CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 an exemplary router-style entry point: a lean task-to-guide table with verified one-level-deep references, minimal padding, and unambiguous guidance on which guide to read when. Its only weaknesses are an unordered conventions section that could be folded into the workflow and one vague closing bullet. It scores highly on progressive disclosure with an ideal bundle structure.

DimensionReasoningScore

Conciseness

The body is lean with no explanations of concepts Claude already knows; every line guides routing or conventions. Minor trims are possible (e.g., 'The guides are bundled locally; no additional skill installation is needed' and 'Specialist skills remain optional when separate skill entries are useful' add little), keeping it just below anchor 5.

4 / 5

Actionability

The task-to-guide table gives concrete, fully resolvable routing (all 16 referenced files exist) and names exact artifacts ('API.md', 'axir-api.json', 'axir-capabilities.json'). As an instruction-only router skill it lacks code, but its guidance is specific and executable; the vague final bullet ('Specialist skills remain optional...') and absence of any example keep it from 5.

4 / 5

Workflow Clarity

For this single-purpose skill the core action is unambiguous: pick the guide matching the task, read it before writing code, and load more when crossing areas, with two worked example combinations. However, supporting steps like checking the installed version against the guide version are presented as unordered conventions rather than sequenced checkpoints, a minor gap versus anchor 5.

4 / 5

Progressive Disclosure

The body is a clear overview with a well-signaled routing table of one-level-deep references; verified against the actual bundle, all 16 referenced files exist and reference files contain no nested bundled references (only external URLs), so navigation is easy and content is appropriately split.

5 / 5

Total

17

/

20

Passed

Description

62%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 has an explicit 'Use when' trigger and names a specific package, giving it decent distinctiveness, but the capability statement is grammatically awkward and reads as a resource list rather than concrete actions. Trigger coverage is thin on natural synonyms. A rewrite separating what the skill does from when to use it, with clearer action verbs, would lift it substantially.

Suggestions

Rewrite as two clean clauses: concrete actions first (e.g., 'Build LLM-powered Rust apps with `axllm`: configure providers, define type-safe signatures, compose agents and workflows.'), then the 'Use when' trigger.

Add natural trigger synonyms users would actually say, such as 'Ax', 'AxLLM', 'LLM app in Rust', 'agent', or 'workflow', to improve trigger term coverage.

Fix the garbled phrasing 'for using the generated Ax package' so the 'what' is a plain, readable statement of capability.

DimensionReasoningScore

Specificity

Names the domain ("writing Rust code with `axllm`") and lists concrete nouns ("factory functions, package docs, examples, and API reference"), but these are resources rather than actions and the clause "for using the generated Ax package" is tangled, so coverage is not comprehensive as required for 4-5.

3 / 5

Completeness

It has both an explicit trigger ("Use when writing Rust code with `axllm`") and a stated what (using the Ax package, factory functions, docs, examples, API reference), but the 'what' clause is grammatically muddled and could be more explicit, placing it between anchors 3 and 5.

4 / 5

Trigger Term Quality

"Rust" and "axllm" are natural terms users would say, but common variations and synonyms (e.g., Ax, AxLLM, LLM app, agent workflow) are missing, and phrases like "the generated Ax package" are not things users naturally type.

3 / 5

Distinctiveness Conflict Risk

"Rust code with `axllm`" carves a clear niche with low conflict risk, but generic ecosystem terms like "Ax package" and "factory functions" leave minor overlap risk with closely related sibling skills (e.g., other language bindings).

4 / 5

Total

14

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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

Reviewed

Table of Contents

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.