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

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

82%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 tight, well-structured API-oriented skill body that stays lean and points to external docs for detail, with good guardrails and some embedded validation notes. The main gaps are a lack of full copy-paste examples beyond the core pattern, no explicit output-verification step, and referenced files that are signaled but not bundled.

Suggestions

Add 1-2 complete, copy-paste-ready Rust examples beyond the two-line Core Pattern — e.g. a full multi-sampling with result-picker program — to lift actionability to fully executable.

Include an explicit verify step in the workflow (e.g. 'cargo check' / run a no-key example to confirm the generated program compiles and behaves) so generated code is validated before delivery.

Convert the Package Facts file references into markdown links (e.g. [API.md](API.md)) and ensure the referenced files (API.md, axir-api.json, examples/) are actually bundled so navigation is real.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: bulleted facts, a minimal core code snippet, and no padding or explanation of basic concepts (no 'what is Rust' or 'how streaming works'); every section earns its place.	5 / 5
Actionability	Concrete API names and an executable 'Core Pattern' snippet are present, but most sections (multi-sampling, provider options, MCP) name methods/keys rather than giving full copy-paste-ready programs, leaving minor gaps.	4 / 5
Workflow Clarity	The core ax→forward flow is clear and Guardrails supply checkpoint-style guidance, plus validation behaviors are noted ('Core rejects an index outside 0..N-1', 'fail before transport'), but there is no explicit compile/verify-the-output step for the generated code.	4 / 5
Progressive Disclosure	The 'Package Facts' section clearly signals one-level-deep references (API.md, axir-api.json, axir-capabilities.json, examples/) and keeps the SKILL.md an overview, but the references are plain backtick filenames rather than links and the referenced bundle files are not actually present.	4 / 5
	Total	17 / 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, third-person description with an explicit 'Use when' trigger and a comprehensive capability list scoped tightly to the axllm/AxGen Rust niche. Slightly technical in its trigger vocabulary, which keeps trigger-term quality just below perfect.

Dimension	Reasoning	Score
Specificity	The description enumerates a comprehensive set of concrete capabilities — 'forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing' — covering the package's surface broadly.	5 / 5
Completeness	It explicitly answers both 'what' (the named AxGen capabilities) and 'when' via the 'Use when writing Rust code with axllm...' trigger clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of domain keywords ('Rust code', 'axllm', 'AxGen programs', 'streaming', 'tools'), though most are API-specific jargon rather than the natural synonyms a user might say (e.g. 'structured generation', 'LLM calls').	4 / 5
Distinctiveness Conflict Risk	The 'axllm' / 'AxGen' / Rust niche is highly specific with distinct triggers, giving minimal conflict risk against other 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: packages/rust/skills/ax-rust-gen/SKILL.md
Commit: 3951b05

Reviewed: 5 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.