agentsclimarketplace
Sign in

The catalog

616,489 rows, by stacks then stars

  • Run2 itinerary data exploration

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/travel-planning/run2_itinerary-data-exploration Skill

    75★ repo

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

  • Run2 itinerary planning

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/travel-planning/run2_itinerary-planning Skill

    75★ repo

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

  • Run2 ffmpeg keyframes

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/video-object-counting/run2_ffmpeg-keyframes Skill

    75★ repo

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

  • Run2 image grayscale

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/video-object-counting/run2_image-grayscale Skill

    75★ repo

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

  • Run2 object counting

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/video-object-counting/run2_object-counting Skill

    75★ repo

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

  • Run2 excel index match

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/weighted-gdp-calculation/run2_excel-index-match Skill

    75★ repo

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

  • Run2 excel sumproduct

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/weighted-gdp-calculation/run2_excel-sumproduct Skill

    75★ repo

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

  • Run2 openpyxl editing

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/weighted-gdp-calculation/run2_openpyxl-editing Skill

    75★ repo

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

  • Run2 advanced technical pillow

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/anthropic-poster-design/run2_advanced-technical-pillow Skill

    75★ repo

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

  • Run2 anthropic brand identity

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/anthropic-poster-design/run2_anthropic-brand-identity Skill

    75★ repo

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

  • Run2 classical poetry mastery

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/chinese-poem-generator/run2_classical-poetry-mastery Skill

    75★ repo

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

  • Run2 literary emotive writing

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/chinese-poem-generator/run2_literary-emotive-writing Skill

    75★ repo

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

  • Run2 mandarin rhyme comprehensive

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/chinese-poem-generator/run2_mandarin-rhyme-comprehensive Skill

    75★ repo

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

  • Run2 pdf field mapping

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/court-form-filling/run2_pdf-field-mapping Skill

    75★ repo

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

  • Run2 pdf form filling advanced

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/court-form-filling/run2_pdf-form-filling-advanced Skill

    75★ repo

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

  • Run2 advanced pareto

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/dbscan-parameter-tuning/run2_advanced-pareto Skill

    75★ repo

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

  • Run2 matching metrics

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/dbscan-parameter-tuning/run2_matching-metrics Skill

    75★ repo

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

  • Run2 optimized dbscan

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/dbscan-parameter-tuning/run2_optimized-dbscan Skill

    75★ repo

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

  • Run2 parallel orchestration

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/dbscan-parameter-tuning/run2_parallel-orchestration Skill

    75★ repo

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

  • Run2 csv reporting

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/dependency-vulnerability-check/run2_csv-reporting Skill

    75★ repo

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

  • Run2 trivy offline

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/dependency-vulnerability-check/run2_trivy-offline Skill

    75★ repo

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

  • Run2 vulnerability extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/dependency-vulnerability-check/run2_vulnerability-extraction Skill

    75★ repo

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

  • Run2 advanced projections

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/earthquake-plate-calculation/run2_advanced_projections Skill

    75★ repo

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

  • Run2 antimeridian handling

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/earthquake-plate-calculation/run2_antimeridian_handling Skill

    75★ repo

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

  • Run2 enterprise product data analysis

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/enterprise-information-search/run2_enterprise-product-data-analysis Skill

    75★ repo

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

  • Run2 user identity feedback extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/enterprise-information-search/run2_user-identity-feedback-extraction Skill

    75★ repo

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

  • Run2 fund analysis pro

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/financial-analysis/run2_fund-analysis-pro Skill

    75★ repo

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

  • Run2 fund search pro

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/financial-analysis/run2_fund-search-pro Skill

    75★ repo

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

  • Run2 stock analysis pro

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/financial-analysis/run2_stock-analysis-pro Skill

    75★ repo

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

  • Run2 druid build maven

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/fix-security-bug/run2_druid-build-maven Skill

    75★ repo

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

  • Run2 druid patching checklist

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/fix-security-bug/run2_druid-patching-checklist Skill

    75★ repo

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

  • Run2 jackson empty key vulnerability

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/fix-security-bug/run2_jackson-empty-key-vulnerability Skill

    75★ repo

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

  • Run2 gh api curl master

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/github-repo-analytics/run2_gh_api_curl_master Skill

    75★ repo

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

  • Run2 robust community metrics

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/github-repo-analytics/run2_robust_community_metrics Skill

    75★ repo

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

  • Run2 project alignment

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/nlp-paper-reproduction/run2_project_alignment Skill

    75★ repo

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

  • Run2 robust env

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/nlp-paper-reproduction/run2_robust_env Skill

    75★ repo

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

  • Run2 simpo loss

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/nlp-paper-reproduction/run2_simpo_loss Skill

    75★ repo

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

  • Run2 data mapping

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/offer-letter-generator/run2_data-mapping Skill

    75★ repo

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

  • Run2 docx expert

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/offer-letter-generator/run2_docx-expert Skill

    75★ repo

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

  • Run2 advanced subject classifier

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/organize-messy-files/run2_advanced_subject_classifier Skill

    75★ repo

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

  • Run2 file organization and validation

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/organize-messy-files/run2_file_organization_and_validation Skill

    75★ repo

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

  • Run2 robust text extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/organize-messy-files/run2_robust_text_extraction Skill

    75★ repo

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

  • Run2 scala datetime handling

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/python-scala-translation/run2_scala-datetime-handling Skill

    75★ repo

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

  • Run2 scala idiomatic fp

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/python-scala-translation/run2_scala-idiomatic-fp Skill

    75★ repo

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

  • Run2 scala json navigation

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/python-scala-translation/run2_scala-json-navigation Skill

    75★ repo

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

  • Run2 scala numeric precision

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/python-scala-translation/run2_scala-numeric-precision Skill

    75★ repo

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

  • Run2 scala text processing

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/python-scala-translation/run2_scala-text-processing Skill

    75★ repo

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

  • Run2 pdf parsing pro

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/schedule-planning/run2_pdf_parsing_pro Skill

    75★ repo

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

  • Run2 scheduling pro

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/schedule-planning/run2_scheduling_pro Skill

    75★ repo

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

  • Run2 d3 force clustering

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/stock-data-visualization/run2_d3-force-clustering Skill

    75★ repo

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

  • Run2 d3 interactive ui

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/stock-data-visualization/run2_d3-interactive-ui Skill

    75★ repo

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

  • Run2 stock data wrangling

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/stock-data-visualization/run2_stock-data-wrangling Skill

    75★ repo

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

  • Run2 glm config

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/temperature-simulation/run2_glm-config Skill

    75★ repo

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

  • Run2 glm evaluation

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/temperature-simulation/run2_glm-evaluation Skill

    75★ repo

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

  • Run2 advanced filtering

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/travel-planning/run2_advanced_filtering Skill

    75★ repo

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

  • Run2 budget validation

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/travel-planning/run2_budget_validation Skill

    75★ repo

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

  • Run2 itinerary logic

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/travel-planning/run2_itinerary_logic Skill

    75★ repo

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

  • Run2 ffmpeg extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/video-object-counting/run2_ffmpeg_extraction Skill

    75★ repo

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

  • Run2 image processing

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/video-object-counting/run2_image_processing Skill

    75★ repo

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

  • Run2 object counting optimized

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3-flash-preview/video-object-counting/run2_object_counting_optimized Skill

    75★ repo

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