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 MEKXH/golem --skill data-pipelinegit clone --depth 1 https://github.com/MEKXH/golemWrote 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/mekxh/golem/data-pipeline)<a href="https://agentmods.dev/skills/mekxh/golem/data-pipeline"><img src="https://agentmods.dev/badge/skills/mekxh/golem/data-pipeline.svg" alt="Measured on agentmods" 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 | $0.00022 | $0.00353 |
| Opus 5 | $0.00011 | $0.00177 |
| Sonnet 5 | $0.00004 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
data-pipeline 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.
What it actually says
Data Pipeline Workflow
Use this skill for geospatial ETL tasks: ingest, normalize, convert, reproject, and prepare datasets for analysis.
Step 1: Discover and Inspect Inputs
Start by locating candidate datasets with geo_data_catalog, then inspect them with geo_info and geo_crs_detect.
Step 2: Reuse Learned Pipelines First
Before composing a new ETL flow, inspect whether pipelines/geo/ already contains a similar learned sequence for the same transformation goal.
Step 3: Normalize CRS and Format
Use geo_process when the workflow needs reprojection, clipping, or batch GDAL/OGR steps.
Use geo_format_convert for direct format changes.
Step 4: Reuse Verified SQL Patterns First
When the pipeline targets PostGIS, inspect the codebook before composing custom SQL:
geo_sql_codebook(action="list", intent="<pipeline validation goal>")
geo_sql_codebook(action="render", pattern="<pattern_name>", values={...})
geo_spatial_query(action="schema")
geo_spatial_query(action="query", sql="SELECT ...")
Step 5: Fabricate a Reusable Pipeline Tool
If the ETL step is repetitive and not covered by learned pipelines or built-in geo tools, fabricate a persistent workspace tool under tools/geo/.
Conventions
- Prefer learned pipelines before inventing a fresh ETL sequence.
- Prefer GeoPackage for intermediate vector outputs.
- Prefer GeoTIFF for intermediate raster outputs.
- Keep intermediate and final outputs inside the workspace.
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.
- 8d ago First seen · 38 lines · 22 tokens per session scan A 1e52e245d7fd
data-pipeline is a skill published in the GitHub repository MEKXH/golem (199 stars, last pushed 2mo ago), licensed MIT. It adds 22 tokens to every session and 353 once invoked, about $0.0001 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
torchdrug
Build and troubleshoot TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation, retrosynthesis, protein representation learning, and knowledge graph reasoning. Use when code imports torchdrug or needs its datasets, models, tasks, or Engine.
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for…
pyhealth
Build clinical/healthcare deep-learning pipelines with PyHealth — loading EHR/signal/imaging datasets (MIMIC-III/IV, eICU, OMOP, SleepEDF, ChestXray14, EHRShot), defining tasks (mortality, readmission, length-of-stay, drug recommendation, sleep staging, ICD coding, EEG events), instantiating models (Transformer…
deepspot-m
Generate transcriptome-wide virtual spatial transcriptomics from H&E histology with DeepSpot-M. Use when you need spatial gene expression in log1p-CPM for 224x224 tiles at about 20x, want to query protein-coding genes by symbol instead of a fixed panel, or want to run prediction across a whole slide after tiling with…
pick-a-pii-model
Select an on-device OpenMed PII model from the committed registry by language, runtime format, and size budget, then require recall validation before deployment. Use when an agent must choose a local PII detector for CPU, Apple Silicon, or a mobile export without relying on live model discovery.
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…