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

portfolio-analysis

25

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Analyzing fund portfolios including AUM extraction, holdings counts, and portfolio composition.

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

sec13f-data-format

26

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Understanding SEC 13-F filing data structure, TSV format, and key tables for hedge fund analysis.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Securing Apache Druid's JavaScript execution engine against code injection and security bypass attacks.

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

git-patch-workflow

28

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Creating, managing, and applying unified diff patches with Git for source code modifications.

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

maven-druid-build

30

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Building Apache Druid with Maven, managing memory constraints, and skipping verification checks.

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

github-cli-queries

31

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Query GitHub repositories for PRs and issues using gh CLI with date filtering and structured output.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Process GitHub API data to calculate PR/issue metrics including merge time averages, author rankings, and bug categorization.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Generate and write structured JSON reports with proper formatting and validation.

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

nlp-project-setup

35

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Set up Python environment for NLP and preference optimization projects.

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

simpo-loss-function

37

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Implement SimPO loss with length-normalized rewards and target margin.

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

python-docx

38

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Programmatically read, modify, and create Word documents (.docx) with python-docx library.

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

template-processing

39

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Process templates with placeholder substitution and conditional sections.

not rated 83 +1 1mo ago A 11 tokens original MIT

file-organization

43

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Organize files into target directories based on classification results.

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

pdf-text-extraction

44

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Extract text content from PDF files for analysis and classification.

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

scala-adt-enums

45

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Translating Python Enums and Protocols to Scala sealed traits and algebraic data types.

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

scala-circe-json

46

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Working with Circe JSON library in Scala for type-safe JSON processing.

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

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Scala collections, iterators, and functional programming patterns for Python developers.

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

scala-generics

48

cxcscmu/SkillLearnBench

Skill Claude CodeCodex

Translating Python generic types, variance, and type bounds to Scala 2.13.

not rated 83 +1 1mo ago A 22 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: