agentsclimarketplace
Sign in

The catalog

616,489 rows, by stacks then stars

  • Run2 d3 force bubble

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/stock-data-visualization/run2_d3-force-bubble 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-opus-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 strategy

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

    75★ repo

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

  • Run2 glm lake modeling

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/temperature-simulation/run2_glm-lake-modeling Skill

    75★ repo

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

  • Run2 netcdf obs matching

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/temperature-simulation/run2_netcdf-obs-matching 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-claude-opus-4-6/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 planning

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-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 travel data extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/travel-planning/run2_travel-data-extraction 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-opus-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 opencv grayscale

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/video-object-counting/run2_opencv-grayscale Skill

    75★ repo

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

  • Run2 template matching tuning

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-opus-4-6/video-object-counting/run2_template-matching-tuning 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-opus-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 weighted mean

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

    75★ repo

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

  • Run2 anthropic brand tokens

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

    75★ repo

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

  • Run2 exploded view drawing

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

    75★ repo

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

  • Run2 matplotlib technical poster

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/anthropic-poster-design/run2_matplotlib-technical-poster Skill

    75★ repo

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

  • Run2 chinese poetry composition

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/chinese-poem-generator/run2_chinese-poetry-composition Skill

    75★ repo

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

  • Run2 qiyan lushi

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/chinese-poem-generator/run2_qiyan-lushi Skill

    75★ repo

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

  • Run2 sc100 small claims form

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/court-form-filling/run2_sc100-small-claims-form Skill

    75★ repo

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

  • Run2 dbscan clustering

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/dbscan-parameter-tuning/run2_dbscan-clustering 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-sonnet-4-6/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 pareto frontier

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/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 cvss score extraction

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/dependency-vulnerability-check/run2_cvss-score-extraction Skill

    75★ repo

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

  • Run2 trivy offline scanning

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/dependency-vulnerability-check/run2_trivy-offline-scanning Skill

    75★ repo

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

  • Run2 vulnerability csv reporting

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/dependency-vulnerability-check/run2_vulnerability-csv-reporting Skill

    75★ repo

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

  • Run2 earthquake analysis

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/earthquake-plate-calculation/run2_earthquake-analysis Skill

    75★ repo

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

  • Run2 geopandas plate tectonics

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/earthquake-plate-calculation/run2_geopandas-plate-tectonics Skill

    75★ repo

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

  • Run2 competitor analysis

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/enterprise-information-search/run2_competitor-analysis Skill

    75★ repo

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

  • Run2 enterprise data retrieval

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/enterprise-information-search/run2_enterprise-data-retrieval Skill

    75★ repo

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

  • Run2 13f fund analysis

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/financial-analysis/run2_13f-fund-analysis Skill

    75★ repo

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

  • Run2 fuzzy fund search

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/financial-analysis/run2_fuzzy-fund-search Skill

    75★ repo

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

  • Run2 holdings comparison

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/financial-analysis/run2_holdings-comparison Skill

    75★ repo

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

  • Run2 palantir holders

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/financial-analysis/run2_palantir-holders Skill

    75★ repo

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

  • Run2 druid cve 2021 25646

    cxcscmu/SkillLearnBench/skills/b2-self-feedback-claude-sonnet-4-6/fix-security-bug/run2_druid-cve-2021-25646 Skill

    75★ repo

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

  • 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.