CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-ollama-tool

Add Ollama MCP server so the container agent can call local models and optionally manage the Ollama model library.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/add-ollama-tool/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%Weight 40%Scale 1-5

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

A high-quality, highly actionable install guide: fully executable steps, exact code edits with before/after context, an explicit validation gate, and strong troubleshooting coverage. The main gaps are minor — some prose that could be tightened and content that could be split into reference files.

DimensionReasoningScore

Conciseness

The body is dense with executable instructions — copy commands, exact before/after diffs, validation commands — and does not explain concepts Claude already knows (no 'what is MCP' padding). It falls short of 5 because a few passages (the credentials-vs-configuration aside, the shared-block rationale, some troubleshooting prose) could be trimmed slightly.

4 / 5

Actionability

Every step is copy-paste ready: exact `cp` commands, complete TypeScript snippets showing the current code and the replacement, specific validation commands (`pnpm run build`, vitest/bun test invocations), and concrete verification prompts. The common cases (macOS and Linux restart, default host with fallback) are all covered.

5 / 5

Workflow Clarity

The workflow is cleanly phased (Pre-flight → Apply → Configure → Verify) with an explicit validation gate ('All must be clean before proceeding'), an idempotency check ('If it does, skip to Phase 3'), conditional handling of the opt-in admin tools, and a troubleshooting section that maps observed failures to causes and fixes — a full feedback loop.

5 / 5

Progressive Disclosure

The single file is well organized with clear phase headings, tool tables, and a dedicated troubleshooting section, and it points one level deep to a sibling skill ('add-atomic-chat-tool') for the credential-env shape rather than duplicating it. It is not a 5 because the ~300-line body inlines content (tool catalog, troubleshooting) that could live in reference files, and the copied source files it depends on are not broken out into a references/ structure.

4 / 5

Total

18

/

20

Passed

Description

61%Weight 40%Scale 1-5

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

A specific, domain-anchored description that clearly says what the skill does, but it omits any 'Use when...' trigger clause and lacks synonym coverage. Adding explicit trigger guidance and naming the concrete tool operations (list, generate, pull, delete) would move it toward the top anchors.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user mentions Ollama, local LLMs, or wants the agent to run models locally'.

Name the concrete operations (list models, generate responses, pull/delete models) instead of the generic 'call local models and optionally manage the model library'.

Include natural synonyms such as 'local LLM' or 'offline model' so the description matches how users actually phrase the request.

DimensionReasoningScore

Specificity

The description names the domain ('Ollama MCP server') and two actions — 'call local models' and 'optionally manage the Ollama model library' — matching the anchor for 1-2 concrete actions rather than the several specific actions (list, generate, pull, delete) that would justify a 4. It is not score 2 because the actions named are concrete, not generic filler.

3 / 5

Completeness

The 'what' is clear (adds an MCP server exposing local models as tools, with optional library management), but there is no 'Use when...' clause or equivalent trigger guidance — the rubric guideline explicitly caps completeness at 3 for that. It is not a 2 because the 'what' is specific and unambiguous.

3 / 5

Trigger Term Quality

'Ollama MCP server', 'local models', and 'model library' give good natural-keyword coverage — a user asking about Ollama or local models would phrase it this way. It falls short of 5 because common synonyms and variations ('LLM', 'offline models', 'run models locally') are absent.

4 / 5

Distinctiveness Conflict Risk

'Ollama' is a clear niche with distinct triggers, unlikely to fire for unrelated skills. It is not a 5 because it overlaps in shape with other local-model integration skills (the body itself references 'add-atomic-chat-tool'), so a user request about 'local models' generically could match more than one skill.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

nanocoai/nanoclaw

Path

.claude/skills/add-ollama-tool/SKILL.md

Reviewed

Table of Contents

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.