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

70%

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

68%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.

The body is a concise, well-sectioned overview with a concrete executable core pattern and sensible guardrails. Its weaknesses are the absence of any multi-step workflow with validation checkpoints and slight overlap between the facts and API-surface sections.

Suggestions

Add a short numbered workflow for the core task (e.g., 1. consult examples/, 2. wire AxCodeRuntime, 3. run forward, 4. verify against no-key transport) with an explicit validation step to lift workflow clarity.

Merge or clearly differentiate 'Package Facts' and 'Relevant API Surface' to remove the overlap and tighten conciseness.

Convert the package-doc references into explicit links (e.g., [API.md](API.md)) and confirm those files ship in the bundle so navigation is genuinely one level deep.

Dimension	Reasoning	Score
Conciseness	The body is lean with terse bullet fact lines like 'Real network support: yes.' and 'Scripted no-key transport support: yes.' and no basic-concept padding, matching 'efficient; minor instances of over-explanation'; not 5 because 'Package Facts' and 'Relevant API Surface' overlap somewhat and could be consolidated.	4 / 5
Actionability	A concrete executable Core Pattern ('let helper = axllm::agent(...)?; helper.forward(&llm, inputs, None)?') plus actionable guardrails ('Start from package examples for exact native syntax') match 'mostly executable guidance; concrete code with minor gaps'; not 5 because the example is minimal and bulk detail is deferred to external package docs rather than covered inline.	4 / 5
Workflow Clarity	No numbered multi-step sequence or validation checkpoints exist; the content is reference/guardrail material ('When To Use', 'Guardrails') rather than a workflow, matching 'steps listed but validation gaps; checkpoints missing'; not 4 because there is no explicit sequence to follow at all, and not lower because the canonical Core Pattern is unambiguous.	3 / 5
Progressive Disclosure	Clear sectioned overview ('When To Use', 'Package Facts', 'Core Pattern', 'Relevant API Surface', 'Guardrails') points one level deep to package docs ('API.md', 'axir-api.json', 'examples/'), matching 'good structure; most content appropriately placed; references mostly clear'; not 5 because references are plain-text mentions rather than links and the section split has minor overlap.	4 / 5
	Total	15 / 20 Passed

Description

71%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.

The description is a clear, niche-scoped trigger with explicit 'Use when' guidance and several concrete capability targets. Its main weakness is jargon-heavy trigger terms and a single compressed action verb that limits both trigger naturalness and specificity.

Suggestions

Add a couple of natural-language synonyms or plainer phrasings alongside the jargon (e.g., 'building agent loops' or 'running actor code') so users can trigger it without knowing exact internal terms.

Vary the action verbs beyond 'writing' (e.g., 'wire', 'run', 'debug') to broaden the stated capability set toward comprehensive coverage.

Consider naming the package context once and then listing capabilities as distinct verb-led actions for a clearer 'what'.

Dimension	Reasoning	Score
Specificity	Quotes 'writing Rust code with `axllm` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles' name several concrete capability targets, matching the 'lists several specific actions; minor gaps' anchor; not 5 because the single verb 'writing' is applied across targets rather than a comprehensive set of distinct actions.	4 / 5
Completeness	Both 'what' ('writing Rust code with `axllm` for ...') and an explicit 'when' ('Use when writing Rust code ...') are present with concrete triggers, matching the 'has both what and when; when could be more explicit' anchor; not 5 because the 'what' is compressed into one action across a list rather than a clearly comprehensive statement of behavior.	4 / 5
Trigger Term Quality	Terms like 'axllm', 'RLM executor loops', 'AxCodeRuntime sessions', and 'runtime envelopes' are domain-accurate but heavily jargon-laden with no common synonyms or variations, fitting 'some relevant keywords but missing common variations'; not 4 because few of these are phrases a user would naturally say verbatim outside this niche.	3 / 5
Distinctiveness Conflict Risk	The Rust + axllm + AxCodeRuntime/RLM niche is highly specific with distinct triggers and minimal overlap with other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor; cannot exceed 5.	5 / 5
	Total	16 / 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: packages/rust/skills/ax-rust-agent-rlm/SKILL.md
Commit: 1abea97

Reviewed: 2 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.