model-calibration

model-calibration is a skill for Claude Code, Codex from cxcscmu/SkillLearnBench. It costs 16 tokens per session (1,274 once invoked), scanned A, original, MIT.

A method for comparing lake-model simulations with observed measurements and adjusting model parameters. RMSE, or root mean squared error, summarizes how far simulated values are from real observations.

In plain words
What is it for?
Use it to calculate overall, deep-water, and summer deep-water temperature errors during lake-model validation.
Why use it?
It gives a consistent way to measure model accuracy and identify whether calibration improves the results.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to calculate overall, deep-water, and summer deep-water temperature errors during…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cxcscmu/skilllearnbench/model-calibration
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 cxcscmu/SkillLearnBench --skill model-calibration
Clone the repo
git clone --depth 1 https://github.com/cxcscmu/SkillLearnBench

Made for: Claude Code, Codex.

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.

agentmods badge for model-calibration

README.md
[![agentmods](https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/model-calibration.svg)](https://agentmods.dev/skills/cxcscmu/skilllearnbench/model-calibration)
Your own site
<a href="https://agentmods.dev/skills/cxcscmu/skilllearnbench/model-calibration"><img src="https://agentmods.dev/badge/skills/cxcscmu/skilllearnbench/model-calibration.svg" alt="Measured on agentmods" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,274 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.01274
Opus 5 $0.00008 $0.00637
Sonnet 5 $0.00003 $0.00255
Haiku 4.5 $0.00002 $0.00127

Measured 3d ago against content hash 3c900ee5a3ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

model-calibration 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 3d 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.

skills/b1-one-shot-claude-haiku-4-5/temperature-simulation/model-calibration/SKILL.md · 175 lines

How it starts

The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Calibration Skill

Overview

Model calibration involves adjusting parameters to minimize differences between simulations and observations. RMSE (Root Mean Squared Error) is a standard metric for measuring model performance.

RMSE Calculation

Basic Formula

RMSE = sqrt(mean((simulated - observed)^2))

Implementation

import numpy as np
import pandas as pd

def calculate_rmse(simulated, observed):
    """Calculate RMSE between matched pairs"""
    if len(simulated) == 0:
        return np.nan
    residuals = simulated - observed
    rmse = np.sqrt(np.mean(residuals**2))
    return rmse

def calculate_metrics(sim_temps, obs_temps, depths=None, dates=None):
    """
    Calculate multiple RMSE metrics

    Parameters:
    - sim_temps: matched simulated temperatures
    - obs_temps: matched observed temperatures
    - depths: depth of each match (for deep water filtering)
    - dates: datetime of each match (for seasonal filtering)

    Returns:
    - overall_rmse: RMSE of all matched pairs
    - annual_deep_rmse: RMSE of pairs at depths >= 13m
    - summer_deep_rmse: RMSE of summer (Jun-Sep) pairs at depths >= 13m
    """

    overall_rmse = calculate_rmse(sim_temps, obs_temps)

    # Annual deep water (depths >= 13m)
    if depths is not None:
        deep_mask = np.array(depths) >= 13
        annual_deep_rmse = calculate_rmse(
            sim_temps[deep_mask],
            obs_temps[deep_mask]
        )
    else:
        annual_deep_rmse = np.nan

    # Summer deep water (Jun-Sep, depths >= 13m)
    if dates is not None and depths is not None:
        summer_mask = (np.array([d.month for d in dates]) >= 6) & \
                     (np.array([d.month for d in dates]) <= 9)
        deep_mask = np.array(depths) >= 13
        combined_mask = summer_mask & deep_mask
        summer_deep_rmse = calculate_rmse(
            sim_temps[combined_mask],
            obs_temps[combined_mask]
        )
    else:
        summer_deep_rmse = np.nan

    return {
        'overall_rmse': overall_rmse,
        'annual_deep_rmse': annual_deep_rmse,
        'summer_deep_rmse': summer_deep_rmse
    }

Read the full file on GitHub · 175 lines

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.

  1. 3d ago First seen · 175 lines · 16 tokens per session scan A 3c900ee5a3ac

Subscribe to this mod's changes

model-calibration is a skill published in the GitHub repository cxcscmu/SkillLearnBench (83 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 1,274 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 2026-09-03.

Related

Other skills, from other repositories

rdkit

Cheminformatics toolkit for fine-grained molecular control. SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints, substructure search, 2D/3D generation, similarity, reactions. For standard workflows with simpler interface, use datamol (wrapper around RDKit). Use rdkit for advanced control, custom…

benchflow-ai/skillsbench · 80 tokens

logistics-rules-to-optimization

Translate logistics and operations rules into optimization variables and constraints. Use when an operations problem describes vehicles, routes, depots, pickups, dropoffs, inventory, capacity, assignments, time windows, service targets, penalties, resource limits, or other business rules that need to become an…

benchflow-ai/skillsbench · 66 tokens

mip-solver-and-solution-audit

Operational workflow for hard integer-programming optimization tasks: selecting an installed solver, preserving solver/incumbent certificates, extracting feasible schedules, recomputing metrics from final outputs, and writing consistent reports. Use when a task requires a MIP, solver status, objective value, bound…

benchflow-ai/skillsbench · 77 tokens

lab-unit-harmonization

Comprehensive clinical laboratory data harmonization for multi-source healthcare analytics. Convert between US conventional and SI units, standardize numeric formats, and clean data quality issues. This skill should be used when you need to harmonize lab values from different sources, convert units for clinical…

benchflow-ai/skillsbench · 82 tokens

routing-subtour-elimination

Subtour-elimination methods for TSP, VRP, pickup/dropoff routing, and routing MIPs with binary arc variables. Use when route-continuity constraints may permit disconnected cycles and the model needs MTZ constraints, flow-based connectivity constraints, DFJ subset cuts, or lazy/iterative subtour cuts.

benchflow-ai/skillsbench · 70 tokens

seisbench-model-api

An overview of the core model API of SeisBench, a Python framework for training and applying machine learning algorithms to seismic data. It is useful for annotating waveforms using pretrained SOTA ML models, for tasks like phase picking, earthquake detection, waveform denoising and depth estimation. For any waveform…

benchflow-ai/skillsbench · 88 tokens