Updated 1mo ago
by cxcscmu
SkillLearnBench
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
92 GitHub stars (92)
+9 in 30 days
| Period | New stars |
|---|---|
| Oct 1 | 0 |
| Oct 2 | 0 |
| Oct 3 | 0 |
| Oct 4 | 0 |
| Oct 5 | 0 |
| Oct 6 | 0 |
| Oct 7 | 0 |
| Oct 8 | 0 |
| Oct 9 | +2 |
| Oct 10 | 0 |
| Oct 11 | +1 |
| Oct 12 | +1 |
| Oct 13 | +1 |
| Oct 14 | 0 |
| Oct 15 | 0 |
| Oct 16 | 0 |
| Oct 17 | 0 |
| Oct 18 | 0 |
| Oct 19 | 0 |
| Oct 20 | 0 |
| Oct 21 | +3 |
| Oct 22 | 0 |
| Oct 23 | 0 |
| Oct 24 | 0 |
| Oct 25 | 0 |
| Oct 26 | 0 |
| Oct 27 | 0 |
| Oct 28 | 0 |
| Oct 29 | 0 |
| Oct 30 | 0 |
| Oct 31 | 0 |
| Nov 1 | 0 |
| Nov 2 | 0 |
| Nov 3 | 0 |
| Nov 4 | −1 |
| Nov 5 | +2 |
- 30 skills (30 skills found in its SKILL.md files)
- 7 forks (7 forks)
- 1mo ago last update (Last updated 1mo ago)
Install
Skills CLI
npx skills add cxcscmu/SkillLearnBench
Asks which skills and agents to install. Just one: npx skills add cxcscmu/SkillLearnBench --skill skill-creator — add -g for every project.
Claude Code
git clone https://github.com/cxcscmu/SkillLearnBenchcp -r "SkillLearnBench/baselines/b4-skill-creator/inject/skill-creator" ~/.claude/skills/
Copies the skill-creator skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add cxcscmu/SkillLearnBench
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md — showing the first 30 of 1278 files.
-
skill-creator
Create modular skill documents (SKILL.md files) for Claude Code. Use this skill whenever a task requires generating reusable knowledge documents, capturing domain expertise, or building skills that encode workflows, APIs, or specialized techniques. Invoke this whenever you need to write a SKILL.md from scratch, even if the user doesn't explicitly ask for a "skill".
baselines/b4-skill-creator/ on GitHub (opens in a new tab)inject/ skill-creator/ SKILL.md -
anthropic-brand-colors
Anthropic's official brand color palette, design tokens, and typography standards for consistent brand application.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)anthropic-poster-design/ anthropic-brand-colors/ SKILL.md -
python-pillow-graphics
Create technical graphics, diagrams, and posters using Python Pillow library with precise color control and typography.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)anthropic-poster-design/ python-pillow-graphics/ SKILL.md -
technical-illustration-design
Design principles and techniques for creating technical exploded-view diagrams and engineering documentation posters.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)anthropic-poster-design/ technical-illustration-design/ SKILL.md -
classical-poetry-peace-theme
Compose classical Chinese poetry on peace themes using authentic imagery, perspective shifts, and the voice of ordinary people experiencing war's aftermath.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)chinese-poem-generator/ classical-poetry-peace-theme/ SKILL.md -
mandarin-rhyming-guide
Master modern Mandarin pinyin finals and tone systems to create accurate rhymes for classical poetry following contemporary pronunciation standards.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)chinese-poem-generator/ mandarin-rhyming-guide/ SKILL.md -
seven-char-regulated-verse
Master the structure, tonal patterns, and rhyming requirements of classical seven-character regulated verse (七言律诗) in Chinese poetry.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)chinese-poem-generator/ seven-char-regulated-verse/ SKILL.md -
california-sc100-form
Understand the structure and fields of the California Small Claims Court Form SC-100
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)court-form-filling/ california-sc100-form/ SKILL.md -
pdf-form-filling
Fill PDF form fields programmatically using Python libraries like pypdf or pdfrw
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)court-form-filling/ pdf-form-filling/ SKILL.md -
dbscan-custom-metrics
Implement DBSCAN clustering with custom distance metrics using scikit-learn's pairwise_distances.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)dbscan-parameter-tuning/ dbscan-custom-metrics/ SKILL.md -
greedy-bipartite-matching
Implement greedy bipartite matching for pairing cluster centroids with expert annotations.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)dbscan-parameter-tuning/ greedy-bipartite-matching/ SKILL.md -
parallel-grid-search
