Add or repair machine-readable agent discovery and interoperability surfaces for a website. Use when asked to expose llms.txt, AGENTS.md, Agent Skills, ARD, MCP, A2A, WebMCP, OpenAPI, API catalogs, agent-readable sitemaps, or an ARWP site profile. Discover what the site truly supports, prefer upstream standards, and…
Improve website content for search, AI search, citation, and recommendation surfaces without AI-generated filler. Use when asked to optimize articles, docs, landing pages, comparisons, answer pages, or knowledge content for Google Search, AI Overviews/AI Mode, ChatGPT Search, Bing/Copilot citations, or ARWP content…
Add ARWP verification, regression contracts, evidence receipts, scheduled audits, and CI to a website repository. Use when asked to continuously check ARWP quality, prevent agent/search regressions, monitor public interfaces, generate evidence, or prove that an ARWP implementation remains consistent over time. Keep…
Run an evidence-backed website growth loop for Search, Google Discover and recommendations, generative Search, Bing AI citations, ChatGPT Search and agent readability. Use when asked to make a site rank or discover better, get into recommendations, improve AI-search visibility, apply current ARWP guidance, or…
Prepare, upgrade, or migrate a website repository to the Agent-Ready Web Profile (ARWP). Use when asked to make a site agent-ready, AI-search-ready, easier for AI agents to understand, improve search/discovery quality, add ARWP metadata, or apply the ARWP profile to an existing site. Inspect the repository, implement…
Convert an ARWP Growth audit into a target-specific website upgrade graph with current source-backed practices, applicability, exact change surfaces, implementation recipes, verification contracts, measurement signals and knowledge-freshness checks. Use when the goal is to inspect a real site and decide what should be…
Trace why a website change exists, connect repository transformations back to evidence and rules, identify missing verification or outcome evidence, and compute source/rule change blast radius through the canonical ARWP BraidGraph instead of inventing a parallel provenance model. Use for change explanation…
Audit and prepare a genuine website corpus for versioned dataset publication, archival DOI citation, provenance and machine-readable discovery without treating DOI or metadata as ranking factors.
Explore and implement future-ready website semantics, machine-readable entity/evidence graphs, retrieval feedback and browser-agent operability after current Search foundations are healthy. Use when the goal is to prepare a real site for emerging Search/AI/agent systems beyond today's documented rich-result…
Reverse-engineer observable, evidence-bearing patterns from currently visible Search/AI reference pages, compare them with a target site, and route repeated gaps into evidence-backed experiments without pretending correlations are ranking factors. Use when the goal is competitive/reference analysis, site maturity…
Convert an ARWP Adaptive Site Upgrade graph into deterministic, digest-gated changes in a target website repository. Use after the agent has inspected the target repository and can resolve exact production files, grounded facts and verification conditions. Compile explicit path-allowlisted transformations, simulate…
Select concrete implementation practices from the ARWP discoverability corpus and validate editorial evidence receipts for articles and comparisons. Use as a specialist within arwp-growth-loop after the site problem and measurement scope are known.
Inspect and verify multiple local website repositories and their public ARWP profiles from one versioned workspace manifest. Use for portfolio-wide status, drift triage, repeated local checks, bounded live checks, or choosing the next site to improve. Do not use for a single-site implementation or as authorization to…
Define a website's problem territory, audience, explicit scope and anti-scope, page architecture, navigation, visual system and performance budget before expanding content or discoverability work. Use at the start of a site build/redesign or when a site feels broad, fragmented or feature-led.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: