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.
fetch-meta-from-kb - Skill - OpenSmartRoute
Skillv1.0.0
fetch-meta-from-kb
Fetch recent journals rows directly from PostgreSQL and return a JSON array containing doi, title, abstract, and date (filtered by rolling DAYS on created_at).
Imported from tiangong-ai/agent-skills (fetch-meta-from-kb/SKILL.md). Install upstream with npx skills add tiangong-ai/agent-skills --skill fetch-meta-from-kb. Copyright stays with the author.
Fetch Meta from KB
Workflow
Read DB env vars from .env or process env: KB_DB_HOST, KB_DB_PORT, KB_DB_NAME, KB_DB_USER, KB_DB_PASSWORD.
Query journals where created_at >= now_utc - DAYS, ordered by created_at DESC, selecting only doi, title, abstract, date.
Return/write JSON array records with exactly these fields: doi, title, abstract, date.
Script
Run:
cd fetch-meta-from-kbpython3 scripts/fetch_meta_from_kb.py --days 7 --output selected-abstract.json
Install fetch-meta-from-kb 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.
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}'
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": "tiangong-ai-agent-skills-fetch-meta-from-kb",
"kind": "skill",
"name": "fetch-meta-from-kb",
"description": "Fetch recent `journals` rows directly from PostgreSQL and return a JSON array containing `doi`, `title`, `abstract`, and `date` (filtered by rolling `DAYS` on `created_at`). Use when users need raw paper payloads for downstream processing without LLM filtering or hotspot report generation.",
"publisher": "tiangong-ai",
"version": "1.0.0",
"capabilities": {
"domains": [
"data_analysis",
"science"
],
"tags": [
"skill-md",
"skills-sh"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Fetch recent `journals` rows directly from PostgreSQL and return a JSON array containing `doi`, `title`, `abstract`, and `date` (filtered by rolling `DAYS` on `created_at`). Use when users need raw paper payloads for downstream processing without LLM filtering or hotspot report generation."
],
"primary": false,
"metadata": {
"source": {
"provider": "skills.sh",
"repository": "https://github.com/tiangong-ai/agent-skills",
"path": "fetch-meta-from-kb/SKILL.md",
"ref": "HEAD",
"url": "https://github.com/tiangong-ai/agent-skills/blob/HEAD/fetch-meta-from-kb/SKILL.md",
"key": "tiangong-ai/agent-skills/fetch-meta-from-kb/SKILL.md"
}
},
"instructions": "# Fetch Meta from KB\n\n## Workflow\n\n1. Read DB env vars from `.env` or process env: `KB_DB_HOST`, `KB_DB_PORT`, `KB_DB_NAME`, `KB_DB_USER`, `KB_DB_PASSWORD`.\n2. Query `journals` where `created_at >= now_utc - DAYS`, ordered by `created_at DESC`, selecting only `doi`, `title`, `abstract`, `date`.\n3. Return/write JSON array records with exactly these fields: `doi`, `title`, `abstract`, `date`.\n\n## Script\n\nRun:\n\n```bash\ncd fetch-meta-from-kb\npython3 scripts/fetch_meta_from_kb.py --days 7 --output selected-abstract.json\n```\n\nEnv example:\n\n```dotenv\nKB_DB_HOST=<HOST>\nKB_DB_PORT=5432\nKB_DB_NAME=<DATA",
"cost": {
"context_tokens": 195
}
}
Fetch it by URL: GET /api/v1/registry/tiangong-ai-agent-skills-fetch-meta-from-kb/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.
