Borrowing it
Nothing to install: this file belongs to datenoio/iterabledata. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/datenoio/iterabledata/main/.cursor/skills/ai-integration/SKILL.mdgit clone --depth 1 https://github.com/datenoio/iterabledataWrote 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/datenoio/iterabledata/ai-integration)<a href="https://agentmods.dev/skills/datenoio/iterabledata/ai-integration"><img src="https://agentmods.dev/badge/skills/datenoio/iterabledata/ai-integration/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/datenoio/iterabledata/ai-integration"><img src="https://agentmods.dev/badge/skills/datenoio/iterabledata/ai-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00034 | $0.00662 |
| Opus 5.5 | $0.00014 | $0.00265 |
| Sonnet 5.5 | $0.00007 | $0.00132 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
ai-integration 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Integration
Core APIs
from iterable.ai import doc
from iterable.ai.context import sample_for_llm, redact_for_llm
from iterable.catalog import describe_format, export_catalog, list_formats
from iterable.ops import inspect
Documentation generation
# Local provider (no API key)
doc.generate("data.csv", provider="lmstudio", base_url="http://localhost:1234/v1")
# With inspect
inspect.analyze("data.csv", autodoc=True, autodoc_provider="openai")
Install: pip install iterabledata[ai] or pip install -e ".[ai]".
Block-based documentation (generate_blocks)
from iterable.ai import doc
result = doc.generate_blocks(
"data.csv",
blocks=["general", "schema", "quality", "examples", "statistics"], # codebook also available
context={"title": "Population", "territory": "Russia"},
progress=lambda e: print(e.stage.value, e.progress),
)
result["blocks"]["schema"]["data"]["fields"] # structured data per block
result["full_document_markdown"] # assembled document
- Each block returns
{markdown, data};statisticsis computed (no LLM);lineage/geo_coverageare deferred stubs. - LLM blocks use structured output (
provider.generate_structured) with Pydantic models initerable.ai.models. - Sampling adapts to file size (
MAX_ROWS_SAMPLING); stats supportnull_fraction,top_values,is_dictionary(DICT_THRESHOLD). - Provider config via
LLM_PROVIDER/LLM_BASE_URL/LLM_API_KEY/LLM_DEFAULT_MODEL;provider="openai-compatible"targets any OpenAI-compatible endpoint. doc.generate(..., blocks=[...])delegates togenerate_blocks; withoutblocksthe legacy single-document path is unchanged.
Safe LLM sampling
Always sample and redact before cloud APIs:
rows = sample_for_llm("data.csv", max_rows=10, strategy="stratified")
safe = redact_for_llm(rows)
Format catalog for agents
describe_format("xml") # includes example_args, limitations, capabilities
export_catalog(format="json") # full catalog; committed at dev/formats.json
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.
- 1mo ago First seen · 81 lines · 34 tokens per session scan A cbe2c4f403d2
ai-integration is a skill published in the GitHub repository datenoio/iterabledata (37 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 662 once invoked, about $0.0001 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.
Other skills, from other repositories
fastapi
FastAPI best practices and conventions. Use when working with FastAPI APIs, Pydantic models, dependencies, streaming responses including Server-Sent Events (SSE), and serving frontend apps. Keeps FastAPI code clean and up to date with the latest features and patterns.
accelerate
Run PyTorch training across GPUs with minimal changes.
pytorch-patterns
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
optimize-for-gpu
GPU-accelerates scientific Python on NVIDIA hardware and verifies that the result is correct and faster. Use for CUDA/GPU optimization; CPU-bound NumPy, SciPy, pandas, scikit-learn, NetworkX, scikit-image, vector-search, image-processing, graph, simulation, or file-I/O workloads; CuPy, cuDF, cuML, cuGraph, cuVS…
developing-genkit-python
Develop AI-powered applications using Genkit in Python. Use when the user asks about Genkit, AI agents, flows, or tools in Python, or when encountering Genkit errors, import issues, or API problems.
marimo-pair
Work inside the user's live marimo notebook from the code editor: run Python in the same kernel the user does, inspect live notebook state, and commit durable notebook changes through code mode. Use whenever you create, analyze, or improve the user's marimo notebook.