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

69%

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-ai/SKILL.md

Quality

Content

46%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 information-dense with genuine package-specific knowledge (profiles, retries, routing, error semantics), but it is organized as a monolithic reference: one tiny code snippet, unwieldy compound-sentence prose, deep reference material inlined, and no bundle files backing the many cited paths. It reads as generated documentation dumped into SKILL.md rather than a navigable skill overview.

Suggestions

Ship the referenced bundle files (API.md, axir-capabilities.json, examples/) or remove/repair the dangling pointers, so cited paths resolve to real files in the skill.

Move model-specific minutiae (GPT-5.x/Anthropic/Gemini sampling rules, Astra session-work internals) into one-level-deep reference files, keeping SKILL.md as a concise overview with clearly signaled links.

Add one complete, executable Rust example (client construction with options, a call, and error handling) inline so the common path is copy-paste ready before deferring to examples/.

Dimension	Reasoning	Score
Conciseness	Almost every sentence carries package-specific facts rather than concepts Claude already knows, but sections like the per-model sampling rules ('A client starts from its provider's defaults: temperature 0, or temperature 0.7 and top-p 1 for `openai-responses`...') and the 25-line 'Astra Session Work' section are walls of 100+ word compound sentences that need significant tightening, and repeated 'as in TypeScript' parity clauses add tokens without Rust-relevant instruction.	3 / 5
Actionability	Concrete specifics exist (exact API names like `AxAIServiceTimeoutError`, `retry: { maxRetries: 0 }`, defaults, error message formats), but the only executable code is the two-line Core Pattern snippet and every example pointer (`examples/`, `src/examples/rust/generation/`) references files absent from the bundle, leaving key usage details (e.g. a complete client construction with options) unshown.	3 / 5
Workflow Clarity	'When To Use' and 'Guardrails' give entry-point direction and prioritization ('Start with `examples/adaptive_balancer_no_key`...'), but the body is a thematic reference with no sequenced process or validation checkpoints. No destructive or batch operations are involved, so the workflow-cap rule does not apply.	3 / 5
Progressive Disclosure	Model-specific minutiae (GPT-5.1-5.6 sampling rules, Anthropic thinking constraints, Astra session internals) is inlined in SKILL.md where it clearly belongs in separate reference files, and every cited path (`API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`) dangles because the bundle contains no such files. Section headers exist, but the inlining plus dangling references match the anchor-2 condition of content that belongs in separate files being inlined.	2 / 5
	Total	11 / 20 Passed

Description

78%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 description with an explicit 'Use when' trigger, a distinctive Rust+axllm niche, and a broad list of specific capability areas. Its main weaknesses are that capabilities are named as topics rather than actions, and it lacks synonym/extension trigger terms.

Dimension	Reasoning	Score
Specificity	The description lists several specific capabilities ('named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers'), but they are topic nouns rather than verb-led concrete actions, so it falls just short of the comprehensive-action anchor.	4 / 5
Completeness	Both what and when are present: 'Use when writing Rust code with `axllm`' is an explicit trigger and the feature list conveys the scope. However, what and when are merged into a single clause and the 'what' is implied rather than stated as concrete actions, so it does not clearly match the anchor-5 example's explicit dual statement.	4 / 5
Trigger Term Quality	Natural terms a user would say are present ('Rust', 'OpenAI', 'Gemini', 'Anthropic', 'axllm'), giving good keyword coverage, but common variations and extensions are missing (e.g. '.rs', 'Cargo.toml', 'crate', 'LLM providers').	4 / 5
Distinctiveness Conflict Risk	The 'Rust' + 'axllm' qualifier carves a clear niche; the provider names (OpenAI, Gemini, Anthropic) are conditioned on that qualifier, so the risk of triggering in place of a generic provider-API skill is minimal.	5 / 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: website/static/rust/.well-known/agent-skills/ax-rust-ai/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.