add-ollama-tool

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

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

62%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.

A well-sequenced, highly concrete procedural skill with strong workflow clarity and validation checkpoints. Its weaknesses are the missing bundle source files it claims to ship (hurting actionability and progressive disclosure) and a modest amount of explanatory prose that could be trimmed for conciseness.

Suggestions

Ship the four referenced files (ollama-mcp-stdio.ts, ollama-registration.test.ts, ollama-env.ts, ollama-wiring.test.ts) in the bundle, or remove the cp commands and inline/describe the source so the central step is actually executable.

Trim explanatory prose (e.g. consolidate the repeated "registration is the only thing to check" notes and shorten the troubleshooting section) to improve token efficiency.

If the MCP server source is intentionally kept external, add a clearly signaled one-level-deep reference (e.g. a scripts/ path) so progressive disclosure resolves to a real file.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence with no basic-concept padding, but includes explanatory prose (the "Shared block" rationale, repeated notes that registration is the only thing to check, a long troubleshooting narrative) that could be tightened; matches the mostly-efficient-but-could-be-tighter anchor rather than the every-token-earns-its-place anchor 3.	2 / 3
Actionability	Provides copy-paste-ready cp commands, exact before/after index.ts edits, env-var lines, and validation commands, but the core artifacts it instructs you to copy (ollama-mcp-stdio.ts, ollama-env.ts, and the two test files) are not present in the bundle, leaving the guidance incomplete for the central step; not 3 because key files are missing, not 1 because the edits shown are fully executable.	2 / 3
Workflow Clarity	A clear four-phase sequence (Pre-flight, Apply, Configure, Verify) with an explicit validation checkpoint ("All must be clean before proceeding"), idempotency skip, and error-recovery troubleshooting matches the clear-sequence-with-explicit-validation anchor; not 2 because checkpoints and feedback loops are explicit.	3 / 3
Progressive Disclosure	The SKILL.md is well-organized into phases, but it signals four bundle files via cp $S/... (the MCP server source and tests) that do not exist in the bundle (no references/, scripts/, or assets/ dirs), so the cross-file structure is broken; matches the references-present-but-not-resolving/better-organized anchor rather than the well-signaled-resolving-references anchor 3, and not the monolithic-unstructured anchor 1.	2 / 3
	Total	9 / 12 Passed

Description

82%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.

A concise, specific, third-person description that clearly states what the skill does and occupies a distinct niche. Its main weakness is the absence of an explicit "Use when..." trigger clause, leaving the "when should Claude use it" half of completeness only implied.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to expose local Ollama models to the container agent, or to manage the Ollama model library from the agent."

Include a few more natural trigger phrasings users might say (e.g. "add ollama", "use local models", "pull/manage ollama models") to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the concrete primary action ("Add Ollama MCP server") plus two distinct capability groups ("call local models" and "manage the Ollama model library"), matching the multiple-specific-actions anchor; not the vague single-domain wording of score 2.	3 / 3
Completeness	Clearly answers "what" but has no "Use when..." clause or explicit trigger guidance for "when", which per the rubric caps completeness at 2; it is not 1 because the what is fully stated.	2 / 3
Trigger Term Quality	Natural terms a user would say are present ("Ollama", "MCP server", "local models", "model library") with good coverage for this niche; not generic jargon-only (score 1) nor missing common variations (score 2).	3 / 3
Distinctiveness Conflict Risk	"Add Ollama MCP server" is a clear niche with distinct triggers unlikely to overlap with unrelated skills; matches the distinct-niche anchor rather than the generic/could-overlap wording of scores 1-2.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nanocoai/nanoclaw
Path: .claude/skills/add-ollama-tool/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.