add-atomic-chat-tool

Add Atomic Chat MCP server so the container agent can call local models served by the Atomic Chat desktop app via its OpenAI-compatible API.

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-atomic-chat-tool/SKILL.md

Quality

Content

77%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 executable code, clear phasing, and strong validation checkpoints, making it a strong operational guide. Its weakest area is progressive disclosure: most content lives inline in SKILL.md with limited use of separate reference files, and conciseness could be tightened by trimming redundant explanations.

Suggestions

Trim explanatory asides (e.g. 'the app is a fork of Jan and manages its own model library') that Claude does not need to perform the task.

Move the detailed Troubleshooting or env-var reference material into a separate REFERENCES file and link to it from SKILL.md to improve progressive disclosure.

Avoid restating the registration/allow-pattern relationship multiple times; state it once where the registration is performed.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but includes some explanatory padding (e.g. elaborating on Atomic Chat being a Jan fork, or restating that registration derives the allow-pattern) that could be tightened.	2 / 3
Actionability	Provides fully executable copy-paste bash, complete before/after TypeScript edit blocks, and concrete validation commands — copy-paste ready with specific file paths.	3 / 3
Workflow Clarity	Clear phased sequence (Pre-flight, Apply, Configure, Verify) with explicit validation checkpoints ('All must be clean before proceeding') and a Troubleshooting feedback loop for error recovery.	3 / 3
Progressive Disclosure	Well-organized sections, but the MCP server source and test files are referenced for copying without being part of a navigable reference structure here; there is no in-skill overview pointing to detailed bundled materials, so content is largely inline.	2 / 3
	Total	10 / 12 Passed

Description

67%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 and distinctive, naming concrete integration actions and a clear niche. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which leaves the invocation timing implied rather than stated.

Suggestions

Append an explicit trigger clause, e.g. 'Use when you want to give the container agent access to local models served by Atomic Chat, or when the user mentions local LLMs / Atomic Chat.'

Broaden trigger-term coverage with natural user phrasings like 'local LLM', 'offload to a local model', or 'run inference locally via Atomic Chat'.

Keep the concrete actions but trim any redundant phrasing so the description stays concise while adding the missing 'when' guidance.

Dimension	Reasoning	Score
Specificity	Names concrete actions — adding an MCP server and enabling the agent to call local models via an OpenAI-compatible API — and identifies the specific endpoint and integration points.	3 / 3
Completeness	Clearly states what the skill does, but lacks an explicit 'Use when...' trigger clause telling Claude when to invoke it, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes relevant terms like 'Atomic Chat', 'MCP server', 'local models', and 'OpenAI-compatible API', but omits natural variations a user might say (e.g. 'local LLM', 'offload to local model', 'Jan').	2 / 3
Distinctiveness Conflict Risk	The Atomic Chat / OpenAI-compatible local-model niche is specific and unlikely to be confused with other skills; the 'Add Atomic Chat MCP server' framing carves a clear, distinct trigger.	3 / 3
	Total	10 / 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-atomic-chat-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.