overthinkos/notebook-openrouter
ov-layers/skills/notebook-openrouter/SKILL.md
OpenRouter API integration notebook collection provisioned into the workspace volume at deploy time. 3 Jupyter notebooks demonstrating OpenRouter API basics, model discovery, and practical inference. Data-only layer with env_requires — first layer to use the env_requires feature. Use when working with notebook-openrouter, OpenRouter API tutorials, or Jupyter+OpenRouter integration.
development
Updated Apr 24, 2026
$ install --global
skillsauthnpx skillsauth add overthinkos/overthink-plugins notebook-openrouterInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 24, 2026, 3:00 PM152.5s1 file scanned
SKILL.md
- name:
- notebook-openrouter
- description:
- |
notebook-openrouter -- OpenRouter API integration data layer
Layer Properties
| Property | Value |
|----------|-------|
| Dependencies | (none) |
| Packages | (none) |
| Services | (none) |
| Volumes | workspace -> ~/workspace (from jupyter) |
| Data | data/openrouter -> workspace volume, dest: openrouter |
| env_requires | OPENROUTER_API_KEY — API key for OpenRouter LLM inference |
| Install files | (none) |
How It Works
This is a data layer with an env_requires declaration — it uses the data: field to map notebooks to a volume, and env_requires: to declare that the OPENROUTER_API_KEY environment variable must be present:
info: "OpenRouter API integration notebook collection"
env_requires:
- name: OPENROUTER_API_KEY
description: "API key for OpenRouter LLM inference"
data:
- src: data/openrouter
volume: workspace
dest: openrouter
At build time, the contents of data/openrouter/ are staged into /data/workspace/openrouter/ inside the image.
At deploy time, ov config copies the staged data into the workspace volume at <workspace>/openrouter/. The dest: openrouter field places the notebooks in a subdirectory rather than the volume root.
The env_requires declaration is stored as an OCI label (org.overthinkos.env_requires). At ov config time, if OPENROUTER_API_KEY is not present in the resolved environment, a warning is printed:
Warning: jupyter-ml-notebook requires OPENROUTER_API_KEY (API key for OpenRouter LLM inference) — not set
This is the first layer in the project to use the env_requires feature.
Included Notebooks
3 Jupyter notebooks covering OpenRouter API usage with the free model qwen/qwen3.6-plus:free:
| Notebook | Topic | Features |
|----------|-------|----------|
| 00_OpenRouter_Basics.ipynb | API Basics | Authentication, simple chat completion, multi-turn conversation, error handling, usage/cost tracking |
| 01_OpenRouter_Models.ipynb | Model Selection | List all models, filter free models, inspect model details (pricing, context, modality), compare responses across models |
| 02_OpenRouter_Inference.ipynb | Practical Inference | Structured JSON output, text summarization, code generation (with exec), reasoning with thinking tokens, translation pipeline |
Manifest: notebooks.yaml — structured catalog with title, description, and ordering.
Free Tier Rate Limit Gotcha
The free model qwen/qwen3.6-plus:free has strict rate limits (~1 request per minute). All notebooks include an openrouter_chat() / chat() retry helper that handles 429 responses with exponential backoff:
def openrouter_chat(model, messages, retries=5, delay=15):
for attempt in range(retries):
response = requests.post(...)
if response.status_code == 429:
wait = delay * (attempt + 1)
print(f"Rate limited, waiting {wait}s...")
time.sleep(wait)
continue
response.raise_for_status()
return response.json()
The retry helper also handles transient 502 upstream errors from Alibaba (the Qwen provider) where the response is 200 but missing the choices key.
Providing the API Key
The OPENROUTER_API_KEY must be injected into the container environment:
# Via ov config (persisted in quadlet)
ov config jupyter-ml-notebook -e OPENROUTER_API_KEY=sk-or-v1-...
# Via workspace .env file
echo "OPENROUTER_API_KEY=sk-or-v1-..." >> ~/project/.env
# Via direnv .secrets (GPG-encrypted)
ov secrets gpg set OPENROUTER_API_KEY sk-or-v1-...
Usage
# image.yml
jupyter-ml-notebook:
layers:
- jupyter-ml
- notebook-templates
- notebook-finetuning
- notebook-ollama
- notebook-llm-on-supercomputers
- notebook-openrouter
# ... other layers
# Deploy with API key
ov config jupyter-ml-notebook -e OPENROUTER_API_KEY=sk-or-v1-...
ov start jupyter-ml-notebook
# Open http://localhost:8888 -> navigate to openrouter/
Used In Images
/ov-images:jupyter-ml-notebook
Related Skills
/ov:layer— data field documentation, env_requires/env_accepts field documentation/ov:config— data provisioning and env_requires warning duringov configsetup/ov:deploy— volume backing configuration/ov-layers:notebook-ollama— sibling data layer pattern (Ollama integration notebooks)/ov-layers:notebook-finetuning— sibling data layer pattern (Unsloth fine-tuning notebooks)/ov-layers:notebook-templates— sibling data layer pattern (starter notebooks)/ov-layers:notebook-llm-on-supercomputers— sibling data layer pattern (TU Wien course notebooks)/ov-images:jupyter-ml-notebook— the image that includes this layer
When to Use This Skill
Use when the user asks about:
- The notebook-openrouter layer or its contents
- OpenRouter API tutorial notebooks or integration examples
- How to provide
OPENROUTER_API_KEYto Jupyter containers - The
env_requiresfeature (this is the first real consumer) - Free tier rate limits on
qwen/qwen3.6-plus:free - Structured output, reasoning with thinking tokens, or model comparison via OpenRouter
Related
/ov:test— declarative testing (tests:block,ov image test,ov test)
Related Skills
overthinkos/plugin
tools
VerifiedTrustedCommunity
Use when authoring or modifying a charly PLUGIN — a candy with a `plugin:` block that contributes Providers (verbs/kinds/deploy-targets/steps/builders/commands), its own CUE schema, builtin (compiled-in) or external (out-of-tree git repo). Covers the unified Provider model, the per-plugin CUE-schema contract (single source → Go params for dev + schema-over-Describe RPC for runtime), the SDK, and the loader.
SKILL.mdUpdated Jun 22, 2026
overthinkos/cue
tools
VerifiedTrustedCommunity
The CUE data-validation / configuration CLI (cue), pinned to v0.16.1. Use when working with the cue candy, installing the cue binary into a box or onto a target:local dev host, or running the offline schema-vendoring pipeline that feeds charly's egress validation.
SKILL.mdUpdated Jun 16, 2026
overthinkos/egress
tools
VerifiedTrustedCommunity
CUE EGRESS validation — validating (and, where it adds value, generating) the config files charly WRITES to a system BEFORE the bytes hit disk. MUST be invoked before working on charly/egress.go, the vendored schemas under candy/plugin-egress/egress-schemas/vendor/, the ValidateEgress / registerVendoredEgressKind path, the offline `task cue:vendor` pipeline, or adding an egress schema for any written artifact (cloud-init, k8s manifests, traefik routes, runtime config, install ledger, systemd/quadlet units, ssh_config, libvirt XML).
SKILL.mdUpdated Jun 16, 2026
overthinkos/check-k8s
tools
VerifiedTrustedCommunity
Kubernetes cluster-probe declarative check verb — the `kube:` check verb (nodes, pods, ingress, storage class, addon health, apply/delete, and arbitrary resource GETs) served out-of-process by the candy/plugin-kube plugin (vendored client-go; no external kubectl required).
SKILL.mdUpdated Jun 14, 2026