ax-rust-refine

Use when writing Rust code with `axllm` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.

Quality

62%

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-refine/SKILL.md

Quality

Content

57%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 concise and well-organized with a clear API surface and useful guardrails, but its inline code is a shape rather than a runnable example and every detailed reference points to files that are absent from the bundle. Workflow guidance also lacks the validation feedback loop that iterative refinement calls for.

Suggestions

Provide a complete, runnable Rust example (with setup of request/evaluator/options) inline or ensure the referenced examples/ and API.md files actually ship in the bundle.

Add an explicit iterative-refinement workflow with a validation checkpoint (e.g., run optimize, inspect evaluator score, adjust and re-run).

Either include the referenced files (API.md, axir-api.json, axir-capabilities.json) in the bundle or remove the dangling references.

Dimension	Reasoning	Score
Conciseness	The body is lean with well-scoped sections (When To Use, Package Facts, Core Pattern, API Surface, Guardrails) and no padding or explanation of concepts Claude already knows; only minor tightening is possible.	4 / 5
Actionability	The Core Pattern gives a concrete Rust snippet ("axllm::AxGEPA::new(reflection_client, options)?" / "engine.optimize(request, evaluator)?") but it uses undefined variables and is a call shape rather than copy-paste runnable code, and the referenced detail files (API.md, examples/) do not exist in the bundle.	3 / 5
Workflow Clarity	A rough sequence is implied (load examples, build engine, optimize with evaluator) but there is no explicit multi-step workflow and no validation/feedback checkpoint for an inherently iterative refinement process.	3 / 5
Progressive Disclosure	Sections are clearly organized and references (API.md, axir-api.json, axir-capabilities.json, examples/) are explicitly signaled, but none of these referenced files actually exist in the bundle, so the navigation does not resolve.	3 / 5
	Total	13 / 20 Passed

Description

67%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 well-structured with an explicit Use-when clause and a clear, niche domain, but its trigger vocabulary is heavier on framework jargon than on phrases users actually say. Specificity is good but slightly abstract.

Suggestions

Add natural user-facing trigger terms (e.g., "improve LLM outputs", "iterate on candidate responses", "refine Rust generation") alongside the technical jargon.

Broaden the 'when' clause with concrete situations (e.g., "when you need evaluator-driven improvement of generated Rust LLM output").

Dimension	Reasoning	Score
Specificity	Names the domain ("writing Rust code with `axllm`") and several concrete actions ("reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns"), though the actions lean toward abstract patterns rather than concrete operations, so it falls short of comprehensive.	4 / 5
Completeness	Explicitly answers both what (the four refinement capabilities) and when ("Use when writing Rust code with `axllm`"), with the when being concrete; not a 5 because the trigger phrase is singular and could cover more user phrasings.	4 / 5
Trigger Term Quality	"writing Rust code" is a natural trigger, but the remaining terms ("optimizer-backed refinement patterns", "reward-scored generation") are technical jargon users would rarely say, missing common natural variations.	3 / 5
Distinctiveness Conflict Risk	The pairing of Rust + the specific `axllm` package carves a clear niche with low overlap risk, though it could still brush against general Rust LLM-generation skills.	4 / 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: packages/rust/skills/ax-rust-refine/SKILL.md
Commit: 781623e

Reviewed: 1 day 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.