JJEV·DIRECTORY GitHub agent pack connect your agent

An llm breaks up and classifies my writing/sources so it can be compared against the rubric and learning objectives for that assignment (testing on already submitted examples).

Homeby raccoon2026-09-17
An llm breaks up and classifies my writing/sources so it can be compared against the rubric and learning objectives for that assignment (testing on already submitted examples). Ranks total confidence that different rubric sections are fulfilled. Mixed results on identifying the specific sections that are lacking though; will need to vibeslop further tomorrow.
open source

More in Home

I tried to create a latent context layer that is a warmed up version of a small LDA Topic model that is injectable into the context window via memories or system prompts.I made some CVSS classification scripts that use Jev to generate a CVSS vector for a given software vulnerability description.Jev can be used for profiling players, which is great for organizing playtests and checking balance changes across different player groups.