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

79%

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 ./website/static/rust/.well-known/agent-skills/ax-rust-agent-rlm/SKILL.md

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 lean, well-structured reference skill: no padding, concrete core-pattern code, and crisp guardrails that direct the agent to package examples and AxIR as the source of truth. Minor gaps keep it just below top marks: the core snippet has undefined variables, no explicit verification step is given, and referenced API/example files cannot be verified in this bundle.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is lean with zero padding: every line carries package-specific facts ("Real network support: yes", "Runtime profiles: `javascript-quickjs`"), a two-line core pattern, and directive guardrails. Nothing explains concepts Claude already knows; every token earns its place.	5 / 5
Actionability	The core pattern is concrete Rust and the example-selection guidance (no-key vs provider-api) is executable, but `llm` and `inputs` in the snippet are undefined, so it is not copy-paste ready. It sits at 'mostly executable guidance with minor gaps', below fully copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	For this simple single-purpose reference skill the flow (When To Use -> core pattern -> guardrails) is unambiguous, and guardrails act as checkpoints (use no-key examples for deterministic local checks). Not 5 because no explicit verification step (e.g., a compile/build check against the package examples) is included.	4 / 5
Progressive Disclosure	The body is a well-organized overview with one-level-deep pointers to `API.md`, `axir-api.json`, `axir-capabilities.json`, and `examples/`, keeping the main file slim. Not 5 because those referenced files are not verifiable in this bundle (no references/ directory) and the pointers are terse fact-list entries rather than clearly signalled per-topic navigation.	4 / 5
	Total	17 / 20 Passed

Description

68%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 highly distinctive, well-triggered description for a niche Rust package, with an explicit 'Use when' clause and domain-specific keywords. Its main weakness is specificity: it names the domain and constructs but states no concrete capability actions, leaving the 'what' implicit in the trigger clause.

Suggestions

Add 2-3 concrete capability verbs to the description, e.g. 'Wire AxCodeRuntime or ProcessCodeRuntime actor-code sessions, build RLM executor loops with `axllm`, and configure runtime envelopes and profiles' so the 'what' is stated explicitly rather than implied by the 'Use when' clause.

Include the natural trigger variations users would say that currently appear only in the body, such as 'ProcessCodeRuntime', 'AxAgent', 'AxCodeSession', and 'actor-code sessions'.

State the what and when as two separate elements (capabilities first, then 'Use when ...') to reach full completeness, matching the top anchor pattern.

Dimension	Reasoning	Score
Specificity	The description names the domain ("writing Rust code with `axllm`") and target constructs ("RLM executor loops, AxCodeRuntime sessions, runtime envelopes"), but the only action is the generic "writing Rust code ... for" with no concrete capability verbs. It matches anchor 2 (names domain, minimal/generic actions) rather than 3, which requires 1-2 discrete concrete actions.	2 / 5
Completeness	Has an explicit "Use when ..." trigger and an embedded what (writing Rust code with `axllm` for these constructs). Not 5 because the what is implicit in the when-clause rather than stated as concrete capabilities with trigger phrases; clearly above 3 since both what and when are present.	4 / 5
Trigger Term Quality	Good keyword coverage of terms a user of this package would naturally say ("Rust code", "axllm", "AxCodeRuntime", "runtime envelopes", "process runtimes", "runtime profiles"). Not 5 because natural variations used elsewhere in the skill body ("ProcessCodeRuntime", "AxAgent", "AxCodeSession", "actor-code sessions") are missing from the description.	4 / 5
Distinctiveness Conflict Risk	Highly niche triggers (`axllm`, AxCodeRuntime, RLM executor loops) give this a clear, distinct niche with minimal conflict risk against other skills; no generic language that would cause false triggers.	5 / 5
	Total	15 / 20 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: website/static/rust/.well-known/agent-skills/ax-rust-agent-rlm/SKILL.md
Commit: 3f630a0

Reviewed: 3 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.