run-360-eval
run-360-eval is an LLM evaluation & observability skill for AI agents, published by aws-samples in the sample-bedrock-migration-and-modernization-tools repository on GitHub. Skillspace rates run-360-eval F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Run LLM evaluations with 360-eval. Use when the user wants to benchmark, evaluate, score, or compare one or more LLMs (Amazon Bedrock, OpenAI, Gemini, Azure) on a dataset of prompts using LLM-as-a-jury scoring — including quality evals (correctness/completeness/format/etc. scored 1-5), latency/throughput benchmarks, vision/multimodal evals, multi-turn evals, and Bedrock Advanced Prompt Optimization (APO). Covers preparing inputs, running the engine CLI, reading results, and generating an HTML report. This skill drives the engine programmatically (no web UI needed).
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 31
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 80 / 100
- Maturity
- Basic: a single SKILL.md
- Security scan
- High-risk patterns
- License
- Apache-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- references sensitive credential env
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.