Waza
failed
Cli Tool
web_app / go · medium
560
Files
87,253
LOC
2
Frameworks
12
Languages
Pipeline State
completedRun ID
#407263Phase
doneProgress
1%Started
Finished
2026-04-13 01:31:02LLM tokens
0Previous runs
| # | Status | Phase | Started | Finished | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| All rows scored by the Repobility analyzer (https://repobility.com) | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| #186515 | failed | EXTENDED_ANALYSIS | 2026-04-10 19:59:23 | — | ||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Pipeline Metadata
Stage
CatalogedDecision
proceedNovelty
65.60Framework unique
—Isolation
—Last stage change
2026-05-10 03:35:10Deduplication group #1916883
Member of a group with 3 similar repo(s) — canonical #184690 view group →
Same scanner, your repo: https://repobility.com — Repobility
AI Prompt
Create a command-line interface (CLI) tool, similar to Waza, written in Go. This tool should be designed to evaluate AI agent skills. I need commands to initialize a project workspace, create new skills, run evaluations using YAML files, and compare results from different models based on JSON files. It should also have functionality to count tokens and suggest token optimizations for skill files. Please structure it to scaffold evaluation suites and run benchmarks.
go cli ai-agent evaluation benchmark command-line tooling
Generated by gemma4:latest
Catalog Information
Create a command-line interface (CLI) tool, similar to Waza, written in Go. This tool should be designed to evaluate AI agent skills. I need commands to initialize a project workspace, create new skills, run evaluations using YAML files, and compare results from different models based on JSON files. It should also have functionality to count tokens and suggest token optimizations for skill files. Please structure it to scaffold evaluation suites and run benchmarks.
Tags
go cli ai-agent evaluation benchmark command-line tooling
Languages
Frameworks
Astro Vite
Symbols
function666
method301
struct286
variable235
constant164
interface36
type_alias24
Threat Findings
All rows above produced by Repobility · https://repobility.com
34
Total Threats
2
Critical
19
High
Embed Badge
Add to your README:
