agentsclimarketplace
Sign in

The catalog

325,949 rows, by stacks then stars

  • Run3 run glm simulation

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/temperature-simulation/run3_run_glm_simulation Skill

    75★ repo

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

  • Run3 update glm config

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/temperature-simulation/run3_update_glm_config Skill

    75★ repo

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

  • Run1 data querying and filtering

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/travel-planning/run1_data-querying-and-filtering Skill

    75★ repo

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

  • Run1 json itinerary formatting

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/travel-planning/run1_json-itinerary-formatting Skill

    75★ repo

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

  • Run1 route planning and logistics

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/travel-planning/run1_route-planning-and-logistics Skill

    75★ repo

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

  • Run3 csv generation

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/video-object-counting/run3_csv_generation Skill

    75★ repo

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

  • Run3 image preprocessing

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/video-object-counting/run3_image_preprocessing Skill

    75★ repo

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

  • Run3 object counting

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/video-object-counting/run3_object_counting Skill

    75★ repo

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

  • Run3 video frame extraction

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/video-object-counting/run3_video_frame_extraction Skill

    75★ repo

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

  • Run3 Data Retrieval using INDEX and MATCH

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/weighted-gdp-calculation/run3_Data-Retrieval-using-INDEX-and-MATCH Skill

    75★ repo

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

  • Run3 Statistical Calculation and Formatting

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/weighted-gdp-calculation/run3_Statistical-Calculation-and-Formatting Skill

    75★ repo

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

  • Run3 Weighted Mean using SUMPRODUCT

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-flash-lite-preview/weighted-gdp-calculation/run3_Weighted-Mean-using-SUMPRODUCT 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-gemini-3.1-pro-preview/anthropic-poster-design/run3_skill-1 Skill

    75★ repo

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

  • Run1 modern mandarin rhyme tones

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/chinese-poem-generator/run1_modern-mandarin-rhyme-tones Skill

    75★ repo

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

  • Run1 qiyan lvshi composition

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/chinese-poem-generator/run1_qiyan-lvshi-composition Skill

    75★ repo

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

  • Run1 pypdf form filling

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/court-form-filling/run1_pypdf-form-filling Skill

    75★ repo

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

  • Run1 dbscan anisotropic distance

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/dbscan-parameter-tuning/run1_dbscan-anisotropic-distance Skill

    75★ repo

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

  • Run1 skill 1

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/dependency-vulnerability-check/run1_skill-1 Skill

    75★ repo

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

  • Run2 geopandas spatial analysis

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/earthquake-plate-calculation/run2_geopandas_spatial_analysis Skill

    75★ repo

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

  • Run1 json nested list formatting

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/enterprise-information-search/run1_json-nested-list-formatting Skill

    75★ repo

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

  • Run1 llm token tracking

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/enterprise-information-search/run1_llm-token-tracking Skill

    75★ repo

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

  • Run1 parse key value text

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/enterprise-information-search/run1_parse-key-value-text Skill

    75★ repo

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

  • Run3 analyze 13f filings and holdings

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/financial-analysis/run3_analyze_13f_filings_and_holdings 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-gemini-3.1-pro-preview/fix-security-bug/run3_skill-1 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-gemini-3.1-pro-preview/github-repo-analytics/run3_skill-1 Skill

    75★ repo

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

  • Run1 skill 1

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/nlp-paper-reproduction/run1_skill-1 Skill

    75★ repo

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

  • Run1 python docx advanced manipulation

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/offer-letter-generator/run1_python-docx-advanced-manipulation 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-gemini-3.1-pro-preview/organize-messy-files/run3_skill-1 Skill

    75★ repo

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

  • Run1 python to scala idioms

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/python-scala-translation/run1_python-to-scala-idioms Skill

    75★ repo

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

  • Run1 scala functional error handling

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/python-scala-translation/run1_scala-functional-error-handling Skill

    75★ repo

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

  • Run1 scala immutable builder pattern

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/python-scala-translation/run1_scala-immutable-builder-pattern Skill

    75★ repo

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

  • Run1 scala regex processing

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/python-scala-translation/run1_scala-regex-processing Skill

    75★ repo

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

  • Run1 skill 1

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/schedule-planning/run1_skill-1 Skill

    75★ repo

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

  • Run3 d3 interactivity and tooltips

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/stock-data-visualization/run3_d3-interactivity-and-tooltips Skill

    75★ repo

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

  • Run1 skill 1

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/temperature-simulation/run1_skill-1 Skill

    75★ repo

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

  • Run2 itinerary generation and formatting

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/travel-planning/run2_itinerary_generation_and_formatting Skill

    75★ repo

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

  • Run2 travel data retrieval

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/travel-planning/run2_travel_data_retrieval 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-gemini-3.1-pro-preview/video-object-counting/run3_skill-1 Skill

    75★ repo

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

  • Run2 excel 2d lookup formulas

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/weighted-gdp-calculation/run2_excel-2d-lookup-formulas Skill

    75★ repo

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

  • Run2 excel statistical and weighted mean formulas

    cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-gemini-3.1-pro-preview/weighted-gdp-calculation/run2_excel-statistical-and-weighted-mean-formulas Skill

    75★ repo

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

  • Anthropic brand system

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/anthropic-poster-design/anthropic-brand-system Skill

    75★ repo

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

  • Technical poster generation

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/anthropic-poster-design/technical-poster-generation Skill

    75★ repo

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

  • Mandarin rhyming

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/chinese-poem-generator/mandarin-rhyming Skill

    75★ repo

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

  • Regulated verse structure

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/chinese-poem-generator/regulated-verse-structure Skill

    75★ repo

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

  • War peace poetry

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/chinese-poem-generator/war-peace-poetry Skill

    75★ repo

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

  • Pdf form filler

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/court-form-filling/pdf-form-filler Skill

    75★ repo

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

  • Sc100 form mapping

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/court-form-filling/sc100-form-mapping Skill

    75★ repo

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

  • Mars cloud evaluation metrics

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/dbscan-parameter-tuning/mars-cloud-evaluation-metrics Skill

    75★ repo

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

  • Mars cluster to expert matching

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/dbscan-parameter-tuning/mars-cluster-to-expert-matching Skill

    75★ repo

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

  • Mars custom distance metric

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/dbscan-parameter-tuning/mars-custom-distance-metric Skill

    75★ repo

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

  • Mars pareto frontier

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/dbscan-parameter-tuning/mars-pareto-frontier Skill

    75★ repo

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

  • Npm vulnerability scanning

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/dependency-vulnerability-check/npm-vulnerability-scanning Skill

    75★ repo

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

  • Security audit csv report

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/dependency-vulnerability-check/security-audit-csv-report Skill

    75★ repo

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

  • Vulnerability data processing

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/dependency-vulnerability-check/vulnerability-data-processing Skill

    75★ repo

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

  • Geopandas coordinate projections

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/earthquake-plate-calculation/geopandas-coordinate-projections Skill

    75★ repo

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

  • Geospatial earthquake analysis

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/earthquake-plate-calculation/geospatial-earthquake-analysis Skill

    75★ repo

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

  • Plate boundary data processing

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/earthquake-plate-calculation/plate-boundary-data-processing Skill

    75★ repo

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

  • Enterprise search

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/enterprise-information-search/enterprise-search Skill

    75★ repo

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

  • Json data loader

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/enterprise-information-search/json-data-loader Skill

    75★ repo

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

  • Json output formatter

    cxcscmu/SkillLearnBench/skills/b4-skill-creator-claude-haiku-4-5/enterprise-information-search/json-output-formatter Skill

    75★ repo

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