Batch Evaluate — Development skill for Claude Code
Batch evaluate PENDING pattern adoptions from the adoption log.
How to install Batch Evaluate
Installs to ~/.claude/commands/diviner-dojo-agent_framework_template-batch-evaluate.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/Diviner-Dojo/agent_framework_template/HEAD/.claude/commands/batch-evaluate.md -o ~/.claude/commands/diviner-dojo-agent_framework_template-batch-evaluate.md Restart Claude Code, or start a new session, for it to be picked up.
What Batch Evaluate does
description: "Batch evaluate PENDING pattern adoptions from the adoption log. Reviews evidence, checks artifact existence, and presents verdicts for developer approval." allowed-tools: ["Read", "Write", "Edit", "Bash", "Glob", "Grep"]
Batch Evaluate PENDING Adoptions
You are acting as the Facilitator evaluating PENDING pattern adoptions from the adoption log.
Purpose
Process stale PENDING patterns from `memory/lessons/adoption-log.md` and present batch verdicts for developer app
Alternatives in Development
- Cohort Analysis — Cohort retention curves, feature adoption, and segment insights 7.8k ★
- SwiftUI Expert Skill — Modern SwiftUI best practices and iOS 26+ Liquid Glass adoption 2.3k ★
- Artifacts — Artifact Generation & Code Transformation 1.1k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Universal Standards
HITL PROTOCOL: Every agent presents output and waits for explicit APPROVED or REVISE: [instructions]. Silence
Harness Review
Full qualitative review of the agent setup. Read every file, evaluate quality, redundancy, and optimization op
Human HTML
Create or update a human-readable HTML artifact under docs/human-html/ for plans, reviews, architecture explai
Learn Pending
List all staged learning changes awaiting approval
Check Approvals
Check pending approvals and send reminders where overdue. \"who still owes an approval\"
Plan Resume
Resume a pending plan after HITL approval/rejection. Resumes plan state by correlationId.
Related Agents
Retrospective
Retrospective analysis agent. Analyzes completed work (a batch or individual item) to identify process improve
Architecture Gap Scout
Runs find-architecture-gaps over a given scope, dedupes against previously reported initiatives, and files new
Cyra
Security reviewer and approval signer. Read-only security review of auth, access control, secrets, data isolat