add-ollama-tool

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

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

82%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.

The content is a well-sequenced, highly actionable runbook with real validation checkpoints and a useful troubleshooting section. It is concise and assumes Claude's competence; the main improvement would be adding an explicit post-merge/post-copy verification step to make the workflow gates uniform.

Suggestions

Add an explicit validation checkpoint after the per-group copy loop (e.g., confirm the copied index.ts contains the ollama mcpServers entry before proceeding).

Provide a one-line fallback for the git merge conflict case (e.g., preferred resolution order) so the conflict-handling step is as actionable as the others.

Consider moving the management-tool detail and troubleshooting into a referenced file to keep the main body as a tighter overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and does not over-explain concepts Claude already knows; the only mild padding is the quoted user-prompt blocks, which are justified as ready-to-deliver instructions.	4 / 5
Actionability	Provides copy-paste-ready executable commands throughout (ollama list, git fetch/merge, npm run build, launchctl kickstart, docker run curl probe) covering the common cases.	5 / 5
Workflow Clarity	A clear four-phase sequence with validation checkpoints ('Build must be clean before proceeding', pre-flight skip-if-applied) and troubleshooting feedback loops; slightly below 5 because the batch per-group copy and merge-conflict steps could use a more uniform verify-then-proceed gate.	4 / 5
Progressive Disclosure	The skill is a single self-contained file with well-organized sections and no nested references; it scores 4 rather than 5 because it is ~190 lines whose troubleshooting/management-tool detail could plausibly live in a referenced file, and the in-body path references (e.g. scripts/ollama-watch.sh) point at repo targets rather than skill bundle files.	4 / 5
	Total	17 / 20 Passed

Description

53%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.

The description concretely states what the skill adds but provides no 'Use when' trigger guidance, so it reads as capability-only. Adding an explicit trigger clause and a few synonyms would lift the completeness and trigger-term dimensions.

Suggestions

Add an explicit 'Use when...' clause naming the trigger scenarios (e.g., 'Use when the user wants to add Ollama/local LLM tooling to the container agent').

Include natural synonyms users might say ('local models', 'local LLMs', 'Ollama tools') to broaden trigger-term coverage.

Optionally enumerate the surfaced capabilities more granularly (e.g., 'list, generate with, and manage local Ollama models') to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Ollama MCP server') and two concrete actions ('call local models' and 'manage the Ollama model library'), but the coverage is not comprehensive — it does not enumerate the individual tools surfaced.	3 / 5
Completeness	It has a clear 'what' (add an MCP server exposing Ollama tools and optionally managing the model library) but no 'when' / 'Use when' clause; per the guideline a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant keywords ('Ollama MCP server', 'local models', 'manage the Ollama model library') but lacks common variations or synonyms and omits file/extension-style natural phrasing.	3 / 5
Distinctiveness Conflict Risk	'Ollama MCP server' plus 'local models' and 'model library' is a clearly distinct niche with minimal overlap risk, though the absence of explicit trigger phrases keeps it just below a 5.	4 / 5
	Total	13 / 20 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: 1 missing	Warning

	Total	15 / 16 Passed

Repository: jbaruch/nanoclaw-telegram
Path: .claude/skills/add-ollama-tool/SKILL.md
Commit: 7454673

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.