Catalog
Skills
97 internal capabilities, grouped by the question someone arrives with. Employees use the job name and ask in normal language; implementation identifiers stay out of the workflow.62 need nothing but ./install.sh to run at all. Separately — not a competing setup category, a skill can be both — 51 also link your team's live wiki playbook into their report once one is configured.
You rarely need this page to run one — in opencode or Claude Code, describe the job and the right skill is picked from its trigger phrases. This is for browsing what exists.
2 skill(s) have no job group: Contextual copy review, Visual layout audit
97 skills
Is this page any good?One URL, one verdict.
Accessibility (a11y)Accessibility scan for a live page — runs axe-core (Deque) across device presets and scores the page against WCAG, returning an absolute PASS / REVIEW / FAIL verdict plus a self-contained HTML report grouped by impact.wiki-enhancedbrowser+ runtimeCapture secret scrubCapture secret scrub — scan a local site archive or a page's delivered HTML for credentials and SSN-shaped identifiers before the capture is shared, retained, or used for a migration.Critical-path smoke testCritical-path smoke test across every domain at once.wiki-enhancedEmbed health checkThird-party embed health check — renders the page and asks one question per embed: did it actually paint anything? An Instagram feed, review widget, booking iframe or chat bubble that renders an empty container is invisible in the delivered HTML and visible only to the client.wiki-enhancedbrowserForm submittabilityDrives a rendered page to prove its primary form can be submitted.wiki-enhancedbrowserGallery & before/after auditGallery and before/after auditor — renders a gallery page and grades what is actually wrong with it: images that do not load, distorted or excessively cropped gallery cards, before/after cases with a missing partner, gallery images with no alt text, and originals served far larger than they display.wiki-enhancedbrowserwrites (dry-run first)Injected-content scanInjected-content scan — finds content on a site that should not be there.wiki-enhancedLayout / front-end QAFront-end / layout QA for a live page — measures the rendered DOM across device presets and flags objective layout defects: horizontal overflow, tap targets too small, text below the legible floor, skipped heading levels, DOM bloat, interactive elements whose contrast passes at rest but fails on hover or focus, a mobile nav toggle that reveals nothing, and viewport meta defects (missing or blocking zoom).wiki-enhancedbrowserMotion & animation auditMotion and animation audit for a live page — reads the page's authored CSS inside a real rendered browser and returns PASS / REVIEW / FAIL plus a self-contained HTML report.wiki-enhancedbrowserOWASP ZAP DAST evidenceOWASP ZAP DAST report ingestion for a deployed web candidate — reads an existing ZAP traditional JSON report, verifies that every scanned site and instance belongs to the declared candidate origin, binds the evidence to the candidate digest, normalizes risk/CWE/affected-path findings, and writes deterministic JSON plus a self-contained HTML handover report.Page audit (all-in-one)Page QA orchestrator — run every QA tool on one URL and get one standardized report.wiki-enhancedbrowserPageSpeed fix pipelinePageSpeed fix pipeline for WordPress — the write-lane counterpart to Performance (Core Web Vitals).wiki-enhancedbrowserwrites (dry-run first)Performance (Core Web Vitals)Core Web Vitals and performance scan for a live page.wiki-enhancedbrowser+ runtimeScreenshotsCapture multi-device screenshots of any URL from the command line — one PNG per device preset (iPhone → Desktop 4K), headless, on a Playwright core.wiki-enhancedbrowserTestimonials & reviews checkerTestimonials and reviews checker — renders a page and verifies the reviews section actually shows real, current, structured testimonials.wiki-enhancedbrowser
Will search engines find and rank it?Crawl, index, understand.
