agentsclimarketplace
Sign in

The catalog

616,489 rows, by stacks then stars

  • Run3 Weighted Mean Calculation with SUMPRODUCT

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/weighted-gdp-calculation/run3_Weighted-Mean-Calculation-with-SUMPRODUCT Skill

    75★ repo

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

  • Run2 anthropic brand colors

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/anthropic-poster-design/run2_anthropic-brand-colors Skill

    75★ repo

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

  • Run2 anthropic brand typography

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/anthropic-poster-design/run2_anthropic-brand-typography Skill

    75★ repo

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

  • Run2 technical exploded view poster

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/anthropic-poster-design/run2_technical-exploded-view-poster Skill

    75★ repo

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

  • Run2 seven character regulated verse structure and rhyme

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/chinese-poem-generator/run2_seven-character-regulated-verse-structure-and-rhyme Skill

    75★ repo

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

  • Run2 seven character regulated verse tonal patterns

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/chinese-poem-generator/run2_seven-character-regulated-verse-tonal-patterns Skill

    75★ repo

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

  • Run1 california sc100 form fields

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/court-form-filling/run1_california-sc100-form-fields Skill

    75★ repo

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

  • Run1 python pdf form filling

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/court-form-filling/run1_python-pdf-form-filling Skill

    75★ repo

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

  • Run1 sc100 case data extraction

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/court-form-filling/run1_sc100-case-data-extraction Skill

    75★ repo

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

  • Run1 dbscan custom metric

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/dbscan-parameter-tuning/run1_dbscan-custom-metric Skill

    75★ repo

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

  • Run1 greedy centroid matching

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/dbscan-parameter-tuning/run1_greedy-centroid-matching Skill

    75★ repo

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

  • Run1 parallel grid search python

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/dbscan-parameter-tuning/run1_parallel-grid-search-python Skill

    75★ repo

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

  • Run1 pareto frontier extraction

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/dbscan-parameter-tuning/run1_pareto-frontier-extraction Skill

    75★ repo

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

  • Run1 grype trivy offline vulnerability scanning

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/dependency-vulnerability-check/run1_grype-trivy-offline-vulnerability-scanning Skill

    75★ repo

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

  • Run1 npm dependency audit

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/dependency-vulnerability-check/run1_npm-dependency-audit Skill

    75★ repo

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

  • Run1 package lock json parsing

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/dependency-vulnerability-check/run1_package-lock-json-parsing Skill

    75★ repo

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

  • Run1 vulnerability csv report generation

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/dependency-vulnerability-check/run1_vulnerability-csv-report-generation Skill

    75★ repo

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

  • Run2 earthquake time conversion

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/earthquake-plate-calculation/run2_earthquake-time-conversion Skill

    75★ repo

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

  • Run2 geospatial projection selection

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/earthquake-plate-calculation/run2_geospatial-projection-selection Skill

    75★ repo

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

  • Run2 pacific plate earthquake analysis

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/earthquake-plate-calculation/run2_pacific-plate-earthquake-analysis Skill

    75★ repo

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

  • Run3 enterprise data retrieval

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/enterprise-information-search/run3_enterprise-data-retrieval Skill

    75★ repo

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

  • Run3 sec 13f compare holdings q2 q3

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/financial-analysis/run3_sec-13f-compare-holdings-q2-q3 Skill

    75★ repo

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

  • Run3 sec 13f dataset structure

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/financial-analysis/run3_sec-13f-dataset-structure Skill

    75★ repo

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

  • Run3 sec 13f fund analysis aum stocks

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/financial-analysis/run3_sec-13f-fund-analysis-aum-stocks Skill

    75★ repo

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

  • Run3 sec 13f search fund coverpage

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/financial-analysis/run3_sec-13f-search-fund-coverpage Skill

    75★ repo

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

  • Run3 apache druid javascript rce patch creation

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/fix-security-bug/run3_apache-druid-javascript-rce-patch-creation Skill

    75★ repo

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

  • Run3 apache druid javascript rce vulnerability analysis

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/fix-security-bug/run3_apache-druid-javascript-rce-vulnerability-analysis Skill

    75★ repo

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

  • Run3 compile community pulse report json

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/github-repo-analytics/run3_compile-community-pulse-report-json Skill

    75★ repo

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

  • Run3 gh search issues exclude prs

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/github-repo-analytics/run3_gh-search-issues-exclude-prs Skill

    75★ repo

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

  • Run3 gh search prs precise

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/github-repo-analytics/run3_gh-search-prs-precise Skill

    75★ repo

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

  • Run3 simpo environment setup

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/nlp-paper-reproduction/run3_simpo-environment-setup Skill

    75★ repo

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

  • Run3 simpo loss implementation

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/nlp-paper-reproduction/run3_simpo-loss-implementation Skill

    75★ repo

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

  • Run3 simpo unit test execution

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/nlp-paper-reproduction/run3_simpo-unit-test-execution Skill

    75★ repo

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

  • Run2 docx template filling

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/offer-letter-generator/run2_docx-template-filling Skill

    75★ repo

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

  • Run2 python docx nested table recursion

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/offer-letter-generator/run2_python-docx-nested-table-recursion Skill

    75★ repo

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

  • Run3 pdf text extraction for classification

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/organize-messy-files/run3_pdf-text-extraction-for-classification Skill

    75★ repo

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

  • Run3 read python tokenizer source

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/python-scala-translation/run3_read-python-tokenizer-source Skill

    75★ repo

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

  • Run3 read scala test spec

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/python-scala-translation/run3_read-scala-test-spec Skill

    75★ repo

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

  • Run3 scala tokenizer implementation guide

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/python-scala-translation/run3_scala-tokenizer-implementation-guide Skill

    75★ repo

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

  • Run1 email json parsing and meeting extraction

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/schedule-planning/run1_email-json-parsing-and-meeting-extraction Skill

    75★ repo

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

  • Run1 pdf calendar parsing

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/schedule-planning/run1_pdf-calendar-parsing Skill

    75★ repo

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

  • Run3 skill 1

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/stock-data-visualization/run3_skill-1 Skill

    75★ repo

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

  • Run3 glm observation merge rmse

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/temperature-simulation/run3_glm-observation-merge-rmse Skill

    75★ repo

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

  • Run3 glm output extraction

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/temperature-simulation/run3_glm-output-extraction Skill

    75★ repo

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

  • Run3 database search ohio trip

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/travel-planning/run3_database-search-ohio-trip Skill

    75★ repo

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

  • Run3 ohio trip itinerary planning

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/travel-planning/run3_ohio-trip-itinerary-planning Skill

    75★ repo

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

  • Run3 convert keyframes to grayscale

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/video-object-counting/run3_convert-keyframes-to-grayscale Skill

    75★ repo

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

  • Run3 count objects in frames using template matching

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/video-object-counting/run3_count-objects-in-frames-using-template-matching Skill

    75★ repo

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

  • Run3 generate counting csv

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/video-object-counting/run3_generate-counting-csv Skill

    75★ repo

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

  • Run3 video keyframe extraction

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/video-object-counting/run3_video-keyframe-extraction Skill

    75★ repo

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

  • Run3 excel lookup formulas gnumeric compatible

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/weighted-gdp-calculation/run3_excel-lookup-formulas-gnumeric-compatible Skill

    75★ repo

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

  • Run3 gdp weighted mean net exports gcc

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/weighted-gdp-calculation/run3_gdp-weighted-mean-net-exports-gcc Skill

    75★ repo

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

  • Run3 inspect excel structure

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-opus-4-6/weighted-gdp-calculation/run3_inspect-excel-structure 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/b3-teacher-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.

  • Run3 qilv tonal patterns

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/chinese-poem-generator/run3_qilv-tonal-patterns Skill

    75★ repo

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

  • Run3 fill sc100 small claims form

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/court-form-filling/run3_fill-sc100-small-claims-form Skill

    75★ repo

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

  • Run3 inspect pdf fields

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/court-form-filling/run3_inspect-pdf-fields Skill

    75★ repo

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

  • Run1 dbscan custom metric clustering

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/dbscan-parameter-tuning/run1_dbscan-custom-metric-clustering Skill

    75★ repo

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

  • Run1 greedy centroid matching

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/dbscan-parameter-tuning/run1_greedy-centroid-matching Skill

    75★ repo

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

  • Run1 pareto frontier computation

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-sonnet-4-6/dbscan-parameter-tuning/run1_pareto-frontier-computation Skill

    75★ repo

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