Code
Hub
Workspaces
Connect
Indexed graphs
Engine
MCP
copy
hub
/
github.com/garrytan/gstack
/ skill-llm-eval.test.ts
File
skill-llm-eval.test.ts
test/skill-llm-eval.test.ts:None–None ·
view source on GitHub ↗
Source
from the content-addressed store, hash-verified
1
/**
2
* LLM-as-a-Judge evals
for
generated SKILL.md quality.
3
*
4
* Uses the Anthropic API directly (not Agent SDK) to evaluate whether
Callers
nothing calls this directly
Calls
12
detectBaseBranch
Function · 0.90
getChangedFiles
Function · 0.90
selectTests
Function · 0.90
judge
Function · 0.90
extractGrepLines
Function · 0.85
runWorkflowJudge
Function · 0.85
addTest
Method · 0.80
create
Method · 0.80
finalize
Method · 0.80
describeIfSelected
Function · 0.70
testIfSelected
Function · 0.70
push
Method · 0.45
Tested by
no test coverage detected