Chrome UX Report field seriesOptional integration — reads the Chrome UX Report (CrUX) field data for an origin and writes the series the migration gate's "faster without WordPress" claim is judged on.Crawl-finding dispositionCrawl-finding disposition — a crawl tells you what is true; this decides what is worth doing.wiki-enhancedGA4 behaviour seriesOptional integration — reads the GA4 Data API and writes the behaviour series, the sibling to Search Console series.GA4 full API — read / write / deleteStandalone full Google Analytics 4 API — read, write and delete.GBP public listing auditAudit the public surface of every Google Business Profile listing without an API — what Search and Maps actually show: practitioner, acquired-brand and competitor baselines.Google AI Overview readinessGoogle AI Overview readiness — reviews a local Markdown or MDX article for the editorial signals that make a useful answer easier to extract and trust: attributable evidence, self-contained reader-task sections, clear entity definitions, decision tables or lists, and relevant visuals with meaningful alt text.Google Business Profile clientOptional integration — pulls a GBP location's profile, reviews, daily performance metrics and monthly search keywords via the Business Profile and Performance APIs, then grades them to PASS / REVIEW / FAIL.Google Reviews replacementProduction-grade owned Google Reviews replacement — fetches from approved Google sources (Places Details or Business Profile), renders real rating/review count/text/attribution with freshness and failure states, never fabricates.GSC decline decompositionGSC traffic-drop triage with mechanism attribution — decompose a click decline into worse ranking, weaker demand, falling click-through, a mix of the three, the page dropping out of results, or a decline that turns out to be growth, with an ordered rule set, grain-coverage gate, URL-migration clustering, stable-position cohort CTR test, equal-window + YoY cross-check and hedged verdict.GTM audit and fixUnified Google Tag Manager audit-and-fix workflow.wiki-enhanced+ runtimeHeading structureHeading-structure optimizer — reads a page's H1-H6 outline in document order, grades no H1, multiple H1s, skipped levels, empty headings and duplicate text, then proposes a corrected H1-H4 outline.Internal link graphInternal link-graph audit — given a site's URL universe, fetches each page, extracts the internal links, and builds a directed graph of how the site links to itself, then grades the signals rankings depend on: ORPHAN pages linked from nowhere, pages unreachable from the home page, pages buried too many clicks deep, thin single-inlink pages, generic anchor text, and exact-match over-optimization.wiki-enhancedKeyword research & planningKeyword research & planning on the SEMrush Analytics API.wiki-enhancedneeds a keyLink & image checkerOn-page link & image checker — extracts every link and image a page declares, fetches each to its status code, and reports the dead ones (4xx/5xx broken links and broken images) plus the link-quality issues search engines and screen readers care about: non-descriptive anchor text, image-only links with no accessible text, malformed links, insecure external links, new-tab links missing rel=noopener, and excessive link counts.wiki-enhanced+ runtimellms.txt checker + builderllms.txt checker and builder — the AI-crawler precondition nothing else in the toolkit reads or writes.Local SEO (NAP)Local SEO / NAP audit — reads a page's delivered HTML and checks the local-search signals a business page lives or dies by: LocalBusiness structured data with a complete Name-Address-Phone, a phone and street address on the page, NAP consistency between the schema and the visible page (a mismatched phone fails the page), and Google Business Profile readiness — opening hours, geo coordinates, an embedded map.wiki-enhancedbrowserMigration data intelligenceNormalize and analyze mixed raw website exports—GSC, GA4, SEMrush, crawl, PageSpeed/CrUX, backlink, and generic CSV/TSV/JSON/XLSX files—into a quality-audited page evidence table, prioritized SEO opportunities, and implementation-ready inputs for a static rebuild.Nav and IA auditNav/IA audit + thin-page detection — reads a site's primary navigation (nav, role=navigation, .main-nav and nested ul depth), grades deep nav (>3 levels), orphaned or empty/fragment hrefs, duplicate labels to different URLs, broken mobile toggle (when a toggle exists), and thin pages by word count (<150 REVIEW, <50 FAIL, seeded from Old vs new page parity's floor).On-page SEOOn-page SEO scan — reads a page's delivered HTML and checks the head, meta and heading signals search engines use: title presence and length, meta description, rel=canonical, meta robots (noindex), Open Graph tags, viewport, html lang, and exactly one H1, plus a structured-data summary.wiki-enhanced+ runtimeRedirect checkRedirect-chain validator — follows where each URL actually sends a browser, hop by hop, and reports the loops, over-long chains, temporary (302/307) redirects where a permanent one belongs, meta-refresh and JS redirects, https-to-http downgrades, and dead ends.wiki-enhancedRedirect mapperBuild and clean a migration redirect map from historical URL inventories, CMS redirect exports, and the new site's route inventory.Search Console seriesOptional integration — reads Search Console's Search Analytics API and writes the data series nothing else has.SEMrush researchOptional integration — SEO-research client for the SEMrush Analytics API.wiki-enhancedneeds a keySEO drift baseline + compareSEO drift — git for SEO — snapshots a site's SEO-significant fields (title, description, canonical, robots meta, H1, html lang, JSON-LD types, internal-link count, word count from On-page SEO/Structured data (schema)/Link & image checker) into a stamped baseline and diffs a current run against it, severity-coded.Site audit (all-in-one)Site-level audit orchestrator — point it at a domain and it audits the whole site in one run.wiki-enhancedbrowserSite crawl (Screaming Frog)Full-site crawl audit powered by Screaming Frog — the heavyweight, whole-site counterpart to the per-page SEO skills.wiki-enhancedSitemap & robotsRead-only sitemap & robots map — fetches a site's robots.txt and every sitemap it declares (or probes the common locations), follows sitemap indexes down to their children, collects every URL, and reports what is declared, what robots.txt blocks, and what is oversized, cross-host or insecure, plus a crawl-over-crawl diff.wiki-enhancedStructured data (schema)Structured-data audit — checks a page's JSON-LD against a per-type rubric: valid JSON, a schema.org context, and the required and recommended properties that gate rich results for Organization, WebSite, Article, Product, LocalBusiness, BreadcrumbList, FAQPage, Event, Recipe and more.wiki-enhanced+ runtimeSuperAuditOptional integration — sends a URL to a remote SuperAudit engine (a hosted SEO/content audit service with hundreds of checks) and renders its category and check results as a PASS / REVIEW / FAIL report, with the engine's own findings and recommendations as the built-in fixes.wiki-enhancedneeds a key
Is the writing doing its job?Read it, then fix it.
Alt-text writerAlt-text generator — finds the content images on a page that are missing alt text, writes concise descriptive alt for each with a vision model, and on WordPress publishes it to the media library.wiki-enhancedbrowserLLMwrites (dry-run first)Brand voice profile & auditCreates, retrieves and audits against a reusable client brand-voice profile.wiki-enhancedBrand voice rewriteRewrites one page or local HTML document to an approved toolkit.brand-voice/v1 profile while preserving facts, numbers, names, links, calls to action and section order.wiki-enhancedLLMContent briefContent brief generator — turns a keyword into a brief a writer can execute without further research: search intent and audience, a recommended title / meta description / H1, an H2–H3 outline, entities and questions to cover, internal-link anchors, and a word-count target.wiki-enhancedLLMwrites (dry-run first)Content freshnessContent-freshness audit — works out how old a page's content is from every freshness signal it can see: schema datePublished/dateModified, time elements, the Last-Modified header, and visible "last updated" dates.wiki-enhancedContent qualityContent-quality audit — reads a page's visible text and grades whether the copy itself is any good: readability (Flesch–Kincaid grade and reading ease), thin content by word count, H1/title duplication, and leftover placeholder or lorem-ipsum text.wiki-enhancedDraft quality gateDraft quality gate — reviews a local Markdown or MDX article before publication, producing a transparent 100-point editorial score and an independent block for material numeric or time-sensitive claims without a nearby attributable source.Image optimizerOptimize images for the web locally, before upload — replaces Imagify / ShortPixel / EWWW / Smush and the performance reason for a CDN offload.wiki-enhancedMeta title & description writerMeta title & description writer — rewrites a page's SERP snippet (the title tag and meta description) to be CTR-optimized and character-perfect, and can publish it to WordPress.wiki-enhancedbrowserLLMwrites (dry-run first)Promo expiry scannerPromotional expiry scanner — finds date-bearing promo copy on a page and grades what is past its date: "Holiday Specials" still up in August, "Offer ends 12/31/2025" in 2026.wiki-enhancedProvider roster checkProvider roster check — compares the people a site publishes against the roster of who should be there.wiki-enhancedReadability rewriterReadability rewrite — takes web copy that reads too hard and rewrites it to a target reading grade while keeping the meaning.wiki-enhancedLLMSite-wide content searchSite-wide content scout — searches every page of a site (or one page) for literal phrases or labelled regex rules and reports every occurrence with its surrounding sentence, so a copy change can be scoped before anything is edited.wiki-enhancedbrowserSpelling checkSite-wide spelling sweep — fetches a page (or every URL in a list), extracts the visible text, and flags suspected misspellings with a hunspell dictionary (nspell + dictionary-en).wiki-enhanced
What do I hand the client?The deliverable.
