Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/unifapi-agent/agents/schemanpx skills add unifapi-agent/agents --skill schemagit clone --depth 1 https://github.com/unifapi-agent/agentsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00112 | $0.01877 |
| Opus 5 | $0.00056 | $0.00938 |
| Sonnet 5 | $0.00022 | $0.00375 |
| Haiku 4.5 | $0.00011 | $0.00188 |
Grade A, and why
schema scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **Inventory existing markup.** Note what schema (if any) is already present and whether it errors. To read JS-injected JSON-LD on the live page, hand off to **seo-audit** (`browser/html` / `browser/markdown`); a `web_ How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schema Markup
You are an expert in structured data. Your goal is to pick the right schema.org types for a page, generate valid JSON-LD, and steer clear of the mistakes that get rich results disqualified — so search engines understand the content and the page becomes eligible for enhanced results.
This is an advice skill — UnifAPI is not called here. It recommends types and generates JSON-LD; your own assistant writes it into the site. (When you need to read the JS-injected JSON-LD already on a live page before changing it, the seo-audit skill does that via browser/html / browser/markdown — a static fetch can't see client-side-injected schema.)
Workflow
- Read context first. If
.agents/product-marketing.md(or.claude/product-marketing.md, or legacyproduct-marketing-context.md) exists, read it before asking questions; only ask for what it doesn't cover. - Identify the page type and the rich results it can earn — what is the primary content, and which enhanced result is realistically available (see Common Schema Types).
- Inventory existing markup. Note what schema (if any) is already present and whether it errors. To read JS-injected JSON-LD on the live page, hand off to seo-audit (
browser/html/browser/markdown); aweb_fetch/curlstrips<script>tags and will miss it. - Choose the right types and properties — match each to its required and recommended fields (Quick Reference). When a page legitimately is more than one thing, combine types under
@graphrather than emitting separate disconnected blocks. - Generate valid JSON-LD for the page, accurately reflecting visible content (Output Format; full examples in references/schema-examples.md).
- Validate with the Rich Results Test and the Schema.org Validator, fix errors/warnings, then hand the markup to your own assistant to add to the site.
Core Principles
- Accuracy first — markup must represent content that is actually on the page; don't mark up what isn't there; keep it in sync when content changes. Mismatched schema gets rich results revoked.
- Use JSON-LD — Google's recommended format; easiest to maintain. Place it in
<head>or at the end of<body>. - Follow Google's guidelines — only use types/properties Google supports for rich results; check eligibility requirements; avoid spammy markup.
- Validate everything — test before deploying; monitor Search Console Enhancements; fix errors promptly.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 132 lines · 112 tokens per session scan A 0a246eac390e
schema is a skill published in the GitHub repository unifapi-agent/agents (557 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 1,877 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ansvisor-aeo-coach-standalone
Standalone (no-MCP) version of the Ansvisor AEO Coach. Use this only when the user's Claude client cannot connect to the Ansvisor MCP server (e.g. claude.ai web without a Connector configured). Fetches live data from the Ansvisor REST API directly with the user's API key via code execution. For clients that support…
ansvisor-aeo-coach
Acts as an Answer Engine Optimization (AEO) analyst for users running Ansvisor. Activates when the user asks how their brand is doing across AI search engines (ChatGPT, Gemini, Perplexity, Claude, Copilot, AI Overview, AI Mode), why visibility changed, or how they compare to competitors. Uses the Ansvisor MCP server…
open-geo
Run an end-to-end GEO visibility measurement through a real AI interface, persist the captures, and return a portable JSON run artifact plus optional PDF/dashboard outputs. Use automatically on an explicit request to measure a brand's AI-search visibility, and as a composable data-collection step inside another agent…
geo-platform-optimizer
Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually.
geo-report
Generate a professional, client-facing GEO report combining all audit results into a single deliverable with scores, findings, and prioritized actions.
geo-schema
Schema.org structured data audit and generation for rich results and entity clarity — detect, validate, and generate JSON-LD markup. Schema is NOT an AI-citation lever (Ahrefs controlled study, May 2026); it earns rich results and keeps entity data unambiguous.