agentsclimarketplace
Sign in

The catalog

325,949 rows, by stacks then stars

  • Run2 spatial analysis validation

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_spatial-analysis-validation Skill

    75★ repo

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

  • Run2 advanced slack mining

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/enterprise-information-search/run2_advanced-slack-mining Skill

    75★ repo

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

  • Run2 document metadata extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/enterprise-information-search/run2_document-metadata-extraction Skill

    75★ repo

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

  • Run2 multi source data correlation

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/enterprise-information-search/run2_multi-source-data-correlation Skill

    75★ repo

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

  • Run2 cross fund analysis

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/financial-analysis/run2_cross_fund_analysis Skill

    75★ repo

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

  • Run2 fund analysis

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/financial-analysis/run2_fund_analysis Skill

    75★ repo

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

  • Run2 quarter comparison

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/financial-analysis/run2_quarter_comparison Skill

    75★ repo

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

  • Run2 sec13f data loader

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/financial-analysis/run2_sec13f_data_loader Skill

    75★ repo

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

  • Run2 druid javascript deserialization security

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/fix-security-bug/run2_druid-javascript-deserialization-security Skill

    75★ repo

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

  • Run2 jackson security patching

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/fix-security-bug/run2_jackson-security-patching Skill

    75★ repo

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

  • Run2 maven security build

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/fix-security-bug/run2_maven-security-build Skill

    75★ repo

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

  • Run2 data aggregation

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/github-repo-analytics/run2_data-aggregation Skill

    75★ repo

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

  • Run2 github rest api

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/github-repo-analytics/run2_github-rest-api Skill

    75★ repo

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

  • Run2 json validation

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/github-repo-analytics/run2_json-validation Skill

    75★ repo

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

  • Run2 simpo loss detailed implementation

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/nlp-paper-reproduction/run2_simpo-loss-detailed-implementation Skill

    75★ repo

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

  • Run2 simpo testing and verification

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/nlp-paper-reproduction/run2_simpo-testing-and-verification Skill

    75★ repo

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

  • Run2 simpo trainer initialization

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/nlp-paper-reproduction/run2_simpo-trainer-initialization Skill

    75★ repo

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

  • Run2 placeholder replacement

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/offer-letter-generator/run2_placeholder-replacement Skill

    75★ repo

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

  • Run2 python docx basics

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/offer-letter-generator/run2_python-docx-basics Skill

    75★ repo

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

  • Run2 content classification enhanced

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/organize-messy-files/run2_content-classification-enhanced Skill

    75★ repo

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

  • Run2 file organization robust

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/organize-messy-files/run2_file-organization-robust Skill

    75★ repo

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

  • Run2 multi format extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/organize-messy-files/run2_multi-format-extraction Skill

    75★ repo

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

  • Run2 pdf extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/organize-messy-files/run2_pdf-extraction Skill

    75★ repo

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

  • Run2 scala immutable builder

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/python-scala-translation/run2_scala-immutable-builder Skill

    75★ repo

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

  • Run2 scala java time handling

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/python-scala-translation/run2_scala-java-time-handling Skill

    75★ repo

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

  • Run2 scala pattern matching dispatch

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/python-scala-translation/run2_scala-pattern-matching-dispatch Skill

    75★ repo

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

  • Run2 scala string processing

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/python-scala-translation/run2_scala-string-processing Skill

    75★ repo

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

  • Run2 pdf visual extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/schedule-planning/run2_pdf-visual-extraction Skill

    75★ repo

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

  • Run2 request parsing advanced

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/schedule-planning/run2_request-parsing-advanced Skill

    75★ repo

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

  • Run2 time formatting

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/schedule-planning/run2_time-formatting Skill

    75★ repo

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

  • Run2 csv robust loading

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/stock-data-visualization/run2_csv_robust_loading Skill

    75★ repo

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

  • Run2 d3 bubble clusters

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/stock-data-visualization/run2_d3_bubble_clusters Skill

    75★ repo

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

  • Run2 d3 sync interaction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/stock-data-visualization/run2_d3_sync_interaction Skill

    75★ repo

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

  • Run2 market cap formatting

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/stock-data-visualization/run2_market_cap_formatting Skill

    75★ repo

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

  • Run2 glm error diagnosis

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/temperature-simulation/run2_glm-error-diagnosis Skill

    75★ repo

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

  • Run2 netcdf glm matching

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/temperature-simulation/run2_netcdf-glm-matching Skill

    75★ repo

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

  • Run2 nml calibration workflow

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/temperature-simulation/run2_nml-calibration-workflow Skill

    75★ repo

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

  • Run2 parameter optimization strategy

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/temperature-simulation/run2_parameter-optimization-strategy Skill

    75★ repo

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

  • Run2 complete itinerary solution

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/travel-planning/run2_complete_itinerary_solution Skill

    75★ repo

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

  • Run2 data filtering validation

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/travel-planning/run2_data_filtering_validation Skill

    75★ repo

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

  • Run2 itinerary optimization

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/travel-planning/run2_itinerary_optimization Skill

    75★ repo

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

  • Run2 advanced template matching

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/video-object-counting/run2_advanced_template_matching Skill

    75★ repo

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

  • Run2 csv validation export

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/video-object-counting/run2_csv_validation_export Skill

    75★ repo

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

  • Run2 ffmpeg robust extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/video-object-counting/run2_ffmpeg_robust_extraction Skill

    75★ repo

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

  • Run2 image processing verification

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/video-object-counting/run2_image_processing_verification Skill

    75★ repo

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

  • Run2 excel percentages

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/weighted-gdp-calculation/run2_excel-percentages Skill

    75★ repo

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

  • Run2 excel statistics aggregates

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/weighted-gdp-calculation/run2_excel-statistics-aggregates Skill

    75★ repo

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

  • Run2 multi condition lookups

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/weighted-gdp-calculation/run2_multi-condition-lookups Skill

    75★ repo

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

  • Run2 openpyxl cross sheet

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-haiku-4-5/weighted-gdp-calculation/run2_openpyxl-cross-sheet Skill

    75★ repo

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

  • Run2 anthropic brand

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/anthropic-poster-design/run2_anthropic-brand Skill

    75★ repo

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

  • Run2 exploded view layout

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/anthropic-poster-design/run2_exploded-view-layout Skill

    75★ repo

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

  • Run2 pillow technical poster

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/anthropic-poster-design/run2_pillow-technical-poster Skill

    75★ repo

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

  • Run2 mandarin rhyming

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/chinese-poem-generator/run2_mandarin-rhyming Skill

    75★ repo

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

  • Run2 peace poem composition

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/chinese-poem-generator/run2_peace-poem-composition Skill

    75★ repo

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

  • Run2 seven char regulated verse

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/chinese-poem-generator/run2_seven-char-regulated-verse Skill

    75★ repo

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

  • Run2 ca small claims

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/court-form-filling/run2_ca-small-claims Skill

    75★ repo

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

  • Run2 pdf form filling

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/court-form-filling/run2_pdf-form-filling Skill

    75★ repo

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

  • Run2 dbscan custom metric

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/dbscan-parameter-tuning/run2_dbscan-custom-metric 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-opus-4-6/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 optimization

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/dbscan-parameter-tuning/run2_pareto-optimization Skill

    75★ repo

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