AI search visibilityAI Search Visibility report — measures how visible a business is inside AI search answers (ChatGPT, Gemini and other engines) and builds a client-ready report.wiki-enhancedneeds a keyBefore/after checkBefore/after verification for a change to a live page — the safety net for the small edit that doesn't justify a staging round-trip.wiki-enhancedbrowserClient report (PDF)Rolls up a site's tool runs into one branded, client-ready report plus PDF.wiki-enhancedbrowserContent inventoryContent inventory at scale — the classic content-audit spreadsheet, generated.wiki-enhancedInfographic & hero image generatorInfographic and hero-image generator — turns a data brief or CSV into a branded visual: hero image, stat-card, bar/donut timeline or comparison.browserReport builderReport builder — turns a data spec or CSV into a report on three surfaces: an interactive HTML report (sortable columns, live filter, show/hide columns, CSV export, pagination, sticky header), a print-ready PDF with repeating table headers and page breaks, and a Gmail-safe email.browserTicket QA orchestratorTicket troubleshooter & orchestrator — reads a helpdesk ticket from Helpdesk (FreeScout) (or a domain + work-category pair), routes to the right QA skills, runs them, collects their verdicts, and reports PASS / REVIEW / FAIL with next-step guidance.
What is the site actually built on?Stack, hosting, tags.
Analytics & tagsAnalytics & tag presence audit — reads a page's delivered HTML and inventories the measurement, advertising and session-replay tags firing on it: Google Tag Manager, GA4, legacy Universal Analytics, Google Ads, Meta Pixel, LinkedIn, TikTok, Microsoft Ads, Pinterest, Clarity, Hotjar, Segment, Matomo.wiki-enhancedbrowser+ runtimeCloudflare zone clientOptional integration — reads a domain's Cloudflare zone: DNS records, the deploy surface (with --pages-project), and the zone settings that rewrite delivered HTML (Rocket Loader, Auto Minify, Email Obfuscation, Auto HTTPS Rewrites) — settings every HTML-reading skill in the tree is otherwise blind to.needs a keyDivi auditDivi front-end audit that routes by major version (Divi 4 vs Divi 5) — confirms a page is built with Divi, then reads the rendered HTML to report the Divi module inventory and the Divi-specific performance and config signals visible from outside: inline-CSS weight (the classic Divi bloat), Google Fonts loading, the jQuery dependency, and per-breakpoint responsive tailoring.wiki-enhancedbrowserHosting & DNSHosting & DNS infra fingerprint — reads a domain's DNS, TLS, headers and RDAP and reports the backend stack: web host, nameservers, CDN/edge, email provider, SSL issuer, CMS, registrar and last-changed date.wiki-enhancedMainWP fleet clientOptional integration — reads a MainWP dashboard's fleet: every managed WordPress site, pending core/plugin/theme update counts, and connection health.needs a keyWordPress inspectorRead-only WordPress site inspector — fetches a URL and reports what the site is running before you touch it: whether it is WordPress at all, the WP and PHP versions, web server and managed host, active theme and child theme, the page builder (Divi 4 vs 5, Elementor, Beaver Builder, WPBakery, Bricks, Oxygen, Gutenberg), the plugins visible from outside, the caching and CDN layer, and externally-visible security notes — into a DETECTED / LIKELY / NOT WORDPRESS verdict plus an HTML report.wiki-enhancedWordPress REST inventoryOptional read-only WordPress REST client. Lists core facts, registered routes, installed plugins and themes, users and roles, and content totals from an authenticated WordPress site.writes (dry-run first)WP Engine install clientOptional integration — reads which WP Engine install serves a domain: which install (and whether it is production/staging/dev), every domain attached to it, its PHP version, and its backup points.needs a keyWP plugins & themeWordPress plugin and theme audit — takes the plugins and active theme a site exposes and checks each against the WordPress.org directory for freshness: outdated (behind latest), abandoned (long since updated), and lagging the current WordPress version.wiki-enhanced
How do I get started?Setup and onboarding.
Agentic skill security auditAudits a local agent-skill repository against the OWASP Agentic Skills Top 10.Contextual copy reviewRead complete visible page copy in context and find valid-but-wrong words, homophones, missing or duplicated words, malformed phrases, and sentences whose grammar is technically plausible but whose meaning is broken.LLMSetup & doctorThe toolkit's friendly front door, onboarding guide and doctor — routes a business outcome to an approved workstream before a focused capability; guides setup, use, maintenance and contribution; and diagnoses agent links, masked key status, checkout freshness, and Node/OS.Visual layout auditVisual-layout / composition audit — the "passes every check and still looks wrong" gate.browser
Can this launch?The pre-live gate.
Cloudflare crawl remediationApplies reviewed technical-SEO remediation plans to a local Cloudflare Workers Static Assets or Pages-compatible candidate.Cloudflare deploy surface checkVerifies a live Cloudflare Pages deploy for the six traps invisible to every check that only reads HTML: a Content-Security-Policy header silently dropped because its _headers line ran over Cloudflare's length limit; a served asset over 25 MiB, which hard-rejects the whole deploy; the deployed HTML rewritten by Auto-Minify so a byte-parity comparison drifts against a transform nobody made; a stale edge-cached alias serving the previous bundle for up to 24h after a redeploy; declared _headers/_redirects rules that were written but never confirmed live; and an Access-gated preview reachable on its unprotected deployment alias even though the project alias is gated.Cutover readinessCutover readiness for a replacement site — everything wrong with a new build in its own right, before a domain is pointed at it.Migration gateThe migration gate for a WordPress-to-Cloudflare migration.+ runtimeOld vs new page parityOld vs new page parity across two hosts.Pre-cutover site archiveArchives the old site before it stops existing, hash-bound and content-addressed.browserSemantic frontend compilerCompiles a reviewed, structured migration blueprint into a separate semantic first-party static frontend.Static-site boilerplateStatic-site boilerplate generator — writes robots.txt, sitemap.xml, 404.html, and _redirects for a site with no server behind it.Structured site translation converterMachine-translates complete structured site route contracts through an explicit Google Cloud Translation draft lane, and creates reviewable multilingual translation work packages, applies completed translations without changing source-language pages, rewrites internal links to reciprocal language routes, repairs copied source-language fields in existing counterparts, protects glossary terms and identifiers, and validates draft versus human-approved translation status.What the old site didWhat the old site was doing that the new one has to keep doing — the audit that runs while the old site still exists.WordPress to Cloudflare migration engineBuilds and proves WordPress-to-Cloudflare migrations: intake, local origin, closure crawl, asset localization, forms, SEO cleanup, deployed parity, mobile QA, staging, and human cutover.
How do I run my own day-to-day?Tickets, tasks, logs, wiki.
Activity log clientClient for the team's internal Activity Logs work-log tool.Gcloud & BigQuery CLIGuardrailed gcloud + bq operator — run one gcloud or bq command with lint, ACL, project-explicit and dry-run-first semantics instead of shelling execFile ad-hoc.Google Workspace clientGoogle Workspace connector for Gmail and Drive — per-user OAuth via google-oauth.Helpdesk (FreeScout)FreeScout helpdesk client — reads a support desk over its REST API and turns the queue into a snapshot you can act on: every mailbox with conversation counts by status, the total open load, and the most recent active conversations with customer, assignee and age.wiki-enhancedSQL introspectionRead-only SQL introspection micro-skill — describe a BigQuery schema, sample rows, and validate constraints (not-null, uniqueness, referential hints) with SELECT-only guardrails.Task board (monday.com)monday.com task board — board overview (open/done/overdue, by-status, who it sits with) via REST or an agent-captured MCP payload; verdict always INFO.Video to checklistVideo walkthrough to actionable checklist — extracts the transcript, cuts timestamped screenshots, and turns spoken feedback into an annotated, approvable todo list.Wiki publisher (Outline)Publishes a local markdown file, with its local images, to a page on the team Outline wiki — the step other content tools stop short of, leaving a human to copy-paste markdown and drag images in by hand.wiki-enhanced