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. Use when the user wants to run their agent locally, cut API costs, or experiment with open-weight models. See docs/ollama.md for background.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

82%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with a clear, validated multi-step workflow. It loses points for some unnecessary explanatory padding and for referencing docs/ollama.md that is not provided as a bundle file, making progressive disclosure unverified.

Suggestions

Provide docs/ollama.md in a references/ bundle so the referenced background document actually exists, or remove the references to it.

Trim inline rationale like 'Claude Code reads its model from its own settings file, not from env vars' and the 'Why these vars' prose to only the non-obvious rationale Claude would not infer.

Replace illustrative model names like 'gemma4'/'qwen3-coder' with a single placeholder convention to avoid implying specific version availability.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, but includes explanation Claude doesn't need ('Claude Code reads its model from its own settings file, not from env vars') and inline rationale blocks that could be trimmed; 'gemma4' and 'qwen3-coder' illustrative model names plus version-ish details add minor padding.	2 / 3
Actionability	Provides executable, copy-paste-ready bash, SQL, TypeScript, and JSON snippets with exact file paths and commands; step 1 grep checks, container.json blocks, and verification commands are concrete and complete.	3 / 3
Workflow Clarity	Clearly sequenced numbered steps with conditional branches (skip to step 2 if already present), explicit verification in step 6 with expected values, and a revert section; feedback loops present via the troubleshooting section and verify step.	3 / 3
Progressive Disclosure	No bundle files exist and the body references docs/ollama.md but it is not present in references/, so the one-level-deep reference cannot be verified; content is well-organized but the missing referenced file prevents a top score.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete, answering both what and when in third person. Minor caveat: it bundles implementation detail (env var overrides, no provider code changes) that slightly pads it, but this does not drop it below top anchors.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: route an agent group to a local Ollama model, override env vars, set a model setting — specific and concrete, not vague.	3 / 3
Completeness	Explicitly states what it does (route agent group to local Ollama) and when to use it ('Use when the user wants to run their agent locally, cut API costs, or experiment with open-weight models'). Third person throughout.	3 / 3
Trigger Term Quality	Includes natural user phrasing like 'run their agent locally', 'cut API costs', 'experiment with open-weight models' alongside Ollama/Anthropic API, giving good coverage of terms users would say.	3 / 3
Distinctiveness Conflict Risk	A clear niche — local Ollama provider routing for NanoClaw — with distinct triggers unlikely to conflict with generic skills.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	15 / 16 Passed

Repository: nanocoai/nanoclaw
Path: .claude/skills/add-ollama-provider/SKILL.md
Commit: 641963c

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.