ax-rust-llm

Use when writing Rust code with `axllm` for using the generated Ax package, factory functions, package docs, examples, and API reference.

Quality

71%

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-llm/SKILL.md

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.

The content is concise, well-structured, and actionable, with a clean API surface index and clear guardrails. Its weakness is workflow clarity: it describes a code-generation workflow without explicit validation or feedback-loop checkpoints.

Suggestions

Add an explicit validation checkpoint for batch/generation workflows, e.g. 'After generating code, build with `cargo check` and re-run against no-key examples before committing.'

Convert plain path references (API.md, examples/) into clearly signaled navigational links with one-line descriptions of what each file contains.

Dimension	Reasoning	Score
Conciseness	The body is lean and token-efficient: it lists package facts, a minimal core pattern, an API surface index, and guardrails with no filler or explanation of concepts Claude already knows.	5 / 5
Actionability	It gives an executable core pattern (`use axllm::ai; let llm = ai("openai", options)?;`) and a concrete API surface list, but most examples are referenced (examples/) rather than inlined, leaving minor gaps.	4 / 5
Workflow Clarity	'When To Use' and 'Guardrails' provide rough sequencing (start from examples, prefer no-key for local checks, treat AxIR as source of truth), but there are no explicit validation checkpoints or feedback loops despite batch/generation operations.	3 / 5
Progressive Disclosure	Content is well sectioned and points one level deep to real bundle files (API.md, axir-api.json, axir-capabilities.json, examples/), though these references are listed as plain paths rather than clearly signaled navigational links.	4 / 5
	Total	16 / 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 specific and mostly complete, clearly scoping a niche (Rust axllm) with a 'Use when' clause. Its main weakness is trigger-term breadth — it relies on technical jargon rather than natural user phrasings.

Suggestions

Add concrete natural trigger phrases users would say, e.g. 'Use when the user asks to build LLM apps in Rust with Ax, needs provider routing in Rust, or wants to generate Ax code for Rust.'

Explicitly separate 'what' from 'when' so the 'when' lists multiple triggering user intents rather than a single jargon-heavy clause.

Dimension	Reasoning	Score
Specificity	The description names the domain (Rust with axllm) and lists several concrete capabilities (factory functions, package docs, examples, API reference), giving clear actions, though slightly below comprehensive coverage.	4 / 5
Completeness	It answers 'what' (use the generated Ax package, factory functions, docs, examples, API reference) and 'when' ('Use when writing Rust code with axllm'), though the 'when' could be more explicit about specific user phrasings.	4 / 5
Trigger Term Quality	It opens with 'Use when writing Rust code with `axllm`', a reasonable trigger, but lacks natural synonyms or variations users would say; mostly technical jargon around the Ax mental model and generators.	3 / 5
Distinctiveness Conflict Risk	The axllm/Rust niche is fairly specific with distinct triggers, carrying only minor overlap risk with other Ax language 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-llm/SKILL.md
Commit: 781623e

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.