ax-rust-ai

Use when writing Rust code with `axllm` for named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.

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-ai/SKILL.md

Quality

Content

58%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, reference-rich skill body that excels at progressive disclosure and routing workflows. It is held back from the top band by dense prose edge-case rules and thin executable code coverage for common cases.

Suggestions

Add 1-2 complete, copy-pasteable Rust examples for the common cases (named profile + structured output, basic routing) instead of relying on pointers to examples/.

Move the long provider-specific edge-case rules (e.g., per-model Vertex/thinking defaults) into a reference file and summarize the decision rule inline.

Add an explicit validation/verification step (e.g., run the no-key scripted example to confirm routing before live calls) to close the workflow checkpoint gap.

Dimension	Reasoning	Score
Conciseness	The body is dense with provider-specific edge-case rules (e.g., the Vertex `google/gemma-4-26b-a4b-it-maas` rule, thinking-level defaults) that assume Claude's intelligence but pile up into long prose bullets; it is mostly efficient but several passages could be tightened or moved to references.	3 / 5
Actionability	It gives concrete API symbols and named factories, but the single core code example is a two-line snippet and most guidance is descriptive rules rather than copy-paste-ready executable code covering common cases, leaving key details implicit.	3 / 5
Workflow Clarity	Sequences for routing/balancing and credential handling are laid out with explicit decision guidance (start from examples, opt-in for adaptive, no auto-replay on 401/403), and Guardrails act as checkpoints; minor validation gaps remain since there is no explicit verify-after-run step.	4 / 5
Progressive Disclosure	Content is well sectioned and points to real bundle paths (examples/, API.md, axir-api.json, axir-capabilities.json) at one level of depth with clear signaling; the API surface and capability lists are inline rather than in separate files, a minor organization gap.	4 / 5
	Total	14 / 20 Passed

Description

81%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, third-person description that pairs concrete capabilities with an explicit 'Use when...' trigger and a recognizable package name. Slight verbosity from enumerating many provider surfaces keeps it just short of perfect.

Suggestions

Tighten the long enumeration of provider names into a shorter cluster of high-value trigger terms to reduce length while preserving discoverability.

Consider leading with the user intent (e.g., 'writing Rust code that calls LLM providers') before the package name so the trigger reads more naturally.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions (writing Rust code, named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, balancers), giving good coverage with minor gaps since it leans more on enumeration of surfaces than discrete user-facing actions.	4 / 5
Completeness	It explicitly answers both 'what' (write Rust code with `axllm` for the listed provider/routing capabilities) and 'when' (the 'Use when writing Rust code with `axllm` for...' clause) with concrete trigger phrases.	5 / 5
Trigger Term Quality	It surfaces natural terms users would say (Rust, OpenAI, Gemini, Anthropic, routers, balancers, provider clients) with good keyword coverage, though it omits synonyms or file-extension-style triggers and front-loads internal package names like `axllm`.	4 / 5
Distinctiveness Conflict Risk	The `axllm` / Rust / multi-provider deployment niche is fairly distinct, but the breadth of provider names (OpenAI, Gemini, Anthropic) creates some overlap risk with generic provider-SDK skills; it is mostly distinct with minor overlap.	4 / 5
	Total	17 / 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-ai/SKILL.md
Commit: 1abea97

Reviewed: ~16 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.