agentsclimarketplace
Sign in

The catalog

325,949 rows, by stacks then stars

  • Run2 convert images to grayscale inplace

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/video-object-counting/run2_convert-images-to-grayscale-inplace Skill

    75★ repo

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

  • Run2 count objects in frames

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/video-object-counting/run2_count-objects-in-frames Skill

    75★ repo

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

  • Run2 extract video keyframes

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/video-object-counting/run2_extract-video-keyframes Skill

    75★ repo

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

  • Run1 excel lookup two conditions

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/weighted-gdp-calculation/run1_excel-lookup-two-conditions Skill

    75★ repo

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

  • Run1 excel net exports percent gdp

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/weighted-gdp-calculation/run1_excel-net-exports-percent-gdp Skill

    75★ repo

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

  • Run1 excel workbook cross sheet reference

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/weighted-gdp-calculation/run1_excel-workbook-cross-sheet-reference Skill

    75★ repo

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

  • Run3 generate anthropic technical artifact

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/anthropic-poster-design/run3_generate_anthropic_technical_artifact Skill

    75★ repo

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

  • Run2 MandarinToneMapping

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/chinese-poem-generator/run2_MandarinToneMapping Skill

    75★ repo

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

  • Run2 SevenCharacterRegulatedVerseComposition

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/chinese-poem-generator/run2_SevenCharacterRegulatedVerseComposition Skill

    75★ repo

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

  • Run3 fill pdf form

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/court-form-filling/run3_fill_pdf_form Skill

    75★ repo

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

  • Run3 format claim description

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/court-form-filling/run3_format_claim_description Skill

    75★ repo

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

  • Run3 inspect pdf form

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/court-form-filling/run3_inspect_pdf_form Skill

    75★ repo

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

  • Run1 dbscan custom metric weighting

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/dbscan-parameter-tuning/run1_dbscan-custom-metric-weighting Skill

    75★ repo

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

  • Run1 greedy point matching evaluation

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/dbscan-parameter-tuning/run1_greedy-point-matching-evaluation Skill

    75★ repo

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

  • Run1 grid search parallelization

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/dbscan-parameter-tuning/run1_grid-search-parallelization Skill

    75★ repo

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

  • Run1 mars cloud data grouping

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/dbscan-parameter-tuning/run1_mars-cloud-data-grouping Skill

    75★ repo

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

  • Run1 pareto frontier identification

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/dbscan-parameter-tuning/run1_pareto-frontier-identification Skill

    75★ repo

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

  • Run1 csv security report generation

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/dependency-vulnerability-check/run1_csv-security-report-generation Skill

    75★ repo

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

  • Run1 npm audit security analysis

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/dependency-vulnerability-check/run1_npm-audit-security-analysis Skill

    75★ repo

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

  • Run1 vulnerability json parsing

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/dependency-vulnerability-check/run1_vulnerability-json-parsing Skill

    75★ repo

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

  • Run1 geopandas spatial filtering

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/earthquake-plate-calculation/run1_geopandas-spatial-filtering Skill

    75★ repo

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

  • Run1 geospatial metric projections

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/earthquake-plate-calculation/run1_geospatial-metric-projections Skill

    75★ repo

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

  • Run1 plate tectonics pb2002 parsing

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/earthquake-plate-calculation/run1_plate-tectonics-pb2002-parsing Skill

    75★ repo

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

  • Run1 spatial distance to boundary

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/earthquake-plate-calculation/run1_spatial-distance-to-boundary Skill

    75★ repo

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

  • Run1 enterprise data parsing

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/enterprise-information-search/run1_enterprise-data-parsing Skill

    75★ repo

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

  • Run1 formatted json answer generation

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/enterprise-information-search/run1_formatted-json-answer-generation Skill

    75★ repo

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

  • Run1 question file processing

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/enterprise-information-search/run1_question-file-processing Skill

    75★ repo

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

  • Run1 token usage tracking

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/enterprise-information-search/run1_token-usage-tracking Skill

    75★ repo

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

  • Run3 analyze fund holdings and aum

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/financial-analysis/run3_analyze_fund_holdings_and_aum Skill

    75★ repo

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

  • Run3 analyze stock ownership

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/financial-analysis/run3_analyze_stock_ownership Skill

    75★ repo

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

  • Run3 search fund accession number

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/financial-analysis/run3_search_fund_accession_number Skill

    75★ repo

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

  • Run3 search stock cusip

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/financial-analysis/run3_search_stock_cusip Skill

    75★ repo

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

  • Run3 druid jackson parameter mapping fix

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/fix-security-bug/run3_druid-jackson-parameter-mapping-fix Skill

    75★ repo

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

  • Run3 druid javascript vulnerability locator

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/fix-security-bug/run3_druid-javascript-vulnerability-locator Skill

    75★ repo

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

  • Run3 druid patch rebuild procedure

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/fix-security-bug/run3_druid-patch-rebuild-procedure Skill

    75★ repo

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

  • Run3 calculate github community metrics

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/github-repo-analytics/run3_calculate_github_community_metrics Skill

    75★ repo

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

  • Run3 github api paginated search

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/github-repo-analytics/run3_github_api_paginated_search Skill

    75★ repo

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

  • Run2 extract pdf content

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/nlp-paper-reproduction/run2_extract_pdf_content Skill

    75★ repo

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

  • Run2 implement simpo loss

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/nlp-paper-reproduction/run2_implement_simpo_loss Skill

    75★ repo

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

  • Run2 run unit test and save results

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/nlp-paper-reproduction/run2_run_unit_test_and_save_results Skill

    75★ repo

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

  • Run2 setup repo environment

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/nlp-paper-reproduction/run2_setup_repo_environment Skill

    75★ repo

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

  • Run2 docx custom conditional logic

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/offer-letter-generator/run2_docx_custom_conditional_logic Skill

    75★ repo

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

  • Run2 docx recursive text replacement

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/offer-letter-generator/run2_docx_recursive_text_replacement Skill

    75★ repo

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

  • Run3 batch file organization

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/organize-messy-files/run3_batch_file_organization Skill

    75★ repo

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

  • Run3 classify scientific document

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/organize-messy-files/run3_classify_scientific_document Skill

    75★ repo

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

  • Run3 extract office text with pandoc

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/organize-messy-files/run3_extract_office_text_with_pandoc Skill

    75★ repo

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

  • Run3 extract pdf text with poppler

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/organize-messy-files/run3_extract_pdf_text_with_poppler Skill

    75★ repo

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

  • Run3 scala 213 type hierarchy and modeling

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/python-scala-translation/run3_scala-213-type-hierarchy-and-modeling Skill

    75★ repo

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

  • Run3 scala fluent builder pattern

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/python-scala-translation/run3_scala-fluent-builder-pattern Skill

    75★ repo

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

  • Run3 scala functional parsing and error handling

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/python-scala-translation/run3_scala-functional-parsing-and-error-handling Skill

    75★ repo

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

  • Run3 analyze pdf calendar

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/schedule-planning/run3_analyze_pdf_calendar Skill

    75★ repo

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

  • Run3 extract meeting requests

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/schedule-planning/run3_extract_meeting_requests Skill

    75★ repo

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

  • Run3 generate formatted replies

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/schedule-planning/run3_generate_formatted_replies Skill

    75★ repo

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

  • Run3 schedule sequential slots

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/schedule-planning/run3_schedule_sequential_slots Skill

    75★ repo

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

  • Run3 GenerateD3VisualizationLogic

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/stock-data-visualization/run3_GenerateD3VisualizationLogic Skill

    75★ repo

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

  • Run3 GenerateStockVisualizerWebAssets

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/stock-data-visualization/run3_GenerateStockVisualizerWebAssets Skill

    75★ repo

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

  • Run3 SetupStockVisualizerWorkspace

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/stock-data-visualization/run3_SetupStockVisualizerWorkspace Skill

    75★ repo

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

  • Run3 glm config optimization

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/temperature-simulation/run3_glm-config-optimization Skill

    75★ repo

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

  • Run3 glm metric validator

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/temperature-simulation/run3_glm-metric-validator Skill

    75★ repo

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

  • Run3 glm output parser

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3-flash-preview/temperature-simulation/run3_glm-output-parser Skill

    75★ repo

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