Name: ax-agent
Rating: 68.8 (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

85%

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

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 highly actionable, well-structured codegen reference with extensive executable examples and clear decision guidance. Its main weaknesses are redundancy of rules across sections and a few verbose/marketing-flavored passages that could be tightened.

Suggestions

De-duplicate rules that recur across 'Use These Defaults', 'Critical Rules', and per-feature 'Rules' blocks (e.g. child agents in functions[...], discover() batching) by stating them once and cross-referencing.

Trim time-sensitive/marketing prose such as the relevanceRanking A/B-gate sentence to a factual one-line description and defer detail to ax-agent-memory-skills.

Consider moving the Core API Reference, Public Surface, and generated-language observer tables into a bundled REFERENCE file to slim the SKILL.md overview, since no bundle currently exists.

Dimension	Reasoning	Score
Conciseness	The body is dense with non-obvious API specifics Claude does not already know and avoids tutorial prose, but several rules are repeated across sections (child-agents-in-functions, discover() guidance) and the relevanceRanking paragraph carries marketing-flavored, time-sensitive prose ('after its A/B gate passed on both small and frontier models') that could be trimmed, keeping it below the lean 5.	4 / 5
Actionability	Provides numerous copy-paste-ready, fully executable TypeScript examples (Canonical Pattern, Child Agents, Tool Functions, Clarification/Resume, Bubble Errors, Discovery) that cover the common cases, matching the top anchor.	5 / 5
Workflow Clarity	A clear Decision Guide maps user intent to agent shape, reinforced by Critical Rules and a Do Not Generate checklist; as a codegen skill it has no destructive/batch operation requiring validate-fix-retry loops, so it does not reach the explicit-checkpoint 5 but is well above the implicit-gap 3.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with one-level-deep, clearly signaled references (external example URLs and sibling-skill routing); no bundle files are provided, and some inline API reference (Core API Reference, Public Surface, language tables) could be split into a separate reference file, which is a minor organization gap rather than a structural problem.	4 / 5
	Total	17 / 20 Passed

Description

87%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, specific description that clearly states what the skill does and when to use it, with explicit deconfliction routing to sibling skills. Minor keyword-synonym gaps keep trigger quality just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('generate correct core AxAgent code using @ax-llm/ax') and lists several concrete API features (agent(), child agents, namespaced functions, discovery mode, clarification, bubbleErrors, host-side final/clarification protocol), with only minor coverage gaps; not a full enumeration of every action, so it sits below the comprehensive 5.	4 / 5
Completeness	Explicitly answers both 'what' ('helps an LLM generate correct core AxAgent code using @ax-llm/ax') and 'when' ('Use when the user asks about ...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good keyword coverage of the Ax API surface ('agent()', 'child agents', 'discovery mode', 'clarification', 'bubbleErrors') that an Ax user would naturally say, but it lacks synonyms or file extensions (e.g. .ts, TypeScript agents) that would lift it to 5.	4 / 5
Distinctiveness Conflict Risk	Defines a clear niche (core AxAgent codegen) and explicitly routes MCP/RLM/observability/memory/optimize concerns to five named sibling skills, minimizing conflict risk.	5 / 5
	Total	18 / 20 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 (696 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: 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.