ai-agent-skills

Execute SQL, SPARQL, SPASQL, SPARQL-FED, and GraphQL queries against live data spaces and knowledge graphs via OpenLink's OpenAPI-compliant web services. Use this skill whenever the user wants to query a database, RDF store, or SPARQL endpoint; explore a knowledge graph or data space; asks "How to ...", "Define the term ...", or poses a question against a known article or graph context; or mentions linkeddata.uriburner.com, Virtuoso, OPAL, or OpenLink services. Full query templates are in references/query-templates.md — load that file before constructing any predefined query.

Record screencast videos of web application interactions using shot-scraper video. Use when the user says: record a screencast, record a video demo, make a walkthrough of, record this session, record what you just did, add voice-over narration, or mix narration into a screencast. Handles mTLS-authenticated endpoints (linkeddata.uriburner.com:5443), local dev server demos, after-the-fact recording from curl session history, optional OpenAI TTS MP3 generation, and dual-format storyboards: YAML (native input for shot-scraper) and RDF Turtle (optional input, auto-generated session log).

Perform ActivityPub read/write operations against Fediverse instances (Note, Like, Announce, Follow, Delete, Undo). Handles OAuth Authorization Code flow, WebFinger resolution, ActivityPub content negotiation, and server-to-server delivery verification.

Assemble or exercise OPAL Agents and Skills. Trigger on phrases like 'assemble an agent', 'create an AGENTS.md', 'build a skill', 'exercise an agent', 'test a skill', 'list OPAL agents', 'instantiate an agent', or any request to work with OPAL agents, skills, or function tools.

Generate sophisticated, interactive HTML infographics and optional Markdown companion documents from RDF data in any format (Turtle, RDF/XML, N-Triples, JSON-LD). Transform knowledge graphs into visually stunning, data-driven narratives with advanced CSS effects, dynamic interactions, floating navigation, smooth animations, comprehensive metadata, and Markdown variants when requested. Use when converting RDF datasets or SPARQL results into engaging, responsive infographic pages, Markdown companions, marketing assets, documentation, or knowledge exploration artifacts.

Bulk-load RDF archives (N-Triples, Turtle, RDF/XML, N-Quads, TriG, JSON-LD, Notation3 — gzip-compressed or raw) into a Virtuoso instance via isql, using ld_dir + rdf_loader_run. Covers single-file loads, directory-wide ingestion, load monitoring, named-graph management (clear/replace/append), and troubleshooting. Triggers on phrases like "load this RDF into Virtuoso", "bulk load into Virtuoso", "ingest .nt.gz into Virtuoso", or any request to push RDF data to a Virtuoso SPARQL endpoint via isql.

Generate, verify, and manage Web-scale verifiable digital identities (NetIDs) using semantic web standards. Produces self-signed X.509 certificates, WebID profile documents (Turtle, JSON-LD, RDFa HTML), identity card HTML pages with optional OPAL AI widget, vCard VCF, and complete linked-data identity bundles. Uploads identity documents to WebDAV/LDP endpoints via curl. Verifies existing WebID profiles by fetching and executing SPARQL queries against URIBurner. Triggers on phrases like "generate a NetID", "create a YouID identity card", "generate a WebID profile for", "create a WebID profile", "verify WebID", "verify identity at", "generate X.509 certificate for", "upload identity documents to", "delegate identity for", "what is a NetID", "define WebID", "explain YouID", "self-sovereign identity", "digital identity card", "WebID-TLS", "DPKI certificate". Compatible with the OpenLink YouID browser extension.

Generate RDF-Turtle descriptions (schema:ImageObject, schema:VideoObject, schema:WebPage) for infographic files in a WebDAV directory, using SHACL shapes as the property contract. Trigger when: user asks to describe infographics, generate metadata for a DAV directory, create RDF descriptions for image/video collections, or apply a SHACL shape to bulk-describe files. Handles content negotiation (HTML describe pages vs SPARQL DESCRIBE), filename-derived metadata, thumbnail URL detection, and category inference.

Generate RDF Turtle offer/license/price bundles for File Access, Graph Access, and API Access products. Trigger on phrases like 'generate offers', 'create license bundle', 'make a file access offer', 'generate graph access offer', 'create API access offers', or any request to produce resource-access offers in Turtle format.

Intent-driven ACP (Adaptive Commerce Platform) client. Handles natural-language purchase requests by executing checkout, cart, and order flows against OpenLink's ACP API. Integrates Stripe test SPT generation for checkout completion. Supports product resolution from OpenLink offer catalog, checkout updates, cancellation, and subscription payment link detection.

Use this skill when a task needs browser automation through PinchTab: open or inspect web pages, click through flows, fill forms, scrape page text, export screenshots or PDFs, manage persistent browser profiles, or collect article source material for RDF, HTML, and Markdown outputs. Prefer this skill for token-efficient browser work driven by fresh accessibility refs such as e5 and e12.

Create or update a custom DAV DET variant based on RDF Import DET for Virtuoso. Use when the task is to scaffold, modify, or document a DET that ingests RDF documents into the Quad Store, supports one or more Virtuoso-supported RDF document types, implements the required _DAV_* hook family, or needs verification SQL, WebDAV probes, and VAD/source integration notes.

Client-side S3 API access for querying data directly at S3 and S3-compatible endpoints — AWS S3 public/private buckets, Hugging Face Storage Buckets (s3.hf.co), Cloudflare R2, MinIO, Wasabi, Backblaze B2 — without a full download. Uses DuckDB's httpfs extension to run SQL directly against remote Parquet/CSV/JSON/ND-JSON objects (e.g. querying the Common Crawl columnar index or a Hugging Face-hosted crawl index in place), plus AWS CLI/boto3 for object-level list/head/get/put and rclone for bulk cross-store copy. Triggers on phrases like "query data in an S3 bucket", "query an S3 API endpoint", "read a Parquet file from S3 without downloading it", "list objects in this bucket", "query the Common Crawl index", "connect to a Hugging Face Storage Bucket via S3", or any request to read/query/list/copy data at an `s3://` URI or S3-compatible HTTPS endpoint.

Transforms documents or text into RDF-based Knowledge Graphs using schema.org terms. 4-step workflow: (1) Collect document source, {page_url} as @base, output format (JSON-LD or Turtle by default; others if explicitly stated), and destination folder. (2) Generate RDF via schema.org prompt template using chatPromptComplete. (3) Post-generation review: fix syntax errors, present additional Q&A/defined terms/howtos and entity types for approval, return revised final output if approved. (4) Save approved RDF to designated folder and confirm saved path.

Generate comprehensive Knowledge Graphs (RDF-Turtle by default, or JSON-LD and other RDF serializations on request) from content at file: or http(s): scheme URLs. Uses curated prompt templates: a Generic template for general web content (producing JSON-LD), and a Business and Market Analysis template for strategy/analysis content (producing RDF-Turtle with NAICS industry code identifiers, lightweight ontology, FAQ, glossary, and HowTo sections). Trigger when users ask to: generate a knowledge graph, generate RDF or RDF-Turtle, generate JSON-LD, convert a URL to structured semantic data, or extract schema.org data from a page or document.

Transform natural language questions into SPARQL queries for DBpedia and generate beautiful HTML results pages. Query the DBpedia knowledge graph using plain English prompts.

Transform natural language questions into SPARQL queries for Wikidata and generate beautiful HTML results pages. Query the Wikidata knowledge base using plain English prompts.

Expert navigator for the OpenLink FIFA World Cup Knowledge Graph and RDF ontology (https://www.openlinksw.com/ontology/fifa#). Use this skill whenever an agent needs to write SPARQL queries against FIFA World Cup knowledge graph data, look up correct property URIs, understand class hierarchies, interpret numeric coded values (card types, match periods, event types, positions, tactics), design query patterns for matches, players, teams, goals, bookings, substitutions, lineups, weather, rankings, analytics metrics, match officials, referees, country/nationality data, FIFA power rankings, win probability, expected goals (xG), pitch control, goalkeeper saves, or the power rankings named graph (urn:fifa:powerrankings). Trigger this skill for ANY FIFA ontology or KG query-writing task, even if the user just says "write a SPARQL for FIFA data", "how do I query goals/players/match events", "show me analytics for a team", "compare player distances run", "possession stats", "pressing intensity", "query match analytics

Configure and verify ODBC Data Source Names (DSNs) using iODBC or unixODBC. Supports three execution modes in priority order: (C) OpenLink www_sv Admin Assistant HTTP server — preferred when available; (B) odbc_rest_server.py REST bridge — for remote/sandbox access; (A) local CLI via iodbctest/isql. Works on macOS and Linux. Covers all DSN types: MT (Multi-Tier), Virtuoso, Unix Lite, and single-tier. Use when the user asks to list, test, configure, add, or troubleshoot ODBC DSNs.

Use FuXi for various semantic web reasoning needs (RDF, RDFS, OWL, RIF, SPARQL)

Create or update a custom DAV DET that accepts CSV uploads, transforms them to RDF, and then writes to the Quad Store. Use when the task is to scaffold, modify, or document a CSV-backed ingestion DET with DAV hook functions, CSV-to-RDF mapping logic, graph assignment rules, verification SQL, SPARQL checks, and packaging notes.

Generates Knowledge Graphs from two source types: (A) relational database objects via Virtuoso RDF Views, or (B) documents/text transformed to RDF using schema.org terms. PATH RDBMS — STRICT 5-step workflow: ask local-vs-DSN, enumerate tables, resolve hostname, confirm IRI patterns, generate TBox+ABox+rewrite rules, verify with entity samples. PATH D — 4-step workflow: collect document + {page_url} + format (JSON-LD or Turtle), generate RDF via prompt template, post- generation review (syntax fix, additional Q&A/entity types), save to user-designated folder. TOOL HIERARCHY: read queries use Demo.demo.execute_spasql_query; writes use EXECUTE_SQL_SCRIPT; RDF generation uses chatPromptComplete.

Machine Payment Protocol (MPP) client using Stripe. Prompts for a target MPP-protected URL, then handles the 402 challenge flow automatically — creating a Stripe Shared Payment Token (SPT) and retrying to retrieve the paid resource.

Start, stop, restart, enable at boot, and check the status of the OpenLink License Manager (oplmgr) daemon on macOS, Linux, and Windows. Detects OS and init system automatically. Use when the user asks to start, stop, restart, enable, disable, or check the status of the OpenLink License Manager or oplmgr.

Read and display OpenLink Software license files (.lic) in a beautified, human-readable format. Parses ASN.1 DER-encoded license files using openssl, extracts all license fields, flags expired licenses visually, and supports single-file or directory-wide scanning. Use when the user asks to read, inspect, check, or list OpenLink license files.

Configure and manage the OpenLink Request Broker (oplrqb) rule book (oplrqb.ini). Primary use: configure ODBC Agent rules from host DSNs and JDBC Agent rules from discovered JDBC driver JARs. Also covers general Mapping Rules, DB Agent sections (generic_*), Environment sections, broker global settings, alias sections, reinit/restart, log viewing, and version detection. Two modes: (C) www_sv HTTP Admin Assistant on port 8000 — preferred; (A) direct file edit + CLI — fallback. Use when the user asks to configure ODBC or JDBC agents, add or edit mapping rules, view or edit the broker rule book, restart or reinitialize the broker.

Manage, explore, and troubleshoot OPML, RSS, and Atom news feeds using predefined SPARQL/SPASQL queries against OpenLink's linked-data infrastructure. Use this skill whenever the user wants to explore an OPML or RSS/Atom feed URL, retrieve the latest news posts from a feed, diagnose feed processing issues, or configure feed-related settings. Also handles feed auto-discovery when the user provides a plain web page URL — detects feeds via HTML <link rel="alternate"> tags, HTTP Link headers, and common path conventions. Trigger on phrases like "Explore the OPML news source", "Explore the RSS or Atom news source", "Explore the latest edition of", "Discover feeds at", "Find RSS feeds on", or any request referencing OPML/RSS/Atom feed URLs. Full query templates are in references/query-templates.md — load that file before executing any predefined query.

Generate valid RSS 2.0 or Atom 1.0 feeds from web pages that contain post lists but lack a native feed. Triggers on phrases like "generate a feed for", "create an RSS feed from", "make an Atom feed for", "this page has no RSS", or any request to produce a feed URL or feed XML from a blog/news/post-list page. The skill fetches the page, extracts post metadata, and outputs well-formed feed XML plus a self-hostable HTML wrapper with an embedded feed discovery link tag.

Set custom WebDAV properties on resources via PROPPATCH requests using curl. Supports arbitrary prefixed properties (schema:name, dc:title, etc.), auto-generated human-readable titles from filenames with type tags, batch processing, and known namespace defaults.

Comprehensive toolkit for URIBurner MCP Server enabling semantic data discovery, Knowledge Graph exploration, SPARQL/SQL query execution, RDF sponging, and database management. Use native MCP tools for queries; ChatPromptComplete only when user explicitly requests Gemini-powered analysis.

Technical support and database management for OpenLink Virtuoso Server with RDF Views generation, SPARQL queries, and comprehensive database operations. Provides assistance with installation, configuration, troubleshooting, RDF data management, SQL/SPARQL/GraphQL queries, automated RDF Views generation from relational database tables, entity discovery, and metadata management using 23 specialized MCP tools.

Execute mTLS (Mutual TLS) sessions using a PKCS#12 certificate bundle — either HTTP/HTTPS requests via curl (Mode A) or Virtuoso SQL sessions via iSQL with WebID authentication (Mode B). Interactively elicits the PKCS#12 file path, access password, CA bundle, and WebID URI when not already supplied. Use whenever the user wants to make an authenticated HTTP/HTTPS request using a client certificate, open a Virtuoso iSQL session with mTLS + WebID, test an mTLS-protected endpoint, or mentions PKCS#12, .p12, .pfx, mTLS, mutual TLS, iSQL, WebID, or -X/-T/-W flags.