How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

intr5100-lab-01-calibration - Skill

Name: intr5100-lab-01-calibration
Author: patricktiu1205

Imported from patricktiu1205/intr5100-lab-01-calibration (AGENTS.md). Install upstream with npx skills add patricktiu1205/intr5100-lab-01-calibration. Copyright stays with the author.

Lab I workspace instructions

Use the shared Conda environment intr5100 for all Python work. Do not create a per-lab environment.
Experimental records and historical fitted results are fixed. Preserve their file bytes, provenance and calibration/deployment distinction. Do not silently correct the historical IDM/TTC implementations or publish a new fit as the one originally deployed.
The relative-speed and TTC sign discrepancies are documented in review/review_notes.md. Mathematical changes need a separate explicitly requested analysis and clearly distinguished outputs.
Keep final reports in report/, report sources/figures in report/source/, instructions in docs/, review evidence in review/, and older development material in archive/.
Use lowercase snake_case for descriptive names. Preserve recorded timestamps, data schema filenames, TGSIM pair identifiers and method IDs required by metadata.
A standalone clone must work without a sibling course folder. Use local copies of supplied reference files in environment/; keep deduplication links inside the repository.
Keep the concise Lab I report style: A4, 20-mm margins, readable 11-point serif text, black headings and clean tables/figures.
The course-root environment.yml is authoritative in the full workspace. Sync this repository's copy before publishing.
Remove task-created temporary scripts, previews, caches and build byproducts. Preserve source code, raw data, results, diagnostics and reproducibility records.

Naming convention: lowercase snake_case for descriptive files and folders; use lab_01 / lab_02 prefixes on lab deliverables and YYYYMMDD for document dates. Preserve recorded timestamps, dataset/method identifiers, standard README.md / AGENTS.md and required deployment filenames. See review/naming_changes.json for the rename map.

Install intr5100-lab-01-calibration 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": "patricktiu1205-intr5100-lab-01-calibration-intr5100-lab-53ccd3", "kind": "skill", "name": "intr5100-lab-01-calibration", "description": "Naming convention: lowercase snake_case for descriptive files and folders; use `lab_01` / `lab_02` prefixes on lab deliverables and `YYYYMMDD` for document dates. Preserve recorded timestamps, dataset/method identifiers, standard `README.md` / `AGENTS.md` and required deployment filenames. See `review/naming_changes.json` for the rename map.", "publisher": "patricktiu1205", "version": "1.0.0", "capabilities": { "domains": [ "coding", "data_analysis" ], "tags": [ "skill-md", "github-agents" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Naming convention: lowercase snake_case for descriptive files and folders; use `lab_01` / `lab_02` prefixes on lab deliverables and `YYYYMMDD` for document dates. Preserve recorded timestamps, dataset/method identifiers, standard `README.md` / `AGENTS.md` and required deployment filenames. See `review/naming_changes.json` for the rename map." ], "primary": false, "metadata": { "source": { "provider": "github-agents", "repository": "https://github.com/patricktiu1205/intr5100-lab-01-calibration", "path": "AGENTS.md", "ref": "9bedef2b584889d4192c7fbae3288354a98f0ddd", "url": "https://github.com/patricktiu1205/intr5100-lab-01-calibration/blob/9bedef2b584889d4192c7fbae3288354a98f0ddd/AGENTS.md", "key": "patricktiu1205/intr5100-lab-01-calibration/AGENTS.md" } }, "instructions": "# Lab I workspace instructions\n\n- Use the shared Conda environment `intr5100` for all Python work. Do not create a per-lab environment.\n- Experimental records and historical fitted results are fixed. Preserve their file bytes, provenance and calibration/deployment distinction. Do not silently correct the historical IDM/TTC implementations or publish a new fit as the one originally deployed.\n- The relative-speed and TTC sign discrepancies are documented in `review/review_notes.md`. Mathematical changes need a separate explicitly requested analysis and clearly distinguished outputs.\n- Keep final", "cost": { "context_tokens": 466 } }

intr5100-lab-01-calibration

About

Lab I workspace instructions

Install intr5100-lab-01-calibration and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews