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

scala-option-either

49

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Translating Python's None/Optional to Scala's Option, Either, and Try types.

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

datetime-formatting

51

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Format dates and times according to specific requirements for meeting confirmations.

not rated 83 +1 1mo ago A 15 tokens original MIT

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Parse meeting request emails from JSON format and extract duration and time constraints.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Extract calendar events, blocks, and time slots from PDF calendar files using pdfplumber.

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

csv-data-handling

54

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Loading and parsing CSV files with D3.js, data transformation, and handling missing values.

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

d3-force-simulation

55

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

D3.js force simulation for creating interactive bubble charts with clustering, collision detection, and physics-based positioning.

not rated 83 +1 1mo ago A 26 tokens original MIT

d3-fundamentals

56

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Essential D3.js v6 concepts including selections, scales, SVG basics, and data binding for building interactive visualizations.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

D3.js techniques for tooltips, hover effects, click handlers, and cross-filtering between visualizations.

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

data-matching

58

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Matching observation data to simulation output with exact datetime and depth binning.

not rated 83 +1 1mo ago A 17 tokens original MIT

fortran-namelist

59

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Reading and modifying Fortran namelist configuration files for scientific models.

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

glm-simulation

60

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Running the General Lake Model (GLM) with configuration files and parameter calibration.

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

model-calibration

61

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Calculating RMSE metrics and parameter calibration for lake model validation.

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

netcdf-processing

62

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Reading, processing, and analyzing NetCDF output from lake simulation models.

not rated 83 +1 1mo ago A 17 tokens original MIT

budget-management

63

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Track and manage travel budget across accommodations, meals, and activities.

not rated 83 +1 1mo ago A 15 tokens original MIT

data-filtering

64

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Filter accommodations, restaurants, and attractions by travel requirements.

not rated 83 +1 1mo ago A 14 tokens original MIT

data-loading

65

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Load and parse CSV/TXT files from travel database for itinerary planning.

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

route-planning

66

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Plan multi-city road trip routes using distance matrices and constraints.

not rated 83 +1 1mo ago A 15 tokens original MIT

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Extract key frames (I-frames) from video files using FFmpeg to identify scene changes and important moments.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Use OpenCV for image processing, grayscale conversion, and template matching to detect objects in images.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Generate structured CSV files from Python data using the csv module for tabular data export.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Master Excel lookup functions (VLOOKUP, HLOOKUP, INDEX/MATCH, XLOOKUP) for single and multiple criteria.

not rated 83 +1 1mo ago A 32 tokens original MIT

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Use Excel statistical functions for descriptive analysis including percentiles, weighted calculations, and data summaries.

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

excel-xlsx-skill

72

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Use the xlsx skill tool to create, read, modify and analyze Excel spreadsheets with formulas and formatting.

not rated 83 +1 1mo ago A 27 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: