cxcscmu/SkillLearnBench

[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.

83Stars on the repository
200Mods indexed here, across every type
1mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

d3-interactive-table

145

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Build a sortable, highlightable HTML data table linked to a D3 chart so clicking a chart element highlights the matching table row and vice versa.

not rated 83 +1 1mo ago A 35 tokens original MIT

glm-lake-model

146

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Running the General Lake Model (GLM3) for lake temperature simulation, including configuration file structure and execution.

not rated 83 +1 1mo ago A 27 tokens original MIT

glm-netcdf-analysis

147

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Extracting and analyzing GLM NetCDF output to compute RMSE against field observations using exact datetime+depth matching.

not rated 83 +1 1mo ago A 28 tokens original MIT

itinerary-json-output

148

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

How to structure and write a valid travel itinerary JSON file matching the required schema for /app/output/itinerary.json.

not rated 83 +1 1mo ago A 29 tokens original MIT

travel-itinerary-data

149

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

How to query and filter travel itinerary datasets (restaurants, accommodations, attractions, distances) to build constraint-satisfying travel plans.

not rated 83 +1 1mo ago A 31 tokens original MIT

pillow-grayscale

150

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Convert images to grayscale in-place using Pillow (PIL), overwriting original RGB files.

not rated 83 +1 1mo ago A 23 tokens original MIT

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Editing Excel files with openpyxl to insert formulas while preserving all existing formatting, styles, colors, and structure.

not rated 83 +1 1mo ago A 30 tokens original MIT

excel-weighted-mean

152

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Calculating GDP-weighted means and other weighted statistics in Excel using SUMPRODUCT, including net exports as percent of GDP.

not rated 83 +1 1mo ago A 30 tokens original MIT

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Guidelines for applying Anthropic's visual identity and brand tokens in technical and marketing artifacts.

not rated 83 +1 1mo ago A 23 tokens original MIT

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Technical image generation using Python's Pillow library. Use this when you need to programmatically create diagrams, posters, or technical drawings.

not rated 83 +1 1mo ago A 31 tokens original MIT

mandarin-rhyme

155

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Rules for rhyming in poetry based on modern Mandarin (Pinyin).

not rated 83 +1 1mo ago A 21 tokens original MIT

qiyan-lvshi

156

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Rules for composing Chinese seven-character regulated verse (Qi Yan Lv Shi).

not rated 83 +1 1mo ago A 20 tokens original MIT

pdf-inspection

157

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Techniques for inspecting PDF form fields and their properties using Python libraries like pypdf.

not rated 83 +1 1mo ago A 22 tokens original MIT

custom-dbscan-metric

158

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Implementation of a custom distance metric for DBSCAN clustering using scipy and sklearn.

not rated 83 +1 1mo ago A 21 tokens original MIT

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Greedy matching algorithm to pair predicted cluster centroids with ground truth points for F1 and distance metrics.

not rated 83 +1 1mo ago A 28 tokens original MIT

pareto-frontier

160

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Identify Pareto-optimal points from a set of multi-objective solutions.

not rated 83 +1 1mo ago A 20 tokens original MIT

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Techniques for loading and initial processing of GeoJSON and coordinate-based datasets using GeoPandas.

not rated 83 +1 1mo ago A 24 tokens original MIT

spatial-filtering

163

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Methods for filtering GeoDataFrames based on spatial relationships like containment and intersection.

not rated 83 +1 1mo ago A 20 tokens original MIT

json-extraction

164

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Skill to extract information from the structured JSON data, including Slack messages and document metadata.

not rated 83 +1 1mo ago A 21 tokens original MIT

token-estimation

165

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Skill to estimate the number of consumed tokens for the task.

not rated 83 +1 1mo ago A 16 tokens original MIT

13f-comparison

166

cxcscmu/SkillLearnBench

Skill Claude CodeCodex needs its repo

Compare holdings between two quarters or find top holders of a specific stock.

not rated 83 +1 1mo ago A 19 tokens original MIT

13f-data-extraction

167

cxcscmu/SkillLearnBench

Skill Claude CodeCodex needs its repo

Extract AUM, holdings count, and detailed holding information for a specific fund.

not rated 83 +1 1mo ago A 22 tokens original MIT

13f-search

168

cxcscmu/SkillLearnBench

Skill Claude CodeCodex needs its repo

Search for fund accession numbers and stock CUSIPs using fuzzy matching.

not rated 83 +1 1mo ago A 18 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: