ax-rust-agent-rlm

Use when writing Rust code with `axllm` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.

Quality

86%

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

87%Weight 40%Scale 1-3

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

A concise, actionable reference card for the axllm Rust API with clean sectioning. The gap is workflow clarity for the multi-part runtime tasks it claims to support, which are listed but not sequenced.

Suggestions

Add a short numbered workflow for wiring ProcessCodeRuntime or a runtime profile, including a build/run verification step.

Clarify how the Core Pattern relates to the runtime-profile path so the two usage modes are explicitly sequenced rather than only enumerated.

Dimension	Reasoning	Score
Conciseness	Lean bullet sections and a compact code snippet; it assumes Claude's competence and avoids explaining known concepts, with every token earning its place.	3 / 3
Actionability	Provides an executable Rust core pattern plus named API surface ('agent', 'AxAgent', 'ProcessCodeRuntime') and concrete package file paths, making guidance copy-paste ready.	3 / 3
Workflow Clarity	The single agent/forward pattern is unambiguous, but the advertised runtime-wiring tasks (ProcessCodeRuntime, profiles) have no sequenced steps or validation checkpoints.	2 / 3
Progressive Disclosure	Under 50 lines with well-organized sections (When To Use, Package Facts, Core Pattern, Relevant API Surface, Guardrails) and no bundle files requiring offloading.	3 / 3
	Total	11 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 specific, well-triggered description that clearly answers both what and when within a distinct niche. Its main weakness is jargon-heavy trigger terms that a user may not naturally voice.

Suggestions

Add user-natural phrasings alongside the jargon (e.g. 'building agent loops', 'running generated Rust packages') so the description matches what users actually say.

Consider naming the high-level intent (e.g. 'Build and run RLM agent executors in Rust') before the enumerated API surfaces.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete capabilities ('RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles') rather than vague language.	3 / 3
Completeness	Explicit 'Use when...' clause supplies the trigger, and the 'what' is the list of axllm targets, so both what and when are answered.	3 / 3
Trigger Term Quality	Includes natural terms like 'writing Rust code' and 'axllm', but most triggers ('AxCodeRuntime sessions', 'runtime envelopes', 'process runtimes') are technical jargon a user would rarely say verbatim.	2 / 3
Distinctiveness Conflict Risk	Scoped to Rust + the axllm RLM niche with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ax-llm/ax
Path: packages/rust/skills/ax-rust-agent-rlm/SKILL.md
Commit: fe8baf8

Reviewed: 8 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.