Agent skills
Skills for AI coding agents, each with what it costs to load, how much of it is scripts and what it touches on your machine.
How to read a skill
What it costs to keep
Idle in context, in use when it runs, and up to with its linked files.
Scripts or instructions
Script-led, mixed or model-led: how much the model has to work out itself.
What it can reach
Shell, network, file writes, git and credentials, declared or detected.
Quality, security, repo health
Out of 100, each with what it is made of. Turn a card over to see them.
seo-hreflang
31,136Validate hreflang on a multi-language site, or generate correct tags as HTML, HTTP headers or sitemap XML, with content parity and locale checks.
seo-local
31,136Score a local business site on Google Business Profile signals, reviews, NAP consistency, citations, local schema and location page quality.
seo-maps
31,136Analyze a business on map platforms: geo-grid rank scans, GBP field audit, cross-platform reviews and NAP checks, and competitor radius mapping.
seo-page
31,136Review one URL end to end: a scripted set of on-page checks first, then judgment on content, schema, images and Core Web Vitals risks.
seo-plan
31,136Plan SEO for a new or existing site: competitor analysis, architecture, content calendar and a four-phase roadmap from six industry templates.
seo-programmatic
31,136Plan and audit SEO pages generated at scale from data, with quality gates against thin content, scaled content abuse and index bloat.
seo-schema
31,136Detect, validate and generate Schema.org JSON-LD for a page, with current rich result status and warnings on deprecated types.
seo-sxo
31,136Find out why a technically sound page does not rank: compare its page type with the SERP, derive user stories, score personas and draw wireframes.
seo-cluster
31,135Cluster keywords by how Google ranks them, plan hub-and-spoke content with an internal link matrix, and open an interactive cluster map in the browser.
seo-competitor-pages
31,135Create X vs Y, alternatives and best-of pages with feature matrices, matching schema markup, title formulas and conversion-minded layouts.
seo-content-brief
31,135Write research-backed content briefs with competitor gap scoring, a winning outline, per-section word counts, keyword placement and meta tag guidance.
seo-geo
31,135Audit a page for AI Overviews, AI Mode, ChatGPT and Perplexity citations: passage citability, AI crawler access, llms.txt, brand signals and rendering.
seo-ahrefs
31,134Pull live Ahrefs referring domains, backlinks, organic keywords and Content Explorer data into Claude Code through a pinned Ahrefs MCP server.
seo-bing
31,134Read Bing Webmaster link data and submit fresh URLs through IndexNow from Claude Code, for Bing, Copilot citations and other non-Google engines.
seo-posthog
31,134Use the PostHog MCP server to report organic visits, landing pages, devices, countries and referrers from Claude Code with read-only HogQL queries.
seo-profound
31,134Read Profound citation rates for your brand across ChatGPT, Perplexity and other LLMs, with top prompts, competitors and spike or drop alerts.
seo-seranking
31,134Measure brand share of voice across ChatGPT, Gemini, Perplexity, AI Overviews and AI Mode with SE Ranking, plus SERP and backlink data, in Claude Code.
seo-unlighthouse
31,134Run Lighthouse across up to 200 routes with the Unlighthouse CLI from Claude Code, with no API quota, and get median scores per category.
ab-test-analysis
28,201Analyze A/B test results for significance, sample size and guardrail metrics, and get a ship, extend, stop or investigate recommendation.
analyze-feature-requests
28,201Groups customer feature requests into themes, checks strategic fit and ranks the top three by impact, effort and risk.
ansoff-matrix
28,201Map growth options on the Ansoff Matrix across penetration, market development, product development and diversification.
Beachhead Segment
28,201Pick the first market segment for a launch by scoring candidates on pain, budget, winnable share and referral potential.
brainstorm-experiments-existing
28,201Designs low-effort experiments for an existing product, from fake doors to A/B tests, each with a metric and a success threshold.
brainstorm-experiments-new
28,201Writes an XYZ hypothesis for a new product and designs two or three pretotype experiments such as landing pages and pre-orders.