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

jackson-security

169

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Security considerations for Jackson JSON deserialization, specifically regarding @JacksonInject and unintended property overrides.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Best practices for securing JavaScript execution in Java applications using ScriptEngines like Rhino or Nashorn.

not rated 83 +1 1mo ago B 25 tokens original MIT

gh-data-retrieval

171

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Retrieve pull request and issue data from GitHub repositories using the gh CLI with specific filters and JSON output for downstream processing.

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

jq-data-processing

172

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Process JSON data from GitHub CLI using jq to calculate metrics like average merge times, counts, and top contributors.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex needs its repo

Verifies model components like loss functions using unit tests and saves the results as NumPy archives.

not rated 83 +1 1mo ago A 25 tokens original MIT

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Manages NLP environments, handling library dependencies like PyTorch, Transformers, and custom local packages.

not rated 83 +1 1mo ago A 25 tokens original MIT

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Implements the Simple Preference Optimization (SimPO) loss function in PyTorch, focusing on length-normalized log probabilities and target reward margins.

not rated 83 +1 1mo ago A 34 tokens original MIT

batch-organizer

176

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Efficiently organizes large numbers of files into directories.

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

document-classifier

177

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Logic for categorizing documents into subjects based on keyword matching.

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

office-extraction

178

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Extracts text from DOCX and PPTX documents for content analysis.

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

pdf-extraction

179

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Extracts text from PDF documents for content analysis.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Mapping standard and common libraries from Python to Scala, including datetime, decimal, and JSON.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Extract text and identifying colored regions (e.g., rectangles) from a PDF using pdfplumber.

not rated 83 +1 1mo ago A 25 tokens original MIT

scheduling-engine

183

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Algorithm to find earliest available meeting slots given constraints and existing appointments.

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

d3-data-formatting

184

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Loading CSV data, formatting currency/large numbers, and implementing tooltips in D3.

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

d3-force-clustering

185

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Techniques for creating clustered bubble charts using D3 force simulations (v6).

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

glm-evaluator

186

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

A skill to process GLM NetCDF output and calculate specific RMSE metrics by merging with field observations.

not rated 83 +1 1mo ago A 25 tokens original MIT

glm-nml-edit

187

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

A skill to edit GLM's namelist file (glm3.nml) by safely updating parameter values within specific blocks.

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

glm-runner

188

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

A skill to execute the GLM binary and manage its simulation output.

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

data-processing

189

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Filter CSV data (restaurants, accommodations, attractions) based on criteria like city, cuisine, budget, and pet-friendliness.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Techniques for image preprocessing and template matching to count objects in images.

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

video-processing

192

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Tools and techniques for extracting keyframes and processing video files using FFmpeg.

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: