sleevy.app
Finalizing the report
Preparing the stored Is Agentic score
Essential—
Recommended—
Bonus signals—
sleevy.app
Preparing the stored Is Agentic score
sleevy.app
These checks describe whether an ordinary agent can enter, read, and operate the public site.
Agents can reach the site
Crawler access and bot defenses.
Core content is available
Useful content remains accessible without a fragile browser-only path.
Navigation fails safely
Redirects and missing pages give agents a recoverable path.
Controls are understandable
Forms and interactive controls expose usable names and structure.
The public website is always evaluated. Optional surfaces appear when the scan finds positive evidence that they apply.
Strong
Weighted across 17 applicable checks
Strong
Weighted across 12 applicable checks
Ready with gaps
Weighted across 3 applicable checks
Blocked
Weighted across 1 applicable check
Strong
Weighted across 1 applicable check
Critical access gaps come first, followed by other applicable readiness gaps.
Make sure a clean search for your brand name returns your own domain in the top results. If it does not, your brand may be too generic, conflict with a more established term, or not yet indexed. Strengthen brand-name search by claiming consistent NAP across listings, earning press mentions that link to the canonical domain, and avoiding redirect chains that mask the apex domain in search results.
Make your developer resources (API docs, OpenAPI spec, auth docs, developer portal, MCP server) discoverable by name. Publish them at predictable URLs, list them in llms.txt, and include your product name in page titles and headings so search engines surface them for name-based queries.
Build an MCP (Model Context Protocol) server exposing your API as tools. Use Streamable HTTP transport for full score. This lets Claude, ChatGPT, and other AI agents call your product natively.
Add Organization JSON-LD that includes both contactPoint (with email/phone and contactType) and address (PostalAddress). This lets AI verify your business legitimacy and answer contact queries.
Offer a free tier or trial, self-serve API key generation, and a sandbox environment. Agents can't fill out 'contact sales' forms.
Checks are grouped by relevance for Docs & content sites.
2198 chars, semantic headings (H1 + 5 H2s + 4 H3s), 7.1% content ratio
Site accessible to 6 AI agent user-agents
No meta-refresh stubs, JavaScript-redirect stubs, or cross-domain hops across 6 checked pages
All 5 sampled pages are publicly readable (5 with substantive content)
OpenAPI spec found at https://sleevy.app/openapi.json (version: 3.1.0)
Canonical URL serves text/markdown and text/html via Accept negotiation with Vary: Accept
All major AI crawlers can reach the site: ChatGPT-User, ClaudeBot, Google-Extended, ora-agent, DeepSeekBot.
OAuth authorization server metadata at https://sleevy.app (issuer=https://api.sleevy.app/api/auth)
OAuth security scheme "oauth2" declares 8 named scope(s) in the OpenAPI spec (e.g. saved-items:capture, saved-items:read, saved-items:write)
API returns JSON error responses (404 at https://api.sleevy.app (from OpenAPI servers))
Nonexistent paths return HTTP 404 with markdown guidance for agents - the strongest 404 contract
Name search surfaced no pages on sleevy.app, although developer resources exist on the site (API docs, OpenAPI spec, auth docs, MCP server) - weak search indexing or transient search noise
How to pass
Make your developer resources (API docs, OpenAPI spec, auth docs, developer portal, MCP server) discoverable by name. Publish them at predictable URLs, list them in llms.txt, and include your product name in page titles and headings so search engines surface them for name-based queries.
"Sleevy" search returned 8 results but domain did not appear - brand may be too generic or not indexed
How to pass
Make sure a clean search for your brand name returns your own domain in the top results. If it does not, your brand may be too generic, conflict with a more established term, or not yet indexed. Strengthen brand-name search by claiming consistent NAP across listings, earning press mentions that link to the canonical domain, and avoiding redirect chains that mask the apex domain in search results.
Valid sitemap found at https://sleevy.app/sitemap.xml with 28 entries
Rich JSON-LD identity: Organization with name, description, url, and sameAs/logo/address (1 block)
Pricing structured data (schema.org/Offer) found
API/docs link found on homepage and resolves: /docs
When-to-use guidance found in llms.txt
All metadata signals present: canonical URL, lang="en", og:image, og:type
Organization schema found but missing: address
How to pass
Add Organization JSON-LD that includes both contactPoint (with email/phone and contactType) and address (PostalAddress). This lets AI verify your business legitimacy and answer contact queries.
All trust anchor pages verified: About, Contact, Privacy
All 8 measured pages fit an agent context budget (largest ~2K tokens)
Code fences balanced across 2 markdown documents
Developer portal found at /docs
REST API documentation found at https://sleevy.app/docs. Best-of-protocols score: 7/7.
Onboarding signals described but not verified live: sandbox/test environment, zero-auth access
How to pass
Offer a free tier or trial, self-serve API key generation, and a sandbox environment. Agents can't fill out 'contact sales' forms.
MCP mentioned at https://sleevy.app/index.md but no standard manifest endpoint found
How to pass
Build an MCP (Model Context Protocol) server exposing your API as tools. Use Streamable HTTP transport for full score. This lets Claude, ChatGPT, and other AI agents call your product natively.
The live API at https://api.sleevy.app/ returns IETF RateLimit-* headers: ratelimit-limit, ratelimit-remaining, ratelimit-reset.
OpenAPI defines a typed error schema in components.schemas and 4xx/5xx responses reference it
API versioning found (URL versioning (servers or paths)) but no deprecation or sunset policy detected - add Sunset/Deprecation headers or a deprecation policy page
How to pass
Declare a versioning policy agents can rely on: version your API (in the URL path or a version header) and publish how you signal deprecation (a Sunset/Deprecation header or a documented timeline). Agents avoid integrating against a surface that can change without warning.
CLI tool mentioned in llms.txt
How to pass
Publish an official CLI tool on npm, PyPI, or Homebrew. A CLI lets agents and developers script interactions with your product without building API integrations from scratch.
89% of operations define typed response schemas, 89% use application/json
REST: agent-friendly schema (27 operations, 100% with operationIds, 100% documented by description or summary)
Compatible: 27/27 ops with IDs, 27/27 with typed schemas
ARD catalog valid (spec 1.0) - 6/6 entries, trustManifest present
All 6 entries valid with domain-anchored urn:air identifiers
trustManifest present on catalog entries (6/6 entries valid)
Agent config found: github.com/onnokh/sleevy/blob/master/AGENTS.md
Agent Skills index (agentskills.io) found at /.well-known/agent-skills/index.json with 3 skill(s)
Index v0.2.0 conformant; verified SHA-256 of "sleevy-organize-folders" (2 other skills present)
A2A Agent Card found: "Sleevy"
MCP server discoverable via server-card.json at /.well-known/mcp/
Agent mode view found at ?mode=agent (6 signals: llms.txt, openapi, mcp, api, agent, integration)
How to pass
Add a ?mode=agent query parameter to your homepage that returns a structured, machine-readable view with API endpoints, authentication info, and key capabilities instead of marketing HTML.
RFC 8288 Link header advertises: sitemap, describedby, service-desc, service-doc, api-catalog, alternate(markdown)
Full markdown fallback support. Homepage (https://sleevy.app/index.md) and all 3 sampled content pages return markdown: https://sleevy.app/docs.md, https://sleevy.app/docs/api-reference.md, https://sleevy.app/docs/authentication.md
Modular llms.txt files found for sections: docs, api
100% of 28 sampled sitemap entries carry lastmod; newest is 2 day(s) old
Found the llms.txt at https://sleevy.app/llms.txt.
The llms.txt is well-formatted: 55 lines with markdown links, 6,250 characters in total.
Entity linking to github.com - add more authority profiles (Wikipedia, Wikidata, LinkedIn, GitHub)
How to pass
Add sameAs links in your JSON-LD structured data pointing to your Wikipedia page, Wikidata entry, GitHub org, and social profiles. This helps AI disambiguate your brand from similarly named entities.
Some extended schema types found: Service, FAQPage - add FAQPage, Service, or AggregateRating for full coverage
How to pass
Expand your JSON-LD beyond Organization/WebSite. Add FAQPage for common questions, Service or Product for offerings, AggregateRating or Review for social proof, and BreadcrumbList for navigation context.
All 5 probed llms.txt links resolve to real content
Markdown alternate advertised and verified: https://sleevy.app/index.md serves markdown
Frontmatter with title + description, canonical, and last-updated on /index.md
application/linkset+json api-catalog with 2 API link(s)
Path-suffix markdown docs served with text/markdown content-type: /auth.md, /index.md
https://sleevy.app serves markdown to the GPTBot User-Agent even with Accept: text/html - UA-sniffed agent responses in place
All 8 tools on product MCP have detailed descriptions (>= 20 chars)
7/8 tools on product MCP have parameter schemas, 6 with required fields
product MCP identifies as "app.sleevy/mcp" v1.0.0 with instructions
product MCP exposes 8 tools - substantial tool surface
All 8 tool names follow consistent convention, descriptive, and non-generic
RFC 9728 metadata: resource=https://api.sleevy.app, authorization_servers (1), scopes_supported (8)
auth.md at https://sleevy.app/auth.md served as text/markdown; charset=utf-8 (5000 chars)
WorkOS auth.md structure at https://sleevy.app/auth.md - 4/7 walkthrough sections (found Discover, Pick a method, Register, and Claim); anchors: oauth-protected-resource, oauth-authorization-server, and agent_auth; register shapes: id-jag shape
Static fallback (deep check disabled): PRM + AS metadata both reachable with agent_auth.register_uri (https://api.sleevy.app/api/auth/oauth2/register); walkthrough discoverable end-to-end
PRM + AS metadata cross-linked (AS metadata fetched from advertised origin https://api.sleevy.app); agent_auth has register_uri (https://api.sleevy.app/api/auth/oauth2/register), identity_types_supported [anonymous] with per-type *_supported blocks, and skill -> https://sleevy.app/auth.md (also advertised: claim_uri, revocation_uri; events_supported absent)
401 at https://api.sleevy.app at /mcp with spec-shaped WWW-Authenticate hint: Bearer resource_metadata="https://api.sleevy.app/.well-known/oauth-protected-resource/mcp"
agent_auth endpoints reachable (source: AS metadata agent_auth block) - register_uri: HTTP 204, claim_uri: HTTP 204, revocation_uri: HTTP 204
product MCP returns structured JSON-RPC errors with code and message
product MCP uses modern Streamable HTTP transport
REST Idempotency-Key header found on POST /v1/captures/batch in OpenAPI spec
Cursor-based pagination found in OpenAPI spec response schemas or query parameters
product MCP: 8/8 tools have behavioral annotations (readOnlyHint/destructiveHint)
MCP server card found at https://api.sleevy.app/.well-known/mcp/server-card.json (8 tools advertised)
You run both MCP servers, but the documentation one (https://sleevy.app/docs/mcp) is not reachable. Fix it so agents can use it.
How to pass
Beyond your product MCP server, expose a documentation MCP surface so agents can pull your docs and reference material over the same protocol they use to act. Covering both the 'do' and the 'learn' surfaces over MCP earns this.
Batch endpoint found in OpenAPI spec (/batch path)
Server HTML is a well-structured document (main=true, landmarks=3/4, h1=1, maxHeadingSkip=1).
28 native controls, 0 non-native div-soup affordances (100% native).
28/28 interactive elements have a computable accessible name (100%).
No hidden instruction text detected in accessibility-tree attributes or off-screen content.
ACP checkout endpoint reachable at https://api.sleevy.app/checkout_sessions (OPTIONS 204 allows POST, POST 404 confirmed, ACP-shaped error)
Delegate Payment endpoint reachable at https://api.sleevy.app/agentic_commerce/delegate_payment (OPTIONS 204 allows POST, POST 404 confirmed, ACP-shaped error)
What does sleevy.app do and who is it for? Explain it back to me.
Sign me up for Vercel product updates and marketing emails.
Unsubscribe anytime. Privacy Notice
Source: Ora API
What does sleevy.app do and who is it for? Explain it back to me.
41 steps21 reasoning steps10 searches
The agent partially understood Sleevy by fetching its marketing pages (homepage, iOS app, Chrome extension, Raycast integration) but could not complete the task fully due to missing critical information. The site's pages are visually rich but HTML-truncated in responses, forcing the agent to rely on page titles and metadata rather than full content. Most critically, pricing information is entirely absent (a /pricing route returns 404), and the agent could not find business model details despite multiple web searches. The agent assembled a working description of what Sleevy does (API-driven bookmark manager with MCP server support, multi-platform input) and who it targets (power users, developers, AI integrators), but had to explicitly flag that key positioning details and competitor differentiation were missing or inaccessible.