Name: ax-mcp
Rating: 68.8 (1 reviews)
Author: ax-llm

ax-mcp

This skill helps an LLM build correct native Model Context Protocol integrations with @ax-llm/ax. Use when the user asks about AxMCPClient, MCP transports, tools, prompts, resources, subscriptions, tasks, sampling, elicitation, roots, authentication, OAuth, MCP Apps, recording/replay, or MCP integration with AxGen, AxAgent, AxFlow, chat, optimization, and AxEventRuntime.

Quality

83%

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

Quality

Content

76%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 body is highly actionable with executable TS examples and assumes Claude's domain knowledge, but it reads as a dense API reference rather than a sequenced workflow and leans on external docs that are not present as bundle files.

Suggestions

Add an explicit end-to-end integration workflow (attach client -> authorize tool calls -> validate catalog -> forward) with validation checkpoints for side-effecting operations to lift workflow_clarity above 3.

Move the dense OAuth RFC and generated-language detail into a referenced doc file, keeping only the essential TS snippet inline, to tighten conciseness.

Create the referenced bundle files (docs/MCP_SUBSCRIPTIONS.md, docs/MCP_UCP.md) under references/ or scripts/ so the signaled one-level-deep references actually resolve.

Dimension	Reasoning	Score
Conciseness	It largely assumes Claude's competence (no "what is MCP" padding) and stays tight, though the OAuth and Subscriptions sections pack dense RFC and edge-case detail inline that could be trimmed or pushed to references.	4 / 5
Actionability	Multiple concrete, copy-paste TypeScript blocks specify exact class names, options, runtime paths (e.g. mcp.docs.resources.read(uri)) and cover the common integration cases.	5 / 5
Workflow Clarity	The body is organized as a reference catalog with a Testing Checklist and Non-Negotiable Rules, but side-effecting MCP operations lack an explicit sequenced validate-fix-retry loop, so workflow clarity is capped at 3.	3 / 5
Progressive Disclosure	Section headers are clear and one-level-deep references are well signaled (docs/MCP_SUBSCRIPTIONS.md, docs/MCP_UCP.md, src/examples/mcp-event-demo-server.ts, ax-event-runtime skill), but no bundle files exist under references/scripts/assets to verify the referenced paths resolve.	4 / 5
	Total	16 / 20 Passed

Description

91%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 is third-person, concise, and clearly answers both what the skill does and when to use it with a strong concrete trigger list. It is one of the better-structured descriptions, with only slight specificity and overlap-risk room for improvement.

Dimension	Reasoning	Score
Specificity	"build correct native Model Context Protocol integrations with @ax-llm/ax" names the domain and a concrete action, and the trigger list enumerates several specific sub-capabilities (transports, prompts, resources, tasks, sampling, elicitation, OAuth), with only minor coverage gaps.	4 / 5
Completeness	It explicitly states the what ("build correct native Model Context Protocol integrations with @ax-llm/ax") and a concrete when clause ("Use when the user asks about ...") with explicit trigger phrases.	5 / 5
Trigger Term Quality	"Use when the user asks about AxMCPClient, MCP transports, tools, prompts, resources, subscriptions, tasks, sampling, elicitation, roots, authentication, OAuth, MCP Apps" gives comprehensive coverage of the natural API-surface terms a user would mention.	5 / 5
Distinctiveness Conflict Risk	The @ax-llm/ax-native MCP niche is clearly distinguished from generic MCP skills via specific class and feature triggers, with only minor overlap risk against adjacent Ax skills.	4 / 5
	Total	18 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ax-llm/ax
Path: website/static/typescript/.well-known/agent-skills/ax-mcp/SKILL.md
Commit: 1abea97

Reviewed: ~18 hours 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.