agentsclimarketplace
Sign in

The catalog

325,949 rows, by stacks then stars

  • Pytorch loss implementation

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/nlp-paper-reproduction/pytorch-loss-implementation Skill

    75★ repo

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

  • Simpo loss function

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/nlp-paper-reproduction/simpo-loss-function Skill

    75★ repo

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

  • Python docx

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/offer-letter-generator/python-docx Skill

    75★ repo

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

  • Template processing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/offer-letter-generator/template-processing Skill

    75★ repo

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

  • Content classification

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/organize-messy-files/content-classification Skill

    75★ repo

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

  • Document organization pipeline

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/organize-messy-files/document-organization-pipeline Skill

    75★ repo

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

  • Docx pptx extraction

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/organize-messy-files/docx-pptx-extraction Skill

    75★ repo

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

  • File organization

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/organize-messy-files/file-organization Skill

    75★ repo

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

  • Pdf text extraction

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/organize-messy-files/pdf-text-extraction Skill

    75★ repo

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

  • Scala adt enums

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/python-scala-translation/scala-adt-enums Skill

    75★ repo

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

  • Scala circe json

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/python-scala-translation/scala-circe-json Skill

    75★ repo

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

  • Scala collections fp

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/python-scala-translation/scala-collections-fp Skill

    75★ repo

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

  • Scala generics

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/python-scala-translation/scala-generics Skill

    75★ repo

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

  • Scala option either

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/python-scala-translation/scala-option-either Skill

    75★ repo

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

  • Calendar scheduling logic

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/schedule-planning/calendar-scheduling-logic Skill

    75★ repo

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

  • Datetime formatting

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/schedule-planning/datetime-formatting Skill

    75★ repo

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

  • Meeting request parsing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/schedule-planning/meeting-request-parsing Skill

    75★ repo

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

  • Pdf calendar parsing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/schedule-planning/pdf-calendar-parsing Skill

    75★ repo

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

  • Csv data handling

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/stock-data-visualization/csv-data-handling Skill

    75★ repo

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

  • D3 force simulation

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/stock-data-visualization/d3-force-simulation Skill

    75★ repo

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

  • D3 fundamentals

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/stock-data-visualization/d3-fundamentals Skill

    75★ repo

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

  • D3 interactive charts

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/stock-data-visualization/d3-interactive-charts Skill

    75★ repo

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

  • Data matching

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/temperature-simulation/data-matching Skill

    75★ repo

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

  • Fortran namelist

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/temperature-simulation/fortran-namelist Skill

    75★ repo

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

  • Glm simulation

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/temperature-simulation/glm-simulation Skill

    75★ repo

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

  • Model calibration

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/temperature-simulation/model-calibration Skill

    75★ repo

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

  • Netcdf processing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/temperature-simulation/netcdf-processing Skill

    75★ repo

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

  • Budget management

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/travel-planning/budget-management Skill

    75★ repo

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

  • Data filtering

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/travel-planning/data-filtering Skill

    75★ repo

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

  • Data loading

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/travel-planning/data-loading Skill

    75★ repo

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

  • Route planning

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/travel-planning/route-planning Skill

    75★ repo

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

  • Ffmpeg keyframe extraction

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/video-object-counting/ffmpeg-keyframe-extraction Skill

    75★ repo

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

  • Opencv template matching

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/video-object-counting/opencv-template-matching Skill

    75★ repo

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

  • Python csv generation

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/video-object-counting/python-csv-generation Skill

    75★ repo

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

  • Excel lookup functions

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/weighted-gdp-calculation/excel-lookup-functions Skill

    75★ repo

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

  • Excel statistical formulas

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/weighted-gdp-calculation/excel-statistical-formulas Skill

    75★ repo

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

  • Excel xlsx skill

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/weighted-gdp-calculation/excel-xlsx-skill Skill

    75★ repo

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

  • Xlsx tool operations

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-haiku-4-5/weighted-gdp-calculation/xlsx-tool-operations Skill

    75★ repo

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

  • Anthropic brand

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/anthropic-poster-design/anthropic-brand Skill

    75★ repo

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

  • Pillow technical drawing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/anthropic-poster-design/pillow-technical-drawing Skill

    75★ repo

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

  • Chinese rhyme modern

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/chinese-poem-generator/chinese-rhyme-modern Skill

    75★ repo

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

  • Seven char regulated verse

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/chinese-poem-generator/seven-char-regulated-verse Skill

    75★ repo

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

  • Ca small claims sc100

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/court-form-filling/ca-small-claims-sc100 Skill

    75★ repo

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

  • Pdf form filling

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/court-form-filling/pdf-form-filling Skill

    75★ repo

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

  • Custom distance metrics

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/dbscan-parameter-tuning/custom-distance-metrics Skill

    75★ repo

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

  • Parallel processing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/dbscan-parameter-tuning/parallel-processing Skill

    75★ repo

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

  • Pareto optimization

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/dbscan-parameter-tuning/pareto-optimization Skill

    75★ repo

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

  • Cvss score extraction

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/dependency-vulnerability-check/cvss-score-extraction Skill

    75★ repo

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

  • Trivy offline vulnerability scanning

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/dependency-vulnerability-check/trivy-offline-vulnerability-scanning Skill

    75★ repo

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

  • Vulnerability csv reporting

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/dependency-vulnerability-check/vulnerability-csv-reporting Skill

    75★ repo

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

  • Geojson processing

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/earthquake-plate-calculation/geojson-processing Skill

    75★ repo

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

  • Geopandas projections

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/earthquake-plate-calculation/geopandas-projections Skill

    75★ repo

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

  • Plate tectonics analysis

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/earthquake-plate-calculation/plate-tectonics-analysis Skill

    75★ repo

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

  • Enterprise data retrieval

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/enterprise-information-search/enterprise-data-retrieval Skill

    75★ repo

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

  • Json data analysis

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/enterprise-information-search/json-data-analysis Skill

    75★ repo

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

  • 13f data analysis

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/financial-analysis/13f-data-analysis Skill

    75★ repo

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

  • Fuzzy search

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/financial-analysis/fuzzy-search Skill

    75★ repo

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

  • Druid javascript rce

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/fix-security-bug/druid-javascript-rce Skill

    75★ repo

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

  • Jackson inject security

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/fix-security-bug/jackson-inject-security Skill

    75★ repo

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

  • Gh cli pr stats

    cxcscmu/SkillLearnBench/skills/b1-one-shot-claude-opus-4-6/github-repo-analytics/gh-cli-pr-stats Skill

    75★ repo

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