Agent Skill Evals helps you test agent skills with Promptfoo.
Skill Claude CodeCodex
Use when the user reports a concrete bug in an existing application and asks for a code fix. Reproduce the bug, write or run a verifier that fails, change the smallest amount of code that makes the verifier pass, re-run the verifier, and explain the change. Do not use for: feature requests, code review, dependency…
Skill Claude CodeCodex
Helps with GitHub workflows.
Skill Claude CodeCodex
Use when validating repository-level checks that do not need a copied fixture. Do not use for agent behavior.
Skill Claude CodeCodex
This fixture intentionally omits Agent Skill Evals routing frontmatter.
Skill Claude CodeCodex
Use when validating Agent Skill Evals runtime test fields. Do not use for real agent runs.
Skill Claude CodeCodex
Use when checking verifier wiring. Do not use for live agent behavior.
Skill Claude CodeCodex
Evaluate an existing agent skill with Promptfoo-native behavior, routing, or role-play tests. Use when a skill needs executable evidence that its product promise works. Do not use to author the domain skill itself.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: