Scaffolds evaluation suites for the Axiom AI SDK. Generates eval files, scorers, flag schemas, and config from natural-language descriptions. Use when creating evals, writing scorers, setting up flag schemas, or configuring axiom.config.ts.
86%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required Workflow step 8 runs `scripts/eval-results`, which queries Axiom eval spans and projects `eval.case.input` and `eval.case.output` from live production traffic, so end users can inject text the agent reads without it selecting any specific item.
openclaw/clawhub
7aa988e
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.