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.
paper-reflect - Skill - OpenSmartRoute
Skillv1.0.0
paper-reflect
Generate a lightweight structured reflection JSON for a single paper record.
Imported from TheAuser/Academic-Graph-Agent (workspace/skills/paper-reflect/SKILL.md). Install upstream with npx skills add TheAuser/Academic-Graph-Agent --skill paper-reflect. Copyright stays with the author.
paper-reflect
Use this skill when the user wants structured extraction from a paper record.
Workflow
Run python3 /root/openclaw-dev/workspace/scripts/reflect_paper.py <paper_json_path>
Read the saved reflection JSON under /root/openclaw-dev/workspace/data/reflections/
Treat this as a stable MVP skeleton, not a final Deep Reflection implementation
Outputs
entities
claims
gaps
placeholder arrays for methods, problems, datasets, metrics, baselines
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.
{
"ocm": "1",
"id": "theauser-academic-graph-agent-paper-reflect",
"kind": "skill",
"name": "paper-reflect",
"description": "Generate a lightweight structured reflection JSON for a single paper record.",
"publisher": "TheAuser",
"version": "1.0.0",
"capabilities": {
"domains": [
"general"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Generate a lightweight structured reflection JSON for a single paper record."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/TheAuser/Academic-Graph-Agent",
"path": "workspace/skills/paper-reflect/SKILL.md",
"ref": "ce9622eb99944b550b137eb3004923a6b834735f",
"url": "https://github.com/TheAuser/Academic-Graph-Agent/blob/ce9622eb99944b550b137eb3004923a6b834735f/workspace/skills/paper-reflect/SKILL.md",
"key": "TheAuser/Academic-Graph-Agent/workspace/skills/paper-reflect/SKILL.md"
}
},
"instructions": "# paper-reflect\n\nUse this skill when the user wants structured extraction from a paper record.\n\nWorkflow\n- Run `python3 /root/openclaw-dev/workspace/scripts/reflect_paper.py <paper_json_path>`\n- Read the saved reflection JSON under `/root/openclaw-dev/workspace/data/reflections/`\n- Treat this as a stable MVP skeleton, not a final Deep Reflection implementation\n\nOutputs\n- entities\n- claims\n- gaps\n- placeholder arrays for methods, problems, datasets, metrics, baselines",
"cost": {
"context_tokens": 117
}
}
Fetch it by URL: GET /api/v1/registry/theauser-academic-graph-agent-paper-reflect/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.
