Name: ax-mcp
Rating: 69.6 (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

85%

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

80%

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

A highly actionable, lean technical reference with strong executable examples and good validation coverage in the test checklist. Its weaknesses are reference-style rather than sequenced-workflow organization and limited progressive disclosure: the main external reference target is not in the bundle and much API detail is inline.

Suggestions

Add a short end-to-end 'Quick start' or sequenced workflow at the top with explicit checkpoints (attach client -> discover catalog -> authorize -> run -> verify -> close in finally) to raise workflow clarity.

Move the subscriptions/event-runtime and authentication/OAuth detail into a referenced file (e.g. docs/MCP_SUBSCRIPTIONS.md) and ensure it actually exists in the bundle so progressive disclosure is one level deep rather than inline.

Add a brief feedback-loop note for side-effecting tool calls (what to do on an uncertain post-side-effect failure besides 'never blindly replay') to strengthen error recovery guidance.

Dimension	Reasoning	Score
Conciseness	The body is dense and reference-style, assuming Claude's competence throughout (no preamble explaining what MCP/HTTP/SSE are); every section carries substantive technical detail with no fluff, even across its length.	3 / 3
Actionability	Multiple complete, executable TypeScript blocks (transport + client setup, AxGen forward with mcpContext, AxAgent, catalog reads, task handling, event source/runtime) with concrete options and API names make the guidance copy-paste ready.	3 / 3
Workflow Clarity	Validation is present via the Testing Checklist (assert collisions fail, test denial before execution, close in finally), but the document is organized as a per-feature reference rather than a single clearly sequenced end-to-end workflow with explicit checkpoints between stages.	2 / 3
Progressive Disclosure	Sections are well-organized with clear headers and one clearly signaled external reference ('read docs/MCP_SUBSCRIPTIONS.md'), but no bundle files exist (empty/absent references, scripts, assets) and the referenced docs file is not present, while substantial API reference content remains inline in a ~400-line SKILL.md.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 strong description: third-person, explicit 'Use when' triggers, broad natural keyword coverage, and a clearly delineated niche. The only weakness is that it enumerates subsystems rather than multiple distinct concrete actions, capping specificity at 2.

Dimension	Reasoning	Score
Specificity	The lead verb 'helps an LLM build correct native Model Context Protocol integrations' names the domain and a concrete action, and the description enumerates many subsystems (transports, tools, prompts, resources, subscriptions, tasks, sampling, elicitation, roots, auth, OAuth, MCP Apps, recording/replay), but the action verbs are thin ('build', 'asks about') rather than a list of multiple distinct concrete actions.	2 / 3
Completeness	It answers both 'what' ('helps an LLM build correct native Model Context Protocol integrations with @ax-llm/ax') and 'when' with an explicit 'Use when the user asks about ...' trigger clause.	3 / 3
Trigger Term Quality	The explicit 'Use when the user asks about ...' clause lists a broad set of API and concept names (AxMCPClient, MCP transports, prompts, resources, subscriptions, tasks, sampling, elicitation, OAuth, MCP Apps, AxGen, AxAgent, AxFlow, AxEventRuntime) that users would naturally mention when they need this skill.	3 / 3
Distinctiveness Conflict Risk	It targets a very specific niche (native MCP integration with @ax-llm/ax) with distinctive API-level triggers, making it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 12 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: 7911e27

Reviewed: 5 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.