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

71%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.

Highly actionable content with concrete code and clear multi-stage workflows plus error-recovery loops, but it is a long monolithic reference with repeated guidance across sections and no use of bundle files to offload the bulk API detail.

Suggestions

Move the Option Layout, AxJSRuntime Security options, and llmQuery reference tables into separate reference files (e.g. REFERENCE.md, SECURITY.md) and keep SKILL.md as an overview with one-level-deep links, mirroring how the GitHub example links are already signaled.

De-duplicate the contextPolicy preset definitions, executorModelPolicy semantics, and actor-turn rules so each concept is stated once in its canonical section and only cross-referenced elsewhere.

Consolidate the 'Do Not Generate' list so it only captures rules not already enforced in 'RLM Actor Code Rules', or convert it into a checklist tied back to those rules to reduce restated content.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining general concepts Claude already knows, but it is a ~500-line monolithic reference with noticeable repetition — contextPolicy presets, autoUpgrade, executorModelPolicy, and actor-turn rules are restated across 'Use These Defaults', 'Context Policy Presets', 'Choosing Presets', 'Option Layout', and 'Do Not Generate'.	3 / 5
Actionability	It provides multiple copy-paste-ready, executable snippets — the canonical agent(...) config, actor-turn JS reuse example, llmQuery single and batched forms, runtime permission recipes, and the agent.test(...) harness — covering the common cases with real signatures.	5 / 5
Workflow Clarity	The three-stage pipeline and actor-turn sequence are clearly ordered with explicit feedback loops (inspect Action Log errors, fix on the next turn, validate via agent.test(...)), though some checkpoints are stated as rules rather than embedded step-by-step procedures.	4 / 5
Progressive Disclosure	There are no bundle files and the SKILL.md inlines a large API reference (Option Layout, AxJSRuntime Security, llmQuery Rules) that clearly belongs in separate reference files; section headers are clear and external GitHub example links are one-level-deep and well signaled, which keeps it from scoring lower.	3 / 5
	Total	15 / 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 with explicit what/when structure and comprehensive, natural trigger terms tied to specific API surfaces. The only minor weakness is that the capability statement is a single action rather than a list of several concrete actions.

Dimension	Reasoning	Score
Specificity	Names the concrete domain ('generate correct AxAgent RLM/runtime code using @ax-llm/ax') with a specific package and code-gen action, though it rests on essentially one action supported by a long enumeration of trigger terms rather than listing several distinct capabilities.	4 / 5
Completeness	It explicitly answers both 'what' (helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax) and 'when' (Use when the user asks about ...) with concrete trigger phrases.	5 / 5
Trigger Term Quality	The 'Use when' clause enumerates a comprehensive set of natural API names users would actually say — AxJSRuntime, contextFields, contextPolicy, promptLevel, executorModelPolicy, llmQuery(...), recursionOptions — including synonyms and specific signatures.	5 / 5
Distinctiveness Conflict Risk	It carves a clear niche (AxAgent RLM runtime via @ax-llm/ax) anchored to specific API terms, making overlap with sibling skills minimal; the body further disambiguates against ax-agent / ax-agent-observability / ax-agent-memory-skills.	5 / 5
	Total	19 / 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 (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: 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.