ollama-setup

Configure auto-configure Ollama when user needs local LLM deployment, free AI alternatives, or wants to eliminate hosted API costs. Trigger phrases: "install ollama", "local AI", "free LLM", "self-hosted AI", "replace OpenAI", "no API costs". Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Quality

77%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/ai-ml/ollama-local-ai/skills/ollama-setup/SKILL.md

Quality

Content

65%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 skill body is highly actionable with concrete, executable commands and a useful error table, but it is held back by content duplication with its own reference files and an implicit rather than explicit validation feedback loop for system-modifying operations.

Suggestions

De-duplicate: keep the body's Instructions as a high-level sequence and move the detailed RAM/model tables and install command blocks into references/skill-workflow.md, linking to it instead of restating it.

Weave an explicit feedback loop into the workflow (e.g., 'If `ollama list` is empty or the curl check fails, return to step 3/4 and re-pull the model before proceeding').

Link references/examples.md from the Examples section (or move the inline scenarios there) so all bundle files are discoverable and content is split cleanly.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence (no 'what is Ollama' preamble), but the RAM/model selection table and install commands are duplicated between the Instructions and references/skill-workflow.md, and the three Examples scenarios restate the workflow rather than earning their tokens.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands across platforms ('brew install ollama', 'curl -fsSL https://ollama.com/install.sh \| sh', the docker run invocation), specific model names with sizes, and a concrete error-handling table with fixes.	3 / 3
Workflow Clarity	A clear 10-step sequence with verification steps (5, 6, 10) is present, but because this involves system-level installs (curl\|sh, systemd, Docker) the rubric expects an explicit validate->fix->retry feedback loop woven into the flow; recovery guidance lives only in a separate error table, leaving checkpoints implicit.	2 / 3
Progressive Disclosure	It points one level deep to real files (references/skill-workflow.md, references/errors.md) with clear signaling, but the model/RAM and install content is duplicated inline rather than cleanly split, and the existing references/examples.md is never linked from the body.	2 / 3
	Total	9 / 12 Passed

Description

90%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 clearly states the skill's purpose and provides natural, distinctive trigger phrases with an explicit Use-when clause. It is slightly held back by the awkward 'Configure auto-configure' phrasing and trailing boilerplate ('Trigger with relevant phrases based on skill purpose').

Suggestions

Fix the doubled verb ('Configure auto-configure Ollama') to a single concrete action and add 1-2 more specific verbs (e.g., 'Install, configure, and integrate Ollama') to strengthen specificity.

Remove the padding clause 'Trigger with relevant phrases based on skill purpose.' and tighten 'Use when appropriate context detected' to reference the listed triggers directly.

Dimension	Reasoning	Score
Specificity	Names the domain and several use cases ('local LLM deployment, free AI alternatives, ... eliminate hosted API costs') but the only concrete action verb is the doubled 'Configure auto-configure Ollama', so it is not a comprehensive list of specific actions.	2 / 3
Completeness	Answers both 'what' (configure Ollama for local LLM deployment / cost elimination) and 'when' (an explicit 'Use when...' clause plus enumerated trigger phrases), matching the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Lists genuinely natural trigger phrases users would say ('install ollama', 'local AI', 'free LLM', 'self-hosted AI', 'replace OpenAI', 'no API costs') with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Ollama-specific triggers ('install ollama', 'replace OpenAI', 'no API costs') carve out a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/ai-ml/ollama-local-ai/skills/ollama-setup/SKILL.md
Commit: 8585d6d

Reviewed: 1 day 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.