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

77%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/rust/skills/ax-rust-agent-rlm/SKILL.md

Quality

Content

70%

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

A concise, jargon-free body that respects Claude's intelligence and stays on-topic. Its weak spots are actionability (the runnable example is thin and the API surface is named rather than shown) and workflow clarity (no explicit sequencing or validation checkpoints for the code-writing process).

Suggestions

Expand the core pattern into a minimal complete example (including how `llm` and `inputs` are constructed) or show one ProcessCodeRuntime/optional-profile call so guidance is copy-paste ready.

Turn the guardrails into a short numbered workflow with an explicit verification step (e.g., build/cargo check, run a no-key example) so code-generation work has a validation checkpoint.

Convert the file references (API.md, axir-api.json, examples/) into clearly signaled inline links under a dedicated section so navigation is one level deep and unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean: package facts, a 2-line core pattern, and tightly written guardrails with no padding or explanation of concepts Claude already knows — every token earns its place.	3 / 3
Actionability	There is a concrete 2-line Rust core pattern, but the broader guidance is declarative ("Wire an AxCodeRuntime...", "Start from package examples") rather than copy-paste ready; the example references symbols not fully shown and is incomplete for the listed API surface.	2 / 3
Workflow Clarity	"When To Use" and guardrails imply a sequence (start from examples, pick no-key vs provider-api by credential availability) but it is not numbered, and there are no validation/verification checkpoints despite the body touching code generation that could be checked (e.g., building/running).	2 / 3
Progressive Disclosure	The body lists one-level-deep references (API.md, axir-api.json, axir-capabilities.json, examples/) but these are not present in the bundle, and navigation to them is a flat bullet list rather than clearly signaled inline links; structure is decent but not the well-organized split of a 3.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 well-formed third-person description that is specific and complete with an explicit trigger clause, and clearly distinct from other skills. Its main weakness is trigger-term naturalness: most listed capabilities use internal jargon rather than language users would actually say.

Suggestions

Soften the jargon in the trigger: add plain-language phrasing users would say (e.g., "writing Rust code for an LLM agent loop" alongside the existing terms) to improve trigger_term_quality.

Consider grouping the five capability targets into one readable phrase and naming the package once, to keep the description crisp.

Dimension	Reasoning	Score
Specificity	Names a concrete domain ("writing Rust code with `axllm`") and lists several specific targets — "RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles" — matching the multi-action anchor.	3 / 3
Completeness	It answers both "what" (the listed capabilities) and "when" via the explicit "Use when writing Rust code with `axllm`..." clause.	3 / 3
Trigger Term Quality	The natural trigger "writing Rust code with `axllm`" is good, but the remaining terms ("RLM executor loops", "runtime envelopes", "process runtimes") are internal jargon a user would rarely say verbatim; common user variations are missing.	2 / 3
Distinctiveness Conflict Risk	Tightly scoped to the specific generated package `axllm` and Ax runtime terms, giving a clear niche unlikely to trigger 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: 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.