fix: use scalar Claude agent tools (#2583)

Normalize scalar Claude agent tool metadata across validators, adapters, dashboards, and generated surfaces with regression coverage.
This commit is contained in:
Affaan Mustafa 2026-07-26 03:20:15 -07:00 committed by GitHub
parent f3afd59045
commit 6a9f075cd9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
79 changed files with 515 additions and 87 deletions

View file

@ -1,7 +1,7 @@
---
name: agent-evaluator
description: Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, conciseness). Use after any non-trivial task when the user wants a quality assessment, or when the agent-self-evaluation skill is active. Produces structured scorecard with evidence and improvement suggestions.
tools: ["Read", "Grep", "Glob", "Bash"]
tools: Read, Grep, Glob, Bash
model: sonnet
---