ax-rust-gen

Use when writing Rust code with `axllm` for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.

Quality

84%

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

76%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 well-organized, token-efficient reference skill with concrete API detail and clear external references. Its main gap is the absence of explicit validation/feedback-loop checkpoints in its workflows.

Suggestions

Add an explicit validation step in the multi-sampling flow (e.g., verify candidate indices fall within 0..N-1 before returning, and fix/retry on parse failures) to introduce a clear validate→fix→retry loop.

Include one fully copy-paste-runnable example (with provider wiring) inline so the Core Pattern is executable standalone, not just a partial snippet.

Move the bulk of the inline API surface (Provider Forward Options, Multi-Sampling, Relevant API Surface) into the referenced API.md and keep SKILL.md as an overview with pointers, to sharpen progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Lean and dense with no padding or re-explanation of concepts Claude already knows; every line (Package Facts, Core Pattern, terse bullets) earns its place.	5 / 5
Actionability	Names exact API symbols (`ax`, `AxGen`, `tool`, `AxMCPClient`) and exact field/enum values (`sampleCount`, `structuredOutputMode` = auto/native/function/json_object), but the code snippets are partial rather than fully copy-paste-runnable programs and full executability is deferred to examples/.	4 / 5
Workflow Clarity	A rough sequence exists (build program → forward) and Guardrails offer do/don't guidance, but there are no explicit validation checkpoints or validate→fix→retry feedback loops for the multi-step generation flows.	3 / 5
Progressive Disclosure	Clear structure with one-level-deep references signaled under Package Facts (API.md, axir-api.json, axir-capabilities.json, examples/), though a fair amount of API surface is inlined that could live in the referenced files.	4 / 5
	Total	16 / 20 Passed

Description

92%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 strong, specific description that pairs a concrete 'Use when...' trigger with a comprehensive list of capabilities. Only marginal room to improve via file extensions and a few more synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain (Rust with `axllm`) and lists multiple concrete actions — forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (writing Rust code with `axllm` for AxGen programs and the listed features) and when (leads with 'Use when...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good keyword coverage including natural phrases a user of this package would say ('writing Rust code', 'multi-sampling', 'result pickers', 'streaming', 'tools'), but lacks file extensions (e.g. `.rs`) and some common synonyms, capping it below 5.	4 / 5
Distinctiveness Conflict Risk	A clear niche — Rust code with the generated `axllm` package for AxGen — with distinct, specific triggers and minimal risk of overlapping unrelated skills.	5 / 5
	Total	19 / 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-gen/SKILL.md
Commit: 1abea97

Reviewed: ~18 hours 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.