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.
aqe-review-quality - Skill - OpenSmartRoute
Skillv1.0.0
aqe-review-quality
Review Agentic QE changes and issue an evidence-backed quality verdict. Use for code review, regression-risk assessment, release readiness, quality-gate evaluation, security/performance/testability…
Imported from proffesor-for-testing/agentic-qe (.agents/skills/aqe-review-quality/SKILL.md). Install upstream with npx skills add proffesor-for-testing/agentic-qe --skill aqe-review-quality. Copyright stays with the author.
Review AQE Quality
Read AGENTS.md, the diff or requested scope, affected implementation,
tests, and configuration.
Review for correctness first: broken behavior, data loss, security,
concurrency, compatibility, and missing error paths.
Verify claims with focused commands where safe and available. Distinguish
observed failures from inferred risks.
Report findings by severity with file and line references, the triggering
scenario, and the smallest useful remediation.
End with one verdict:
PASS: no material finding and adequate evidence;
CONDITIONAL: bounded risks or missing environment-dependent evidence;
FAIL: correctness, safety, compatibility, or verification blocker.
List the exact checks run and any checks not run.
Do not edit code during a review unless the user also asks for fixes.
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://api.opensmartroute.ai/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 aqe-review-quality 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.
{
"ocm": "1",
"id": "proffesor-for-testing-agentic-qe-aqe-review-quality",
"kind": "skill",
"name": "aqe-review-quality",
"description": "Review Agentic QE changes and issue an evidence-backed quality verdict. Use for code review, regression-risk assessment, release readiness, quality-gate evaluation, security/performance/testability review, or checking whether a change has sufficient verification. Do not use when the user primarily asks to implement a feature.",
"publisher": "proffesor-for-testing",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"skill-md",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Review Agentic QE changes and issue an evidence-backed quality verdict. Use for code review, regression-risk assessment, release readiness, quality-gate evaluation, security/performance/testability review, or checking whether a change has sufficient verification. Do not use when the user primarily asks to implement a feature."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/proffesor-for-testing/agentic-qe",
"path": ".agents/skills/aqe-review-quality/SKILL.md",
"ref": "HEAD",
"url": "https://github.com/proffesor-for-testing/agentic-qe/blob/HEAD/.agents/skills/aqe-review-quality/SKILL.md",
"key": "proffesor-for-testing/agentic-qe/.agents/skills/aqe-review-quality/SKILL.md"
}
},
"instructions": "# Review AQE Quality\n\n1. Read `AGENTS.md`, the diff or requested scope, affected implementation,\n tests, and configuration.\n2. Review for correctness first: broken behavior, data loss, security,\n concurrency, compatibility, and missing error paths.\n3. Use [references/quality-gates.md](references/quality-gates.md) to select\n relevant QE review lenses. Do not run unrelated broad scans.\n4. Verify claims with focused commands where safe and available. Distinguish\n observed failures from inferred risks.\n5. Report findings by severity with file and line references, the triggering\n scenario, and the smallest useful remediation.\n6. End with one verdict:\n - `PASS`: no material finding and adequate evidence;\n - `CONDITIONAL`: bounded risks or missing environment-dependent evidence;\n - `FAIL`: correctness, safety, compatibility, or verification blocker.\n7. List the exact checks run and any checks not run.\n\nDo not edit code during a review unless the user also asks for fixes.",
"cost": {
"context_tokens": 248
}
}
Fetch it by URL: GET /api/v1/registry/proffesor-for-testing-agentic-qe-aqe-review-quality/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.