Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/add-ollama-provider
Route a NanoClaw agent group to a local Ollama model instead of the Anthropic API. Ollama speaks the Anthropic API natively (v1/messages), so no provider code changes are needed — just env var overrides and a model setting.
Passed 16 of 19 test cases with the skill, and 10 of 19 without it.
and 7 more in the full report
8 fixed11 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
Where does NanoClaw store the shared Claude settings JSON file for an agent group given its integer ID in data/v2.db?
| Checked | Without skill | With skill |
|---|---|---|
| Locates settings at data/v2-sessions/$AG_ID/.claude-shared/settings.json | Missed | Passed |
The instructions your model reads when the skill loads.
Routes an agent group to a local Ollama instance instead of the Anthropic API.
See docs/ollama.md for how this works and the tradeoffs involved.
curl -s http://localhost:11434/api/tagsollama pull gemma4 or ollama pull qwen3-coder/init-first-agent first if neededThe feature requires two fields in ContainerConfig (env and blockedHosts) and their
corresponding wiring in container-runner.ts. Check if already present:
grep -c 'blockedHosts' src/container-config.ts src/container-runner.ts
If either count is 0, apply the changes in steps 1a and 1b. Otherwise skip to step 2.
In src/container-config.ts, add to the ContainerConfig interface:
env?: Record<string, string>;
blockedHosts?: string[];
And in readContainerConfig, add inside the returned object:
env: raw.env,
blockedHosts: raw.blockedHosts,
test cases passed, vs 10 / 19 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.