The catalog
616,489 rows, by stacks then stars
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/financial-analysis/run2_13f-holdings-comparison Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/financial-analysis/run2_13f-stock-search Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/fix-security-bug/run2_jackson-security Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/github-repo-analytics/run2_github-api-data-fetcher Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/nlp-paper-reproduction/run2_pytorch-simpo-loss Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/offer-letter-generator/run2_python-docx Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/organize-messy-files/run2_file-text-extraction Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/organize-messy-files/run2_keyword-classification Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/python-scala-translation/run2_python-scala-dataclass Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 python scala generics variance
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/python-scala-translation/run2_python-scala-generics-variance Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/python-scala-translation/run2_python-scala-json-circe Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 python scala union overloads
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/python-scala-translation/run2_python-scala-union-overloads Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/schedule-planning/run2_output-generator Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/schedule-planning/run2_pdf-parser Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/schedule-planning/run2_scheduler Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/stock-data-visualization/run2_d3-force-bubble-chart Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/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.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/temperature-simulation/run2_netcdf_rmse_evaluation Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/travel-planning/run2_data_parsing Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/travel-planning/run2_itinerary_generation Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/video-object-counting/run2_ffmpeg-extract Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/video-object-counting/run2_imagemagick-grayscale Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/video-object-counting/run2_object-counting Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/weighted-gdp-calculation/run2_excel-lookup Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/weighted-gdp-calculation/run2_excel-statistics Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b2-self-feedback-gemini-3.1-pro-preview/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.
Run3 Generate Nova Technical Exploded View Poster
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/anthropic-poster-design/run3_Generate-Nova-Technical-Exploded-View-Poster Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Build Pinyin to Tone Reference Table for Classical Chinese Poetry
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/chinese-poem-generator/run3_Build-Pinyin-to-Tone-Reference-Table-for-Classical-Chinese-Poetry Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Compose Seven Character Regulated Verse Character by Character Using Anchors
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/chinese-poem-generator/run3_Compose-Seven-Character-Regulated-Verse-Character-by-Character-Using-Anchors Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Map Pattern for Seven Character Regulated Verse
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/chinese-poem-generator/run3_Map----Pattern-for-Seven-Character-Regulated-Verse Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Verify Rhyme Integrity in Modern Mandarin Finals
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/chinese-poem-generator/run3_Verify-Rhyme-Integrity-in-Modern-Mandarin-Finals Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Extract PDF Form Field Names
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/court-form-filling/run3_Extract-PDF-Form-Field-Names Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Fill California Small Claims Form SC 100
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/court-form-filling/run3_Fill-California-Small-Claims-Form-SC-100 Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run1 dbscan custom distance clustering
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/dbscan-parameter-tuning/run1_dbscan-custom-distance-clustering Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/dbscan-parameter-tuning/run1_greedy-point-matching Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run1 mars cloud data loading matching
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/dbscan-parameter-tuning/run1_mars-cloud-data-loading-matching Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run1 output formatting pareto results
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/dbscan-parameter-tuning/run1_output-formatting-pareto-results Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run1 pareto frontier optimization
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/dbscan-parameter-tuning/run1_pareto-frontier-optimization Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Deduplicate and Order Vulnerability Records
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/dependency-vulnerability-check/run3_Deduplicate-and-Order-Vulnerability-Records Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Extract CVSS Score with Correct Priority
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/dependency-vulnerability-check/run3_Extract-CVSS-Score-with-Correct-Priority Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Filter Vulnerabilities by Severity Level
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/dependency-vulnerability-check/run3_Filter-Vulnerabilities-by-Severity-Level Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Format and Write CSV with Proper Escaping
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/dependency-vulnerability-check/run3_Format-and-Write-CSV-with-Proper-Escaping Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Handle NULL and Missing Values in Vulnerability Data
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/dependency-vulnerability-check/run3_Handle-NULL-and-Missing-Values-in-Vulnerability-Data Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 Map Trivy JSON Fields to CSV Columns Accurately
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/dependency-vulnerability-check/run3_Map-Trivy-JSON-Fields-to-CSV-Columns-Accurately Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 Calculate Distance to Nearest Pacific Boundary
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Calculate-Distance-to-Nearest-Pacific-Boundary Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 Execute Complete Geospatial Analysis Pipeline
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Execute-Complete-Geospatial-Analysis-Pipeline Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 Filter Earthquakes Within Pacific Plate
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Filter-Earthquakes-Within-Pacific-Plate Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 Filter Pacific Plate Boundaries
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Filter-Pacific-Plate-Boundaries Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 Find Earthquake Furthest from Pacific Boundary
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Find-Earthquake-Furthest-from-Pacific-Boundary Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 Identify Pacific Plate Identifier
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Identify-Pacific-Plate-Identifier Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 Load and Parse Plate Boundary Data
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Load-and-Parse-Plate-Boundary-Data Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 Load and Parse Plate Polygon Data
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Load-and-Parse-Plate-Polygon-Data Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 Load and Validate Earthquake Data
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Load-and-Validate-Earthquake-Data Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 Output Result to JSON File
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Output-Result-to-JSON-File Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run2 Project Data to EPSG 4087 for Distance Calculation
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/earthquake-plate-calculation/run2_Project-Data-to-EPSG-4087-for-Distance-Calculation Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 evidence validation checkpoint
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/enterprise-information-search/run3_evidence-validation-checkpoint Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 multi hop evidence extraction
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/enterprise-information-search/run3_multi-hop-evidence-extraction Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 product grounded artifact retrieval
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/enterprise-information-search/run3_product-grounded-artifact-retrieval Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/enterprise-information-search/run3_question-parsing Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
Run3 token counting and output
cxcscmu/SkillLearnBench/skills/b3-teacher-feedback-claude-haiku-4-5/enterprise-information-search/run3_token-counting-and-output Skill
75★ repo[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.