linked-data-skills

linked-data-skills is a skill for Claude Code, Codex from OpenLinkSoftware/ai-agent-skills. It costs 167 tokens per session (7,024 once invoked), scanned A, original, MIT.

A set of procedures for turning database objects or documents into linked data and knowledge graphs. Linked data represents information as connected entities and relationships that software can query.

In plain words
What is it for?
It is for exposing relational database data as RDF, converting documents into schema.org-based RDF, and creating the associated vocabularies, data, and query rules.
Why use it?
It prevents unsafe or ambiguous data conversion by requiring the source type, schema details, and other setup choices before processing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit It is for exposing relational database data as RDF, converting documents into schema.org-based RDF, and creating the associated vocabularies, data, and query rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openlinksoftware/ai-agent-skills/linked-data-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 OpenLinkSoftware/ai-agent-skills --skill linked-data-skills
Clone the repo
git clone --depth 1 https://github.com/OpenLinkSoftware/ai-agent-skills

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.

agentmods badge for linked-data-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/linked-data-skills.svg)](https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/linked-data-skills)
Your own site
<a href="https://agentmods.dev/skills/openlinksoftware/ai-agent-skills/linked-data-skills"><img src="https://agentmods.dev/badge/skills/openlinksoftware/ai-agent-skills/linked-data-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,024 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 59
    Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
    Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
  • medium Excessive Agency · line 160
    Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
    Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
  • medium Excessive Agency · line 191
    Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
    Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
  • medium Excessive Agency · line 323
    Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
    Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
  • medium Excessive Agency · line 199
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Excessive Agency · line 373
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00167 $0.07024
Opus 5 $0.00084 $0.03512
Sonnet 5 $0.00033 $0.01405
Haiku 4.5 $0.00017 $0.00702

Measured 8d ago against content hash b86bfb94714c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

linked-data-skills 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 8d 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.

linked-data-skills/SKILL.md · 533 lines

How it starts

The opening of the file, as written. The whole thing — 533 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Linked Data Skills — Specification (v3.2.0)


MANDATORY PRE-TOOL SEQUENCE — READ BEFORE CALLING ANY TOOL

This section overrides all default tool-calling behavior. The five steps below must be followed in order. No step may be skipped or reordered.

Gate 1 — Send announcement and establish scope (NO TOOL CALL YET)

getSkillResource may be called once to load this skill's content. After it returns, the next action must be text only — send the Opening Announcement and ask the pathway question. Do not call any other tool. Wait for the user's reply.

  • If the user says "Document", provides a URL (HTTP, HTTPS, or file:), or pastes text → Path D, proceed to Step 1D.
  • If the user's message already contains an explicit qualifier.schema pattern (e.g., postgres.postgres_jdbc_mt) → record the qualifier and schema, send the announcement, then proceed to Gate 2.
  • If the user says "local" or names a local qualifier → Path B, proceed to Gate 2.
  • If the user says "DSN: X" → Path A, attach DSN, then proceed to Gate 2.
  • If ambiguous → send the Opening Announcement question. Wait. Do not call any tool.

Gate 2 — Enumerate tables (ADM.DBA.database_schema_objects ONLY)

Call ADM.DBA.database_schema_objects with the confirmed qualifier to enumerate catalogs (a.k.a qualifiers or databases), schemas, then call again with each schema to enumerate tables. Present the full numbered list. Wait for the user's table selection. Typically, you want to list tables for the designated catalog.schema.

The only tool permitted at this gate is ADM.DBA.database_schema_objects. Do not call ADM.DBA.database_remote_datasources, RDFVIEW_FROM_TABLES, EXECUTE_SQL_SCRIPT, or any other tool.

Gate 3 — Resolve hostname and protocol (BEFORE any IRI is written)

After the user selects tables, call Demo.demo.execute_spasql_query for DefaultHost and SSLPort. Derive {protocol} and {host}. These must be known before any IRI string is constructed.

Do not proceed to Gate 4 without concrete {protocol} and {host} values.

Read the full file on GitHub · 533 lines

Files

What ships with it

4 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.

  1. 8d ago First seen · 533 lines · 167 tokens per session scan A b86bfb94714c

Subscribe to this mod's changes

linked-data-skills is a skill published in the GitHub repository OpenLinkSoftware/ai-agent-skills (38 stars, last pushed 4d ago), licensed MIT. It adds 167 tokens to every session and 7,024 once invoked, about $0.0008 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 2026-08-30.