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 skills add ibm-self-serve-assets/building-blocks --skill data-ingestion-unstructuredgit clone --depth 1 https://github.com/ibm-self-serve-assets/building-blocksWrote 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.
[](https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/data-ingestion-unstructured)<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/data-ingestion-unstructured"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/data-ingestion-unstructured/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.
<a href="https://agentmods.dev/skills/ibm-self-serve-assets/building-blocks/data-ingestion-unstructured"><img src="https://agentmods.dev/badge/skills/ibm-self-serve-assets/building-blocks/data-ingestion-unstructured.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Data Exfiltration · line 128 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00077 | $0.01094 |
| Opus 5 | $0.00039 | $0.00547 |
| Sonnet 5 | $0.00015 | $0.00219 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
data-ingestion-unstructured 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IBM Unstructured Data Ingestion Builder
Purpose
Expert guidance for building unstructured data ingestion pipelines using IBM UDI (Unstructured Data Ingestion) and IBM Docling — processing documents (PDF, DOCX, HTML, images) from IBM COS into IBM watsonx.data vector storage.
IBM Cloud Product Coverage
| IBM Cloud Product | Usage |
|---|---|
| IBM UDI (Unstructured Data Integration) | DataStage-based unstructured document processing |
| IBM watsonx.data | Target: Iceberg tables for metadata; Milvus/OpenSearch for vectors |
| IBM Cloud Object Storage | Source document storage |
| IBM watsonx.ai | Embedding generation for vectorised chunks |
| IBM Cloud IAM | POST /identity/token (apikey grant) |
Rules
- Use
doclingfor high-quality PDF/DOCX parsing (IBM's document AI library) - Use
unstructuredas fallback for broad format support (HTML, PPTX, email) - IBM UDI via DataStage: use
IBM.UDIconnector in DataStage job definition - Chunking:
RecursiveCharacterTextSplitter(chunk_size=512, chunk_overlap=128)for RAG - Always extract title, source path, page number, and chunk_seq as metadata
- COS download: always use
ibm-cos-sdkwith IAM OAuth (not HMAC) in Python
Scope
- IBM UDI DataStage connector configuration
- IBM Docling document parsing (PDF, DOCX, images)
- unstructured.io multi-format parsing (HTML, PPTX, email, Excel)
- OCR for scanned PDFs and image-based documents
- Chunking strategies: fixed-size, semantic, sentence-based
- Metadata extraction and enrichment
- IBM COS to watsonx.data pipeline patterns
Procedure
Phase 1: IBM Docling PDF Parsing
from docling.document_converter import DocumentConverter
converter = DocumentConverter()
result = converter.convert(cos_local_path)
doc = result.document
# Extract text preserving document structure
markdown_text = doc.export_to_markdown()
# or JSON structure
json_doc = doc.export_to_dict()
Phase 2: IBM COS Document Download
import ibm_boto3
from ibm_botocore.client import Config
cos = ibm_boto3.client("s3",
ibm_api_key_id=COS_API_KEY,
ibm_service_instance_id=COS_INSTANCE_CRN,
config=Config(signature_version="oauth"),
endpoint_url=COS_ENDPOINT,
)
cos.download_file(bucket, key, local_path)
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.
- 11d ago First seen · 130 lines · 77 tokens per session scan A 1c57ae719635
data-ingestion-unstructured is a skill published in the GitHub repository ibm-self-serve-assets/building-blocks (24 stars, last pushed yesterday), licensed Apache-2.0. It adds 77 tokens to every session and 1,094 once invoked, about $0.0004 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.
Other skills, from other repositories
markitdown
Convert heterogeneous documents and selected URIs to Markdown with Microsoft MarkItDown for text analysis, search, and LLM/RAG ingestion. Covers safe local conversion, streams, Office/PDF/data formats, batch workflows, plugins, vision OCR, Azure extraction, and the official MCP server.
paddleocr-text-recognition
An optical character recognition tool configuration for extracting text from images, photos, scans, screenshots, and scanned PDFs. OCR means converting text visible in an image into machine-readable text.
azure-ai-document-intelligence-ts
Extract text, tables, and structured data from documents using Azure Document Intelligence (@azure-rest/ai-document-intelligence). Use when processing invoices, receipts, IDs, forms, or building custom document models.
azure-ai
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
markitdown
Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.
ingest
Turn external URLs and documents into LLM-ready content — load + cache web pages (HQCC compression) and OCR PDFs/images to Markdown. Use whenever the user gives a URL, asks you to read a webpage, or attaches a PDF/scan that needs to be parsed before reasoning. Executes via the cloud load, cloud search, and cloud parse…