The Index · Model evaluation
Model evaluation
'Evals' — scoring model output and catching regressions. tashan measures 28 capabilities for this work and ranks them by tashan score — a transparent composite of upkeep, freshness and real adoption. How we measure ›
| # | Capability | tashan | Evidence | Health |
|---|---|---|---|---|
| 1 | HuggingFace Skills server Data & Analytics | 81 | 11k ★ | active |
| 2 | Deepeval server Data & Analytics | 81 | 17k ★ | active |
| 3 | Promptfoo Evals server Dev Tools & CI | 81 | 24k ★ | active |
| 4 | Data & Analytics | 72 | 218 ★ | active |
| 5 | Dev Tools & CI | 69 | 124 ★ | active |
| 6 | Dev Tools & CI | 67 | 37 ★ | active |
| 7 | Dev Tools & CI | 65 | 23 ★ | active |
| 8 | Dev Tools & CI | 65 | 61 ★ | active |
| 9 | Dev Tools & CI | 64 | 74 ★ | active |
| 10 | Productivity | 59 | 16 ★ | active |
| 11 | Dev Tools & CI | 54 | 5 ★ | active |
| 12 | Dev Tools & CI | 51 | 164k ★ | active |
| 13 | Iris server Productivity | 51 | 8 ★ | active |
| 14 | Nnsight server Data & Analytics | 48 | 9 ★ | active |
| 15 | Autoresearch AI Plugin server Dev Tools & CI | 46 | 12 ★ | active |
| 16 | Everdict server Dev Tools & CI | 45 | 1 ★ | active |
| 17 | Bitfab server Dev Tools & CI | 44 | 1 ★ | active |
| 18 | Claude Performance server Dev Tools & CI | 43 | 1 ★ | active |
| · | Caio Review skill Dev Tools & CI | not scored yet | 23k ★ | active |
| · | Chief AI Officer Advisor skill Security | not scored yet | 23k ★ | active |
| · | Senior Prompt Engineer skill Productivity | not scored yet | 23k ★ | active |
| · | Agenthub skill Dev Tools & CI | not scored yet | 23k ★ | active |
| · | Eval skill Dev Tools & CI | not scored yet | 23k ★ | active |
| · | Autoresearch Agent skill Dev Tools & CI | not scored yet | 23k ★ | active |
| · | Setup skill Dev Tools & CI | not scored yet | 23k ★ | active |
| · | Prompt Governance skill Productivity | not scored yet | 23k ★ | active |
| · | Self Eval skill Productivity | not scored yet | 23k ★ | active |
| · | Prompt Engineer Toolkit skill Dev Tools & CI | not scored yet | 23k ★ | active |
Who does this work
O*NET has no process step for this yet — its software occupations were surveyed before agentic tooling existed. We list it because the corpus plainly shows people doing it, and we say so rather than forcing it onto an unrelated step.
Other work
Agent configurationAgent developmentAnimation and generated imageryApplication developmentAttributionBookkeepingBrowser automationCode reviewContent marketingContract reviewCopy editingCopywritingDashboards and reportingData pipelinesData qualityDatabase accessDebuggingDesign critiqueDocument productionExploratory data analysisFinancial modellingIncident responseInfrastructure and deploymentKnowledge managementLiterature reviewMarket analysisMessaging and emailObservabilityPRDs and specsProcess automationProduct strategyProject managementPrompt engineeringQuery optimisationRegulatory complianceRetrieval systemsRisk assessmentSEOSales pipelineScientific researchSecurity reviewSoftware architectureStatistical modellingTechnical documentationTest automationTraining materialUser researchVideo editingVisual designWeb developmentWeb researchWeb scraping
Occupational data from the O*NET 30.3 Database by the U.S. Department of Labor, Employment and Training Administration, used under CC BY 4.0. tashan consolidated its process steps into the terms practitioners use; O*NET does not endorse this site.