What is wordlift-kg-builder?

A toolset for building and maintaining knowledge graphs from webpages using WordLift, a service that links structured information about things such as products, organizations, people, and pages. It uses identifiers, JSON-LD markup, validation, and API workflows.

Use it to import sitemap URLs, build product catalogs with GTIN identifiers, create schema.org JSON-LD, validate data, reuse existing entities, verify uploads, and synchronize changes.

It reduces duplicate entities and helps check that imported or updated data is valid and actually stored. It also supports both full imports and later incremental updates.

wordlift-kg-builder — Skill for Claude Code and Codex by wordlift

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 wordlift/wordlift-gemini-cli-extension --skill wordlift-kg-builder

Clone the repo

git clone --depth 1 https://github.com/wordlift/wordlift-gemini-cli-extension

Made for: Claude Code, Codex.

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/wordlift/wordlift-gemini-cli-extension/wordlift-kg-builder/github.svg)](https://agentmods.dev/skills/wordlift/wordlift-gemini-cli-extension/wordlift-kg-builder)

Your own site

<a href="https://agentmods.dev/skills/wordlift/wordlift-gemini-cli-extension/wordlift-kg-builder"><img src="https://agentmods.dev/badge/skills/wordlift/wordlift-gemini-cli-extension/wordlift-kg-builder/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/wordlift/wordlift-gemini-cli-extension/wordlift-kg-builder"><img src="https://agentmods.dev/badge/skills/wordlift/wordlift-gemini-cli-extension/wordlift-kg-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,484 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	$0.00091	$0.07484
Opus 5	$0.00046	$0.03742
Sonnet 5	$0.00018	$0.01497
Haiku 4.5	$0.00009	$0.00748

Measured 12d ago against content hash 6c291d2db4aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

wordlift-kg-builder 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 12d ago.

The scan reads SKILL.md. This mod also ships 12 executable files (scripts/entity_builder.py, scripts/entity_reuse.py, scripts/entity_upgrader.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/wordlift-kg-builder/SKILL.md · 1,024 lines

How it starts

The opening of the file, as written. The whole thing — 1,024 lines — stays where its author put it; the contents beside it link to each section on GitHub.

WordLift Knowledge Graph Builder

Build and maintain Knowledge Graphs from webpages using WordLift's Sitemap Import API, with focus on product catalogs and e-commerce data.

Core Capabilities

Sitemap Import API: Direct import of URLs from sitemap.xml or URL lists
Template Configuration: Interactive workflow to validate markup templates before bulk imports
GS1 Digital Link for Products: {dataset_uri}/01/{GTIN-14} identifiers
Slug-based IDs for Other Entities: {dataset_uri}/{entity_type}/{slug} format (⚠️ MUST use recognized patterns)
Entity Reuse via GraphQL: Prevents duplicates by checking for existing entities (Organizations, Brands, People)
SHACL Validation: Ensures data quality before upload with built-in shapes for Products, Organizations, WebPages, etc.
JSON-LD Creation: Programmatic creation of schema.org markup with EntityBuilder
Entity Upgrading: Post-import type changes and property updates using Fetch-Modify-Update pattern
Entity Verification: Verify entities are actually persisted (not just 200 OK)
Daily Sync Workflows: Full replacement or incremental PATCH updates
Batch Operations: Efficient bulk create/update operations

Quick Start

1. Import Pages from Sitemap

Use the Sitemap Import API to jumpstart your Knowledge Graph:

API Endpoint: POST https://api.wordlift.io/sitemap-imports

from scripts.wordlift_client import WordLiftClient

client = WordLiftClient(api_key)

# Import from sitemap.xml
results = client.import_from_sitemap("https://example.com/sitemap.xml")
print(f"Imported {len(results)} pages")

# Or import specific URLs
results = client.import_from_urls([
    "https://example.com/page1.html",
    "https://example.com/page2.html"
])

The API returns NDJSON (newline-delimited JSON) with details about each imported page.

Important: The endpoint is /sitemap-imports (plural), not /sitemap/import or /sitemap-import.

2. Query Imported Data

Read the full file on GitHub · 1,024 lines

Files

What ships with it

20 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.

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.

12d ago First seen · 1,024 lines · 91 tokens per session scan A 6c291d2db4aa

Subscribe to this mod's changes

wordlift-kg-builder is a skill published in the GitHub repository wordlift/wordlift-gemini-cli-extension (2 stars, last pushed 4mo ago), licensed MIT. It adds 91 tokens to every session and 7,484 once invoked, about $0.0005 per session on Opus 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 2026-08-31.

Marketing and SEO gemini-cli gemini-extension knowledge-graph mcp wordlift

wordlift-kg-builder

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

WordLift Knowledge Graph Builder

Core Capabilities

Quick Start

1. Import Pages from Sitemap

2. Query Imported Data

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

api-design

compound-docs

mobile

nextjs

performance

tailwind