A Python toolkit for loading, cleaning, processing, and comparing well data and well logs. It works with individual wells and projects containing multiple wells.

Use it to load LAS files, inspect curves and metadata, remove spikes, smooth or normalize measurements, change sampling intervals, restrict depth ranges, and work across several wells.

It keeps depth, units, curve information, formation tops, and other well details together while making common cleanup and resampling tasks easier.

welly — Skill for Claude Code and Codex by SteadfastAsArt

Install

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.

Any agent

npx skills add SteadfastAsArt/geoscience-skills --skill welly

Clone the repo

git clone --depth 1 https://github.com/SteadfastAsArt/geoscience-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin welly — /plugin install welly after adding the marketplace above.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/welly/github.svg)](https://agentmods.dev/skills/steadfastasart/geoscience-skills/welly)

Your own site

<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/welly"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/welly/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/steadfastasart/geoscience-skills/welly"><img src="https://agentmods.dev/badge/skills/steadfastasart/geoscience-skills/welly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,319 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00114	$0.01319
Opus 5	$0.00057	$0.00660
Sonnet 5	$0.00023	$0.00264
Haiku 4.5	$0.00011	$0.00132

Measured 10d ago against content hash 93fd21a83600, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

welly 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/project_stats.py, scripts/well_qc.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

welly/SKILL.md · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.

welly - Well Data Analysis

Quick Reference

from welly import Well, Project

# Load single well
w = Well.from_las('well.las')

# Access data
df = w.df()                      # DataFrame
gr = w.data['GR']                # Curve object
values = gr.values               # numpy array
depth = gr.basis                 # depth array

# Well info
print(w.name, w.uwi)
print(w.data.keys())             # Available curves

# Load multiple wells
p = Project.from_las('wells/*.las')
for well in p:
    print(well.name)

Key Classes

Class	Purpose
`Well`	Single well with curves, location, tops
`Project`	Collection of wells for multi-well workflows
`Curve`	Log curve with depth basis, units, and processing methods

Essential Operations

Access Curve Data

gr = w.data['GR']
print(gr.mnemonic, gr.units)     # Metadata
print(gr.start, gr.stop, gr.step)  # Depth range

Process Curves

gr = w.data['GR']

# Clean and filter
gr_clean = gr.despike(window=5, z=2)
gr_smooth = gr.smooth(window=11)

# Transform
gr_norm = gr.normalize()         # 0-1 range
gr_resampled = gr.resample(step=0.5)
gr_clipped = gr.clip(top=1500, bottom=2000)

Work with Formation Tops

w.tops = {
    'TopFormationA': 1500.0,
    'TopFormationB': 1750.0,
}

for name, depth in w.tops.items():
    print(f"{name}: {depth} m")

Multi-Well Project

from welly import Project

p = Project.from_las('wells/*.las')
print(f"Loaded {len(p)} wells")

# Filter and analyze
for w in p:
    if 'GR' in w.data:
        print(f"{w.name}: GR mean={w.data['GR'].values.mean():.1f}")

Export Data

# To DataFrame
df = w.df()

# To LAS file
w.to_las('output.las')

# To CSV
df.to_csv('well_data.csv')

Common Curve Mnemonics

Mnemonic	Description	Units
GR	Gamma Ray	GAPI
NPHI	Neutron Porosity	v/v
RHOB	Bulk Density	g/cc
DT	Sonic	us/ft
RT/ILD	Deep Resistivity	ohm.m
CALI	Caliper	in

Read the full file on GitHub · 170 lines

Files

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.

Changes

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.

10d ago First seen · 170 lines · 114 tokens per session scan A 93fd21a83600

Subscribe to this mod's changes

welly is a skill published in the GitHub repository SteadfastAsArt/geoscience-skills (57 stars, last pushed 5mo ago), licensed MIT. It adds 114 tokens to every session and 1,319 once invoked, about $0.0006 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.

Claude Code Curve Processing Formation Tops LAS Languages Multi-Well Petrophysics Python Scientific Well Logs Welly ai-agents data-analysis geophysics geoscience

obspy-seismology

Seismological data analysis with ObsPy — FDSN waveform download, response removal, phase picking, moment tensor inversion, and seismicity mapping.

xjtulyc/awesome-rosetta-skills · 36 tokens

jupyter-notebook

Iterative Python via live Jupyter kernel (hamelnb).

NousResearch/hermes-agent · 18 tokens

matlab

Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.

K-Dense-AI/scientific-agent-skills · 42 tokens

pennylane

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with…

K-Dense-AI/scientific-agent-skills · 98 tokens

cuopt-numerical-optimization-api

LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.

NVIDIA/skills · 51 tokens

rocm-kernels

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…

huggingface/kernels · 93 tokens