Parallelize hyperparameter grid search using joblib for efficient multi-core execution.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)dbscan-parameter-tuning/ parallel-grid-search/ SKILL.md -
pareto-frontier-analysis
Identify Pareto-optimal solutions from multi-objective optimization results.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)dbscan-parameter-tuning/ pareto-frontier-analysis/ SKILL.md -
cvss-score-extraction
Extract and handle CVSS scores from multiple vulnerability data sources (NVD, GHSA, RedHat) with proper fallback priority.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)dependency-vulnerability-check/ cvss-score-extraction/ SKILL.md -
package-lock-parsing
Parse and extract package information from npm package-lock.json files to identify dependencies and their installed versions.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)dependency-vulnerability-check/ package-lock-parsing/ SKILL.md -
security-audit-csv-reporting
Generate structured CSV security audit reports from vulnerability data with proper filtering, formatting, and field mapping.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)dependency-vulnerability-check/ security-audit-csv-reporting/ SKILL.md -
trivy-vulnerability-scanning
Use Trivy vulnerability scanner in offline mode to detect CVEs in npm dependencies and generate structured JSON reports.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)dependency-vulnerability-check/ trivy-vulnerability-scanning/ SKILL.md -
geopandas-projections
Use GeoPandas with coordinate projections to perform accurate spatial calculations and transformations.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)earthquake-plate-calculation/ geopandas-projections/ SKILL.md -
plate-tectonics-geospatial
Analyze plate tectonics data using GeoPandas, identify points within plates, and calculate distances to boundaries.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)earthquake-plate-calculation/ plate-tectonics-geospatial/ SKILL.md -
usgs-earthquake-analysis
Load, parse, and process USGS earthquake data in GeoJSON or JSON formats.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)earthquake-plate-calculation/ usgs-earthquake-analysis/ SKILL.md -
enterprise-data-retrieval
Retrieve and aggregate information across multiple enterprise data sources
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)enterprise-information-search/ enterprise-data-retrieval/ SKILL.md -
json-data-extraction
Extract, parse, and query JSON data from large enterprise files efficiently
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)enterprise-information-search/ json-data-extraction/ SKILL.md -
json-result-formatting
Format query results to JSON with proper structure and token tracking
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)enterprise-information-search/ json-result-formatting/ SKILL.md -
fuzzy-fund-search
Fuzzy matching techniques for finding hedge funds by name when exact names are unknown
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)financial-analysis/ fuzzy-fund-search/ SKILL.md -
portfolio-analysis
Analyzing fund portfolios including AUM extraction, holdings counts, and portfolio composition
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)financial-analysis/ portfolio-analysis/ SKILL.md -
sec13f-data-format
Understanding SEC 13-F filing data structure, TSV format, and key tables for hedge fund analysis
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)financial-analysis/ sec13f-data-format/ SKILL.md -
druid-javascript-security
Securing Apache Druid's JavaScript execution engine against code injection and security bypass attacks.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)fix-security-bug/ druid-javascript-security/ SKILL.md -
git-patch-workflow
Creating, managing, and applying unified diff patches with Git for source code modifications.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)fix-security-bug/ git-patch-workflow/ SKILL.md -
jackson-deserialization-validation
Securing Jackson JSON deserialization by validating input before processing and preventing unknown properties.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)fix-security-bug/ jackson-deserialization-validation/ SKILL.md -
maven-druid-build
Building Apache Druid with Maven, managing memory constraints, and skipping verification checks.
skills/b1-one-shot-claude-haiku-4-5/ on GitHub (opens in a new tab)fix-security-bug/ maven-druid-build/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.