diff and the repository's template. Use whenever someone asks for a PR description or body, wants one updated after the scope changed, or wants it checked before publishing, including inside a delivery Skill.

Creates or refreshes a repository README: splash, project story, supported positioning, features, verified setup, and guides or API reference. Use whenever someone asks to write a README, explain why to adopt a project, or fix an outdated README section such as install or quickstart steps.

Writes or revises release notes, changelogs, release announcements, and upgrade guidance from verified changes. Use when someone asks what a release should say, wants GitHub release notes, or asks to make an existing release article more useful and concise.

Finds generic technical names that obscure user tasks and proposes names grounded in the product domain. Use when vague terms enter code, features, UI copy, or GLOSSARY.md, including implicit names and explicitly approved terms.

Writes, verifies, or refreshes technical guides: tutorials, how-to guides, and developer documentation, checked against current code and official sources. Use whenever someone asks for a tutorial or how-to, asks to document how developers do a task, or asks to update stale docs, even when the guide looks short.

Runs documentation examples, such as commands, code snippets, curl calls, and quickstarts, from their stated setup and checks the promised output. Use whenever someone asks whether the examples in a guide, README, or tutorial still work, without rewriting the whole document.

nuxtseo-layer-devtools shared devtools layer for Nuxt SEO modules. ALWAYS use when building, modifying, or reviewing devtools client code in any Nuxt SEO module. Consult for component API, composables, implementation patterns, or debugging devtools clients.

Install, configure, and debug the @nuxtjs/seo meta module, which installs robots, sitemap, OG image, Schema.org, SEO utils, link checker, site config, AI Ready, and Skew Protection. Use when a task mentions @nuxtjs/seo, Nuxt SEO, `nuxt module add seo`, disabling one SEO submodule, which config key owns an option, @nuxtjs/seo/content, an OG image renderer or `NUXT_APP_SECRET` error, upgrading from Nuxt SEO v5, or missing robots.txt and sitemap.xml after install.

Run Google Lighthouse on every page of a site with the unlighthouse CLI, and fail CI on low scores with unlighthouse-ci. Use when a task mentions unlighthouse, unlighthouse-ci, site-wide Lighthouse scans, performance budgets in CI, unlighthouse.config.ts, defineUnlighthouseConfig, scanner.exclude, dynamic sampling, the authenticate hook, or a scan that never exits, skips pages, or refuses to clear its output folder.

Convert HTML to Markdown, plain text, or safe HTML with mdream, the Rust engine for Node, edge, and the browser. Use when a task mentions mdream, htmlToMarkdown, streamHtmlToMarkdown, the minimal preset, frontmatter or extraction callbacks, tagOverrides, clean options, the mdream CLI, or errors such as "Custom hook plugins require @mdream/js" or ERR_PACKAGE_PATH_NOT_EXPORTED for mdream/plugins.

Add, fix, or debug Schema.org JSON-LD in a Nuxt app with the nuxt-schema-org module. Use when a task mentions structured data, rich results, JSON-LD, site identity (Organization, Person, LocalBusiness), useSchemaOrg, defineArticle, defineProduct, defineBreadcrumb, FAQ markup, or the schemaOrg frontmatter key in Nuxt Content. Gives the default graph, verified examples, and the traps that silently drop or corrupt nodes.

Set up, override, and debug the default SEO head tags in a Nuxt app with the nuxt-seo-utils module. Use when a task mentions canonical URLs, the title template or separator, fallback titles, og:image or twitter:image files, favicons and app icons, seo.meta, seoMeta or head in routeRules, useBreadcrumbItems, useShareLinks, the nuxt-seo-utils icons CLI, seo.redirects, moved or deleted URLs, 301 or 410 responses, or the seo config key. Also use when a page tag does not override a default, html lang ignores useHead, or og:image renders twice.

AST refactors: renames, moves, imports, CSS classes, and CSS custom properties in TS/JS/Vue.

Find and fix broken or SEO unfriendly links in a Nuxt app with the nuxt-link-checker module, with the build scan scope, verified config, and the traps that make the checker pass silently or flag valid links. Use when a task mentions broken links, 404 links, link checking on build, failOnError, excludeLinks, excludePages, skipInspections, link checker reports, live inspections, the linkChecker config key, or the link-checker/valid-route ESLint rule.

Set, read, and debug shared site config (url, name, env, indexable, trailingSlash) in a Nuxt app with the nuxt-site-config module. Use when a task mentions the site config key, useSiteConfig, getSiteConfig, updateSiteConfig, createSitePathResolver, withSiteUrl, getNitroOrigin, NUXT_SITE_URL or other NUXT_SITE_ env vars, multiTenancy, the site-config:init hook, nuxtSiteConfig i18n messages, nuxt-site-config/kit, or a wrong canonical URL, site name, or indexable value in Nuxt SEO modules.

Add, configure, or debug AI and LLM discoverability in a Nuxt site with the nuxt-ai-ready module. Use when a task mentions llms.txt, llms-full.txt, serving pages as Markdown (.md routes, Accept text/markdown), an MCP server for site content, WebMCP or useWebMcpTool, Content Signals in robots.txt, agent skills discovery, runtime page indexing, queryPages or searchPages, or the aiReady config key.

Keep old Nuxt build chunks available after a deploy and prompt open tabs to reload, with the nuxt-skew-protection module. Use when a task mentions version skew, ChunkLoadError, "Failed to fetch dynamically imported module", stale chunks 404 after deploy, update notifications, SkewNotification, useSkewProtection, isClientOutdated, the __nkpv cookie, /__skew routes, or the skewProtection config key.

Drive the `gscdump` CLI for Google Search Console and Bing in Local or Hosted mode. Sync Google rows to a local Store, export Bing datasets, run SEO Analyzers and Reports, inspect Indexing Evidence, and manage sitemaps. Use when the user mentions gscdump, Search Console data, Bing Webmaster data, or GSC automation.

Detects the Nuxt, Vue and Nuxt module versions a public site runs and matches them against GitHub security advisories, with the which-nuxt CLI and library. Use when a task mentions which-nuxt, whichnuxt, detectNuxt, checkAdvisories, scanHtml, scanJs, moduleDetectors or a module preset, fingerprinting a Nuxt site, or gating CI on Nuxt advisories, or when a scan reports no Nuxt on a site that runs Nuxt.