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.
proteinmpnn - Skill - OpenSmartRoute
Skillv1.0.0
proteinmpnn
Design protein sequences from fixed backbone structures with ProteinMPNN-style workflows. Use when a task asks for backbone-conditioned sequence design, mutation suggestions, fixed residues, or…
Imported from chandan11248/ResearchX (ResearchX-harness/skills/proteinmpnn/SKILL.md). Install upstream with npx skills add chandan11248/ResearchX --skill proteinmpnn. Copyright stays with the author.
ProteinMPNN
Use this skill for fixed-backbone protein sequence design.
Workflow:
Record input structure, chain ids, designed positions, fixed residues, tied positions, symmetry, and design objective.
Verify the local or remote execution route before running.
Save PDB/mmCIF inputs, design masks, command, seeds, model version, FASTA outputs, and score tables.
Filter designs by constraints, diversity, motifs, structure prediction, conservation, and assay-ready feasibility.
Attach provenance and a verification plan before recommending candidates.
Treat generated sequences as candidates that require structural and experimental validation.
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 slot
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}'
Manifest
An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.
chandan11248-researchx-proteinmpnn.ocm.jsonjson
{
"ocm": "1",
"id": "chandan11248-researchx-proteinmpnn",
"kind": "skill",
"name": "proteinmpnn",
"description": "Design protein sequences from fixed backbone structures with ProteinMPNN-style workflows. Use when a task asks for backbone-conditioned sequence design, mutation suggestions, fixed residues, or design filtering.",
"publisher": "chandan11248",
"version": "1.0.0",
"capabilities": {
"domains": [
"science"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Design protein sequences from fixed backbone structures with ProteinMPNN-style workflows. Use when a task asks for backbone-conditioned sequence design, mutation suggestions, fixed residues, or design filtering."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/chandan11248/ResearchX",
"path": "ResearchX-harness/skills/proteinmpnn/SKILL.md",
"ref": "45c84217ed408f067a958a12831fe90cc16742ba",
"url": "https://github.com/chandan11248/ResearchX/blob/45c84217ed408f067a958a12831fe90cc16742ba/ResearchX-harness/skills/proteinmpnn/SKILL.md",
"key": "chandan11248/ResearchX/ResearchX-harness/skills/proteinmpnn/SKILL.md"
}
},
"instructions": "# ProteinMPNN\n\nUse this skill for fixed-backbone protein sequence design.\n\nWorkflow:\n\n1. Record input structure, chain ids, designed positions, fixed residues, tied positions, symmetry, and design objective.\n2. Verify the local or remote execution route before running.\n3. Save PDB/mmCIF inputs, design masks, command, seeds, model version, FASTA outputs, and score tables.\n4. Filter designs by constraints, diversity, motifs, structure prediction, conservation, and assay-ready feasibility.\n5. Attach provenance and a verification plan before recommending candidates.\n\nTreat generated sequences as c",
"cost": {
"context_tokens": 165
}
}
Fetch it by URL: GET /api/v1/registry/chandan11248-researchx-proteinmpnn/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.
