agentsclimarketplace
Sign in

The catalog

325,949 rows, by stacks then stars

  • Python pillow diagrams

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/anthropic-poster-design/python-pillow-diagrams Skill

    75★ repo

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

  • Chinese poetry qilv

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/chinese-poem-generator/chinese-poetry-qilv Skill

    75★ repo

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

  • Cli file writing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/chinese-poem-generator/cli-file-writing Skill

    75★ repo

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

  • Python pypdf

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/court-form-filling/python-pypdf Skill

    75★ repo

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

  • Custom distance metrics

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/dbscan-parameter-tuning/custom-distance-metrics Skill

    75★ repo

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

  • Parallel processing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/dbscan-parameter-tuning/parallel-processing Skill

    75★ repo

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

  • Pareto optimization

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/dbscan-parameter-tuning/pareto-optimization Skill

    75★ repo

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

  • Csv reporting

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/dependency-vulnerability-check/csv-reporting Skill

    75★ repo

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

  • Cvss extraction

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/dependency-vulnerability-check/cvss-extraction Skill

    75★ repo

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

  • Trivy offline scanning

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/dependency-vulnerability-check/trivy-offline-scanning Skill

    75★ repo

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

  • Geopandas distance calculation

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/earthquake-plate-calculation/geopandas-distance-calculation Skill

    75★ repo

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

  • Geopandas point in polygon

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/earthquake-plate-calculation/geopandas-point-in-polygon Skill

    75★ repo

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

  • Enterprise data retrieval

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/enterprise-information-search/enterprise-data-retrieval Skill

    75★ repo

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

  • Json data processing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/enterprise-information-search/json-data-processing Skill

    75★ repo

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

  • Python text search

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/enterprise-information-search/python-text-search Skill

    75★ repo

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

  • 13f data parsing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/financial-analysis/13f-data-parsing Skill

    75★ repo

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

  • Fuzzy string matching

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/financial-analysis/fuzzy-string-matching Skill

    75★ repo

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

  • Jackson druid cve

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/fix-security-bug/jackson-druid-cve Skill

    75★ repo

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

  • Github search api

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/github-repo-analytics/github-search-api Skill

    75★ repo

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

  • Json processing python

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/github-repo-analytics/json-processing-python Skill

    75★ repo

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

  • Huggingface trl

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/nlp-paper-reproduction/huggingface-trl Skill

    75★ repo

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

  • Simpo loss

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/nlp-paper-reproduction/simpo-loss Skill

    75★ repo

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

  • Python docx templating

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/offer-letter-generator/python-docx-templating Skill

    75★ repo

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

  • Document text extraction

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/organize-messy-files/document-text-extraction Skill

    75★ repo

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

  • Text classification heuristics

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/organize-messy-files/text-classification-heuristics Skill

    75★ repo

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

  • Scala circe json

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/python-scala-translation/scala-circe-json Skill

    75★ repo

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

  • Scala functional builders

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/python-scala-translation/scala-functional-builders Skill

    75★ repo

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

  • Scala generics variance

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/python-scala-translation/scala-generics-variance Skill

    75★ repo

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

  • Scala method overloading

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/python-scala-translation/scala-method-overloading Skill

    75★ repo

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

  • Pdf drawing extraction

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/schedule-planning/pdf-drawing-extraction Skill

    75★ repo

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

  • Schedule constraint parsing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/schedule-planning/schedule-constraint-parsing Skill

    75★ repo

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

  • D3 force bubble

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/stock-data-visualization/d3-force-bubble Skill

    75★ repo

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

  • D3 linked interactivity

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/stock-data-visualization/d3-linked-interactivity Skill

    75★ repo

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

  • Glm calibration

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/temperature-simulation/glm-calibration Skill

    75★ repo

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

  • Python pandas merge

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/temperature-simulation/python-pandas-merge Skill

    75★ repo

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

  • Python xarray netcdf

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/temperature-simulation/python-xarray-netcdf Skill

    75★ repo

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

  • Data analysis

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/travel-planning/data-analysis Skill

    75★ repo

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

  • Route planning

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/travel-planning/route-planning Skill

    75★ repo

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

  • Image grayscale

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/video-object-counting/image-grayscale Skill

    75★ repo

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

  • Opencv template matching

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/video-object-counting/opencv-template-matching Skill

    75★ repo

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

  • Video keyframe extraction

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/video-object-counting/video-keyframe-extraction Skill

    75★ repo

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

  • Python openpyxl

    cxcscmu/SkillLearnBench/skills/b1-one-shot-gemini-3.1-pro-preview/weighted-gdp-calculation/python-openpyxl Skill

    75★ repo

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

  • Run2 advanced pil techniques

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/anthropic-poster-design/run2_advanced-pil-techniques Skill

    75★ repo

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

  • Run2 brand color strategy

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/anthropic-poster-design/run2_brand-color-strategy Skill

    75★ repo

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

  • Run2 professional technical layout

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/anthropic-poster-design/run2_professional-technical-layout Skill

    75★ repo

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

  • Run2 composition technique

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/chinese-poem-generator/run2_composition-technique Skill

    75★ repo

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

  • Run2 tonal patterns

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/chinese-poem-generator/run2_tonal-patterns Skill

    75★ repo

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

  • Run2 verification checklist

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/chinese-poem-generator/run2_verification-checklist Skill

    75★ repo

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

  • Run2 pdf skill form filling

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/court-form-filling/run2_pdf-skill-form-filling Skill

    75★ repo

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

  • Run2 sc100 form mapping

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/court-form-filling/run2_sc100-form-mapping Skill

    75★ repo

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

  • Run2 clustering metrics

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/dbscan-parameter-tuning/run2_clustering_metrics Skill

    75★ repo

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

  • Run2 custom distance metrics

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/dbscan-parameter-tuning/run2_custom_distance_metrics Skill

    75★ repo

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

  • Run2 greedy matching

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/dbscan-parameter-tuning/run2_greedy_matching Skill

    75★ repo

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

  • Run2 parallel grid search

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/dbscan-parameter-tuning/run2_parallel_grid_search Skill

    75★ repo

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

  • Run2 pareto frontier

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/dbscan-parameter-tuning/run2_pareto_frontier Skill

    75★ repo

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

  • Run2 csv report generation advanced

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/dependency-vulnerability-check/run2_csv-report-generation-advanced Skill

    75★ repo

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

  • Run2 cvss scoring strategy

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/dependency-vulnerability-check/run2_cvss-scoring-strategy Skill

    75★ repo

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

  • Run2 npm vulnerability scanning enhanced

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/dependency-vulnerability-check/run2_npm-vulnerability-scanning-enhanced Skill

    75★ repo

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

  • Run2 multipart geometry handling

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_multipart-geometry-handling Skill

    75★ repo

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

  • Run2 optimal projection selection

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_optimal-projection-selection Skill

    75★ repo

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