Name: ax-agent
Rating: 71.2 (1 reviews)
Author: ax-llm

ax-agent

This skill helps an LLM generate correct core AxAgent code using @ax-llm/ax. Use when the user asks about agent(), child agents, namespaced functions, discovery mode, clarification, bubbleErrors, host-side final/clarification protocol, or ordinary agent runtime behavior. For MCP clients, native runtime modules, subscriptions, tasks, or authentication use ax-mcp alongside this skill. For RLM/code-runtime work use ax-agent-rlm; for callbacks and telemetry use ax-agent-observability; for recall/memory/skill loading use ax-agent-memory-skills; for agent.optimize(...) use ax-agent-optimize.

Quality

88%

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

Quality

Content

77%

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

A highly actionable, well-structured codegen reference with clear decision and resume workflows, but it is long for a single file with cross-section redundancy and no progressive disclosure into bundle reference files for the bulky API surface.

Suggestions

De-duplicate rules that recur across 'Critical Rules', dedicated sections, and 'Do Not Generate' (e.g. discovery and bubbleErrors), keeping each rule in one canonical location and cross-referencing it.

Move the exhaustive 'Core API Reference' and 'Public Surface' listings into a reference bundle file (e.g. references/api.md) and link to it one level deep, keeping SKILL.md as a tighter overview.

Drop the sibling-skill routing list from the body since it already appears verbatim in the frontmatter description, or reduce it to a single forward pointer.

Dimension	Reasoning	Score
Conciseness	The body is dense and rule-based without basic-concept padding, but at ~690 lines it restates rules across sections (discovery and bubbleErrors appear in Critical Rules, dedicated sections, and Do Not Generate) and repeats sibling-skill routing already in the description, so not every token earns its place.	2 / 3
Actionability	Provides numerous complete, executable TypeScript examples with imports (Canonical Pattern, Child Agents, Clarification/Resume, Bubble Errors, Discovery) plus specific copy-paste-ready rules, fully actionable rather than abstract.	3 / 3
Workflow Clarity	The Decision Guide sequences intent to agent shape, the clarification/resume pattern is an explicitly ordered multi-step process with error handling (catch AxAgentClarificationError -> getState -> setState -> forward), and discovery includes an error-recovery feedback loop; Do-Not-Generate and Critical Rules serve as checklists.	3 / 3
Progressive Disclosure	Sections are well-organized with clear headers, but the skill is a single monolithic file with no bundle files (references/scripts/assets are empty), and large API-reference material ('Core API Reference', 'Public Surface') is inline rather than split into one-level-deep reference files.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 high-quality description: concrete primary action, explicit trigger terms in a 'Use when...' clause, and strong distinctiveness via sibling-skill routing. It is information-dense rather than padded with fluff.

Dimension	Reasoning	Score
Specificity	States a concrete primary action ('generate correct core AxAgent code using @ax-llm/ax') and enumerates multiple specific concrete capabilities such as 'child agents', 'namespaced functions', 'discovery mode', 'clarification', and 'bubbleErrors' rather than vague language.	3 / 3
Completeness	Clearly answers 'what' ('helps an LLM generate correct core AxAgent code') and 'when' with an explicit 'Use when...' trigger clause, satisfying both halves.	3 / 3
Trigger Term Quality	An explicit 'Use when the user asks about...' clause lists many natural domain terms (agent(), child agents, discovery mode, bubbleErrors) that a user of @ax-llm/ax would actually say, giving good trigger coverage.	3 / 3
Distinctiveness Conflict Risk	Explicitly routes overlapping concerns to sibling skills ('use ax-mcp', 'use ax-agent-rlm', 'use ax-agent-observability', 'use ax-agent-memory-skills', 'use ax-agent-optimize'), carving a clear niche unlikely to trigger the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (694 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: ax-llm/ax
Path: website/static/typescript/.well-known/agent-skills/ax-agent/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.