agentsclimarketplace

Run3 update glm config

Skill cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/temperature-simulation/run3_update_glm_config

Safely updates specific calibration parameters in the glm3.nml file using f90nml, maintaining correct namelist group mapping and file integrity.From its SKILL.md

Install
npx -y skills add cxcscmu/SkillLearnBench --skill run3_update_glm_config

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.0 KB, 228 tokens by cl100k_base, as published. Nobody here has run it

To update the configuration, use the f90nml library to parse the existing file. Map the parameters to their respective namelist groups: Kw to &light, coef_mix_hyp to &mixing, and wind_factor, lw_factor, and ch to &meteorology.

import f90nml

def update_glm_parameters(params):
    nml = f90nml.read('/root/glm3.nml')
    # Map parameters to their correct namelist groups
    nml['light']['Kw'] = params.get('Kw')
    nml['mixing']['coef_mix_hyp'] = params.get('coef_mix_hyp')
    nml['meteorology']['wind_factor'] = params.get('wind_factor')
    nml['meteorology']['lw_factor'] = params.get('lw_factor')
    nml['meteorology']['ch'] = params.get('ch')
    
    # Write back without modifying unrelated sections
    nml.write('/root/glm3.nml', force=True)

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.