agentsclimarketplace
Sign in

The catalog

325,949 rows, by stacks then stars

  • Run2 jackson inject bypass

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/fix-security-bug/run2_jackson-inject-bypass Skill

    75★ repo

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

  • Run2 gh issue analysis

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/github-repo-analytics/run2_gh-issue-analysis Skill

    75★ repo

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

  • Run2 gh pr analysis

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/github-repo-analytics/run2_gh-pr-analysis Skill

    75★ repo

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

  • Run2 gh search api

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/github-repo-analytics/run2_gh-search-api Skill

    75★ repo

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

  • Run2 report builder

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/github-repo-analytics/run2_report-builder Skill

    75★ repo

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

  • Run2 nlp paper reproduction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/nlp-paper-reproduction/run2_nlp-paper-reproduction 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-claude-sonnet-4-6/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 docx conditional sections

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/offer-letter-generator/run2_docx-conditional-sections Skill

    75★ repo

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

  • Run2 python docx placeholders

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/offer-letter-generator/run2_python-docx-placeholders Skill

    75★ repo

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

  • Run2 file classification improved

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/organize-messy-files/run2_file-classification-improved Skill

    75★ repo

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

  • Run2 pdf text extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/organize-messy-files/run2_pdf-text-extraction Skill

    75★ repo

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

  • Run2 pptx docx reading

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/organize-messy-files/run2_pptx-docx-reading Skill

    75★ repo

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

  • Run2 circe json

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/python-scala-translation/run2_circe-json Skill

    75★ repo

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

  • Run2 scala builder

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/python-scala-translation/run2_scala-builder Skill

    75★ repo

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

  • Run2 scala sealed traits

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/python-scala-translation/run2_scala-sealed-traits Skill

    75★ repo

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

  • Run2 scala type classes

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/python-scala-translation/run2_scala-type-classes Skill

    75★ repo

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

  • Run2 scala variance

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/python-scala-translation/run2_scala-variance Skill

    75★ repo

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

  • Run2 meeting scheduler with output

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/schedule-planning/run2_meeting-scheduler-with-output Skill

    75★ repo

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

  • Run2 pdf calendar parsing

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/schedule-planning/run2_pdf-calendar-parsing Skill

    75★ repo

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

  • Run2 timezone dst

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/schedule-planning/run2_timezone-dst Skill

    75★ repo

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

  • Run2 d3 bubble chart

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/stock-data-visualization/run2_d3-bubble-chart Skill

    75★ repo

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

  • Run2 d3 force cluster

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/stock-data-visualization/run2_d3-force-cluster Skill

    75★ repo

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

  • Run2 d3 interactive table

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/stock-data-visualization/run2_d3-interactive-table Skill

    75★ repo

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

  • Run2 glm calibration

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/temperature-simulation/run2_glm-calibration Skill

    75★ repo

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

  • Run2 glm netcdf analysis

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/temperature-simulation/run2_glm-netcdf-analysis Skill

    75★ repo

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

  • Run2 glm rmse metrics

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/temperature-simulation/run2_glm-rmse-metrics Skill

    75★ repo

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

  • 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.