A system for adding JSON-LD structured data, a machine-readable description of a web page, so search engines can understand its content. It supports page types such as articles, products, frequently asked questions, and navigation trails.

Use it when building programmatic SEO pages or fixing schema errors reported by Google Search Console. It can generate site, page, breadcrumb, article, product, FAQ, rating, and other context-specific markup from real page data.

It reduces errors in the structured data that search engines use for enhanced results. It also helps ensure generated pages describe themselves with the schema type that matches their actual content.

pseo-schema — Skill for Claude Code by lisbeth718/pseo-skills

Install

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.

Any agent

npx skills add lisbeth718/pseo-skills --skill pseo-schema

Clone the repo

git clone --depth 1 https://github.com/lisbeth718/pseo-skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lisbeth718/pseo-skills/pseo-schema/github.svg)](https://agentmods.dev/skills/lisbeth718/pseo-skills/pseo-schema)

Your own site

<a href="https://agentmods.dev/skills/lisbeth718/pseo-skills/pseo-schema"><img src="https://agentmods.dev/badge/skills/lisbeth718/pseo-skills/pseo-schema/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/lisbeth718/pseo-skills/pseo-schema"><img src="https://agentmods.dev/badge/skills/lisbeth718/pseo-skills/pseo-schema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,939 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What 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 5.1	$0.00088	$0.03939
Opus 5.5	$0.00035	$0.01576
Sonnet 5.5	$0.00018	$0.00788
Haiku 4.5	$0.00009	$0.00394

Measured 9d ago against content hash b1d972e53998, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pseo-schema scanned grade A with 0 findings 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 9d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/pseo-schema/SKILL.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pSEO Schema Markup

Implement JSON-LD structured data that describes what is visibly on each programmatic page, so eligible pages can qualify for rich results.

Research basis: https://github.com/lisbeth718/pseo-skills/blob/main/docs/research-2026-10.md (primary sources, 2026-10-12).

Core Principles

JSON-LD format: Always use JSON-LD, not Microdata or RDFa
Context-appropriate types: Match schema type to the page's actual content
Data-driven generation: Schema is built from the same data that drives the page
Valid and complete: Every schema block must pass Google's Rich Results Test
No fabrication: Only include fields backed by real data
Matches visible content: Structured data must match the text users see on the page (Google's AI features docs repeat this)
Review it like content: Google says to manually fact-check AI-generated structured data, along with titles, meta descriptions and alt text

Scope parameter

types selects what to implement. Article, Product, LocalBusiness, JobPosting, Event, Breadcrumb, Organization = sections 1-5 plus the matching rule in section 4 (Product also section 8, LocalBusiness also section 9). Author = sections 6 and 7 (author, reviewer and entity pages). all (default) = everything.

What Schema Does and Does Not Do (as of 2026-10-12)

Rich results only. The value of schema in Google Search is rich-result eligibility. It is not a ranking tactic.
No special schema for AI features. Google states AI Overviews and AI Mode need no special schema.org markup, and tells sites not to over-focus on structured data. Do not add markup "for AI" or "for LLM extraction".
Retired in Google Search, do not generate for rich results:
- FAQ rich results: no longer shown from 2026-05-07, docs removed 2026-06-15
- HowTo (removed 2023) and Sitelinks search box (removed 2024)
- Practice problems (deprecated 2025-11-05, docs removed 2026-01-06)
- Course info, Estimated salary, Learning video, Special announcement, Vehicle listing (phased out, docs removed 2025-09-09)
- ClaimReview: being phased out in Google Search
Dataset markup is only used by Dataset Search since 2025-11-05, not Google Search.
Breadcrumbs: mobile results show the domain only since 2025-01-23. Desktop still shows breadcrumbs, and BreadcrumbList markup remains supported.

Read the full file on GitHub · 359 lines

Changes

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.

9d ago Changed · +93 lines b1d972e53998
26d ago Changed · +51 lines · +32 tokens per session 65f461d0b6af
2mo ago First seen · 215 lines · 56 tokens per session scan A f04291f1a92a

Subscribe to this mod's changes

pseo-schema is a skill published in the GitHub repository lisbeth718/pseo-skills (55 stars, last pushed 9d ago), licensed MIT. It adds 88 tokens to every session and 3,939 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Marketing and SEO

pseo-schema next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
pseo-schemalisbeth718/pseo-skills	Skill	55	9d ago	MIT	A	88	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code