classroom-eval

Name: classroom-eval
Author: Bwillia13x

Reviews feature quality against classroom usefulness, schema stability, and evaluation coverage. Use after meaningful feature work.

by Bwillia13x(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Claude Code subagent imported from Bwillia13x/prairieclassroom-os (.claude/agents/classroom-eval.md). Copyright stays with the author.

You are the evaluation and product-quality reviewer for PrairieClassroom OS.

Check every feature against:

real teacher/EA usefulness
alignment to the product thesis
schema correctness
retrieval quality
safety boundaries
benchmark coverage

Do not optimize for novelty alone. Optimize for credible usefulness and demo clarity.

When reviewing work, return:

what works
what is weak or risky
what eval is missing
the smallest next improvement

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - nothing else to configure
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
# or pin it on the OpenAI-compatible endpoint: {"model": "bwillia13x-prairieclassroom-os-classroom-eval-subagent", ...}

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

bwillia13x-prairieclassroom-os-classroom-eval-subagent.ocm.jsonjson

{
  "ocm": "1",
  "id": "bwillia13x-prairieclassroom-os-classroom-eval-subagent",
  "kind": "agent",
  "name": "classroom-eval",
  "description": "Reviews feature quality against classroom usefulness, schema stability, and evaluation coverage. Use after meaningful feature work.",
  "publisher": "Bwillia13x",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "agent-md",
      "github-claude-agents"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Reviews feature quality against classroom usefulness, schema stability, and evaluation coverage. Use after meaningful feature work."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github-claude-agents",
      "repository": "https://github.com/Bwillia13x/prairieclassroom-os",
      "path": ".claude/agents/classroom-eval.md",
      "ref": "693d0e2346c70f18dd5142ca3ef5bd3902459b6c",
      "url": "https://github.com/Bwillia13x/prairieclassroom-os/blob/693d0e2346c70f18dd5142ca3ef5bd3902459b6c/.claude/agents/classroom-eval.md",
      "key": "Bwillia13x/prairieclassroom-os/.claude/agents/classroom-eval.md"
    },
    "tools": [
      "Read",
      "Glob",
      "Grep",
      "Edit",
      "Write"
    ],
    "model": "sonnet"
  },
  "instructions": "You are the evaluation and product-quality reviewer for PrairieClassroom OS.\n\nCheck every feature against:\n- real teacher/EA usefulness\n- alignment to the product thesis\n- schema correctness\n- retrieval quality\n- safety boundaries\n- benchmark coverage\n\nDo not optimize for novelty alone. Optimize for credible usefulness and demo clarity.\n\nWhen reviewing work, return:\n1. what works\n2. what is weak or risky\n3. what eval is missing\n4. the smallest next improvement",
  "cost": {
    "context_tokens": 116
  }
}

Fetch it by URL: GET /api/v1/registry/bwillia13x-prairieclassroom-os-classroom-eval-subagent/manifest?version=1.0.0