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 exasol-labs/exasol-agent-skills --skill exasol-distributed-mlgit clone --depth 1 https://github.com/exasol-labs/exasol-agent-skillsWrote 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/exasol-labs/exasol-agent-skills/exasol-distributed-ml)<a href="https://agentmods.dev/skills/exasol-labs/exasol-agent-skills/exasol-distributed-ml"><img src="https://agentmods.dev/badge/skills/exasol-labs/exasol-agent-skills/exasol-distributed-ml/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/exasol-labs/exasol-agent-skills/exasol-distributed-ml"><img src="https://agentmods.dev/badge/skills/exasol-labs/exasol-agent-skills/exasol-distributed-ml.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00174 | $0.01088 |
| Opus 5.5 | $0.00070 | $0.00435 |
| Sonnet 5.5 | $0.00035 | $0.00218 |
| Haiku 4.5 | $0.00017 | $0.00109 |
Grade A, and why
exasol-distributed-ml 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exasol Distributed ML and HPC
Trigger when the user mentions: distributed ML, machine learning, train model, batch inference, prediction, feature engineering, hyperparameter, PyTorch, TensorFlow, scikit-learn, RAPIDS, GPU model, model deployment, distributed training, ensemble, anomaly detection, forecasting, clustering at scale, k-means, gradient descent, iterative algorithm, frequent itemset, association rules, market basket, Apriori, FP-Growth, data mining, SON algorithm, partial_fit, federated training, or any pattern where data is trained or scored inside Exasol.
Routing Algorithm
Choose the narrowest matching route. Load all routes that apply — they are designed to be read together.
Route 1 — Pipeline architecture, algorithms, and patterns
Trigger phrases: distributed training, end-to-end ML, feature engineering, batch inference, ensemble, k-means, gradient descent, frequent itemset, association rules, market basket, Apriori, FP-Growth, data mining, federated training, per-entity model, anomaly detection, forecasting, hyperparameter search, map-reduce
→ Load: references/distributed-ml-patterns.md
Route 2 — Model storage, versioning, and lifecycle
Trigger phrases: save model, ONNX, joblib, pickle, model versioning, load model in UDF, update model, latest.json, model registry, model path, BucketFS model
→ Load: references/model-lifecycle.md
Route 3 — GPU, CUDA, and RAPIDS
Trigger phrases: GPU UDF, CUDA SLC, PyTorch, TensorFlow, RAPIDS, cuDF, cuML, GPU acceleration, TorchScript, GPU cluster
→ Load: references/gpu-acceleration.md
Route 4 — Performance, tuning, and memory
Trigger phrases: slow UDF, OOM, out of memory, memory_limit, data skew in ML, profile SET script, chunking, group size, partial_fit convergence, ctx.reset, multi-pass, epoch loop
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.
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 Changed · +22 tokens per session a9339eb1d341
- 1mo ago First seen · 56 lines · 152 tokens per session scan A 455baac32bd5
exasol-distributed-ml is a skill published in the GitHub repository exasol-labs/exasol-agent-skills (10 stars, last pushed 12d ago), licensed MIT. It adds 174 tokens to every session and 1,088 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
using-datavault4dbt
Builds Data Vault 2 models in dbt with the datavault4dbt package — staging, hubs, links, satellites, and business-vault entities — using the YAML-metadata macro pattern with correct hashkeys, hashdiffs, naming, and materializations. Use when creating or editing datavault4dbt models, setting up a raw vault, choosing…
embeddings
Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching, simple lookups, no semantic understanding needed.
chief-ai-officer-advisor
Chief AI Officer advisory for startups: model build-vs-buy decisions (API vs fine-tune vs in-house), AI risk classification under EU AI Act + US state patchwork, AI cost economics (API-to-self-hosted breakeven), and AI team org evolution. Use when deciding whether to call an API or fine-tune, classifying AI use cases…
chief-data-officer-advisor
Chief Data Officer advisory for startups: AI training data rights and consent provenance, data product strategy (warehouse vs lakehouse vs mesh, build-vs-buy), B2B customer-data-as-asset valuation and M&A readiness, data team org evolution. Use when deciding whether to train models on customer data, choosing data…
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
postgres-hybrid-text-search
Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF). Trigger when user asks to: Combine keyword and semantic search Implement hybrid search or multi-modal retrieval Use BM25/pgtextsearch with pgvector together Implement RRF (Reciprocal…