CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

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.

A high-quality, information-dense reference with executable code and explicit validation/cleanup guidance. It assumes competence and avoids concept padding; the main weaknesses are occasional verbosity in enumerations and substantial inlined detail that could be pushed deeper into the referenced docs files.

Suggestions

Move the most detailed lifecycle material (e.g. the long subscriptions ownership and era-aware listening paragraphs) into docs/MCP_SUBSCRIPTIONS.md, keeping SKILL.md as a tighter overview with signaled links.

Condense the long OAuth feature enumeration into a compact list or push it to docs/MCP_UCP.md so the inline section stays scannable.

Add a short numbered 'integration workflow' at the top (choose transport -> create client -> attach to AxGen/AxAgent/AxFlow -> validate via testing checklist) to give a clear end-to-end sequence with checkpoints.

DimensionReasoningScore

Conciseness

Dense, domain-specific guidance that assumes Claude's competence and avoids explaining basic concepts, with only minor stretches (e.g. the long OAuth feature enumeration) that could be tightened; not quite lean enough for 5.

4 / 5

Actionability

Provides copy-paste-ready TypeScript examples, specific API calls, concrete commands (npm run test:mcp-oauth, npm run test:mcp-events:generated), and exact env vars covering the common integration cases.

5 / 5

Workflow Clarity

Sections are logically ordered and include a Testing Checklist with explicit validation steps plus cleanup-in-finally guidance, but as a reference manual it lacks a single tight step-sequence with feedback loops throughout, so it falls short of 5.

4 / 5

Progressive Disclosure

Well-structured with clear section headers and clearly signaled one-level-deep references (docs/MCP_SUBSCRIPTIONS.md, docs/MCP_UCP.md, checked-in examples); no bundle files exist to verify, and some detailed subsections are inlined that could live in the referenced docs, keeping it below 5.

4 / 5

Total

17

/

20

Passed

Description

95%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.

A strong, third-person description that clearly states what it does and when to use it with a comprehensive trigger list. It is highly distinctive and unlikely to fire for the wrong skill; the only minor gap is that it centers on one main action rather than enumerating several distinct concrete actions.

DimensionReasoningScore

Specificity

Names the domain and concrete action ('build correct native Model Context Protocol integrations with @ax-llm/ax') and enumerates multiple integration surfaces, but the action set is essentially singular rather than a list of distinct concrete actions, so it sits below 5.

4 / 5

Completeness

Explicitly answers 'what' (build correct native MCP integrations with @ax-llm/ax) and 'when' via a concrete 'Use when the user asks about ...' trigger clause listing specific phrases.

5 / 5

Trigger Term Quality

Comprehensive enumeration of natural terms a user would say (AxMCPClient, MCP transports, tools, prompts, resources, subscriptions, tasks, sampling, elicitation, roots, authentication, OAuth, MCP Apps, recording/replay, AxGen, AxAgent, AxFlow, AxEventRuntime), including synonyms.

5 / 5

Distinctiveness Conflict Risk

A clear niche (native MCP with @ax-llm/ax) with highly specific triggers like AxMCPClient and AxGen, making conflict with unrelated skills minimal.

5 / 5

Total

19

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
ax-llm/ax
Reviewed

Table of Contents

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.