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.
refine-critique-loop - Skill - OpenSmartRoute
Skillv1.0.0
refine-critique-loop
Use this plugin when the user has an existing OpenDesign artifact and wants targeted critique, patching, brand tightening, responsive fixes, or quality improvement without starting over.
Imported from nexu-io/open-design (plugins/spec/examples/refine-critique-loop/SKILL.md). Install upstream with npx skills add nexu-io/open-design --skill refine-critique-loop. Copyright stays with the author (MIT).
Refine Critique Loop
Workflow
Read the existing artifact and identify the user's refinement goal.
Run a structured critique for hierarchy, fit, accessibility, responsiveness, and artifact-specific quality.
Apply the smallest useful patch.
Re-run critique and stop when quality converges or the iteration limit is reached.
Return a diff summary and what changed.
Output Contract
Patch the existing artifact and produce refine-summary.md.
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 refine-critique-loop 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": "nexu-io-open-design-refine-critique-loop",
"kind": "skill",
"name": "refine-critique-loop",
"description": "Use this plugin when the user has an existing OpenDesign artifact and wants targeted critique, patching, brand tightening, responsive fixes, or quality improvement without starting over.",
"publisher": "nexu-io",
"version": "1.0.0",
"capabilities": {
"domains": [
"legal",
"marketing"
],
"tags": [
"skill-md",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Use this plugin when the user has an existing OpenDesign artifact and wants targeted critique, patching, brand tightening, responsive fixes, or quality improvement without starting over."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/nexu-io/open-design",
"path": "plugins/spec/examples/refine-critique-loop/SKILL.md",
"ref": "HEAD",
"url": "https://github.com/nexu-io/open-design/blob/HEAD/plugins/spec/examples/refine-critique-loop/SKILL.md",
"key": "nexu-io/open-design/plugins/spec/examples/refine-critique-loop/SKILL.md"
},
"license": "MIT"
},
"instructions": "# Refine Critique Loop\n\n## Workflow\n\n1. Read the existing artifact and identify the user's refinement goal.\n2. Run a structured critique for hierarchy, fit, accessibility, responsiveness, and artifact-specific quality.\n3. Apply the smallest useful patch.\n4. Re-run critique and stop when quality converges or the iteration limit is reached.\n5. Return a diff summary and what changed.\n\n## Output Contract\n\nPatch the existing artifact and produce `refine-summary.md`.",
"cost": {
"context_tokens": 116
}
}
Fetch it by URL: GET /api/v1/registry/nexu-io-open-design-refine-critique-loop/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.