Name: ax-agent-rlm
Rating: 68 (1 reviews)
Author: ax-llm

ax-agent-rlm

This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions, or long-running agent runtime behavior.

Quality

83%

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 thorough, highly actionable reference with executable examples and a clear actor-loop workflow, but it is long and internally repetitive, and keeps detailed API material inline rather than splitting it into referenced files.

Suggestions

Remove the redundancy between "Do Not Generate" and "RLM Actor Code Rules" — consolidate into one checklist so the don'ts are stated once.

Collapse the repeated preset guidance in "Choosing Presets, Prompt Level, And Model Size" by cross-referencing "Context Policy Presets" instead of restating each preset.

Split the long-form API reference (Option Layout, AxJSRuntime Security, Custom Code Runtimes) into separate reference files linked from SKILL.md to improve progressive disclosure and token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is dense library-specific API behavior Claude would not already know, but at ~500 lines it carries real redundancy — "Do Not Generate" recapitulates "RLM Actor Code Rules" and "Choosing Presets..." re-explains "Context Policy Presets" — so it could be tightened and is not a 3.	2 / 3
Actionability	Multiple complete executable examples (canonical agent config, agent.test harness, llmQuery fan-out, runtime security recipes, reuse snippet) are copy-paste ready, matching the score-3 anchor.	3 / 3
Workflow Clarity	The actor turn loop is explicitly sequenced (one observable step per turn, inspect→log→stop, continue next turn) with an explicit error-recovery feedback loop and a validation path via agent.test(...), so it is not the sequence-with-gaps score-2 case.	3 / 3
Progressive Disclosure	No bundle files exist and all reference-grade detail (option layout, security, custom runtimes) is inline in one monolithic SKILL.md; section headers and one-level external example links are well-signaled, but content is not split into files, so it is not a 3.	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, third-person description that clearly states what the skill does and gives explicit, library-specific trigger terms. The only weakness is that it describes a single primary action rather than enumerating multiple concrete capabilities.

Dimension	Reasoning	Score
Specificity	"helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax" names the domain and one concrete action, but unlike the score-3 anchor it does not list multiple distinct concrete actions (e.g. extract/fill/merge), and it is not vague enough for a 1.	2 / 3
Completeness	It states what ("helps an LLM generate correct AxAgent RLM/runtime code") and an explicit when ("Use when the user asks about..."), clearly answering both, so it is not capped at 2.	3 / 3
Trigger Term Quality	"RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, ... llmQuery(...), recursionOptions, or long-running agent runtime behavior" gives broad coverage of the actual API terms a @ax-llm/ax user would naturally say, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	It pins a specific library (@ax-llm/ax) and niche APIs (AxJSRuntime, llmQuery, executorModelPolicy), forming a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 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 (502 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-rlm/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.