Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
score-eval - Skill - OpenSmartRoute
Skillv1.0.0
score-eval
Score the eval diff at $ARGUMENTS against the eval rubric.
Imported from neondatabase/agent-skills (evals/neon-postgres-egress-optimizer/.claude/skills/score-eval/SKILL.md). Install upstream with npx skills add neondatabase/agent-skills --skill score-eval. Copyright stays with the author.
Score the eval diff at $ARGUMENTS against the eval rubric.
Read the diff file at the path provided
Read the eval rubric at eval-rubric.md
Read the original fixture app in fixtures/hono-drizzle-app/ for comparison
For each problem P1-P5, answer the Detected? and Fixed? questions from the rubric as yes or no
Append a row to results.csv — fill in all fields you can determine from the diff and context. Leave fields you can't determine empty.
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 - a plan picks it for its slotcurl-s-X POST https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install score-eval and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
When a provider is down or over quota the request moves on; the trace says it did.
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
neondatabase-agent-skills-score-eval.ocm.jsonjson
{
"ocm": "1",
"id": "neondatabase-agent-skills-score-eval",
"kind": "skill",
"name": "score-eval",
"description": "Score the eval diff at $ARGUMENTS against the eval rubric.",
"publisher": "neondatabase",
"version": "1.0.0",
"capabilities": {
"domains": [
"data_analysis"
],
"tags": [
"skill-md",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Score the eval diff at $ARGUMENTS against the eval rubric."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/neondatabase/agent-skills",
"path": "evals/neon-postgres-egress-optimizer/.claude/skills/score-eval/SKILL.md",
"ref": "HEAD",
"url": "https://github.com/neondatabase/agent-skills/blob/HEAD/evals/neon-postgres-egress-optimizer/.claude/skills/score-eval/SKILL.md",
"key": "neondatabase/agent-skills/evals/neon-postgres-egress-optimizer/.claude/skills/score-eval/SKILL.md"
}
},
"instructions": "Score the eval diff at $ARGUMENTS against the eval rubric.\n\n1. Read the diff file at the path provided\n2. Read the eval rubric at eval-rubric.md\n3. Read the original fixture app in fixtures/hono-drizzle-app/ for comparison\n4. For each problem P1-P5, answer the Detected? and Fixed? questions from the rubric as yes or no\n5. Append a row to results.csv — fill in all fields you can determine from the diff and context. Leave fields you can't determine empty.",
"cost": {
"context_tokens": 114
}
}
Fetch it by URL: GET /api/v1/registry/neondatabase-agent-skills-score-eval/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
