CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-rust-refine

Use when writing Rust code with `axllm` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.

63

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-refine/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-sectioned skill body that mostly respects token budget and points to a concrete API pattern. Its gaps are un-actionable incompleteness in the code example and broken references to bundle files that are absent.

Suggestions

Provide the missing bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) or remove the references so signaled paths resolve.

Make the Core Pattern self-contained by showing how reflection_client, options, request, and evaluator are constructed, or link directly to a specific example file.

Add a brief validation/checkpoint step (e.g., run a no-key example to confirm the call shape compiles) to give the workflow a concrete feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — terse Package Facts, a minimal Core Pattern snippet, and bullet Guardrails — without explaining what Rust or libraries are, earning the 'every token earns its place' anchor.

3 / 3

Actionability

The Core Pattern shows real Rust ('axllm::AxGEPA::new(reflection_client, options)?') but the inputs are undefined and it defers to 'examples/' for exact syntax, so it is concrete yet incomplete rather than copy-paste ready.

2 / 3

Workflow Clarity

Sections like 'When To Use' and 'Core Pattern' give structure, but there is no sequenced multi-step workflow or validation checkpoint, and the single action is not fully unambiguous across the multiple listed scenarios.

2 / 3

Progressive Disclosure

Sections are well organized, but the body references API.md, axir-api.json, axir-capabilities.json, and examples/ as bundle resources and none of these files (nor references/ scripts/ assets/) actually exist, so the signaled references are broken.

2 / 3

Total

9

/

12

Passed

Description

85%

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 tight, well-structured description that answers both what and when with an explicit 'Use when' trigger and a distinctive package-scoped niche. Its main weakness is jargon-heavy capability phrasing that a user would be less likely to say verbatim.

Suggestions

Soften jargon in the capability list with user-spoken variants (e.g., 'improve LLM outputs', 'refine prompts', 'iterate on candidates') alongside the technical terms to raise trigger-term quality.

Consider adding a plain-language synonym for 'optimizer-backed refinement patterns' so the description triggers on more natural phrasings.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — 'reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns' — matching the multi-action anchor rather than the single-domain score 2.

3 / 3

Completeness

An explicit 'Use when writing Rust code with `axllm`' clause provides the when, and the capability list provides the what, satisfying both halves; it is not capped at 2 because the trigger guidance is present.

3 / 3

Trigger Term Quality

It has natural package-level triggers ('Rust code with `axllm`') but the bulk ('reward-scored generation', 'optimizer-backed refinement patterns') is technical jargon lacking common user-spoken variations, so it does not reach the broad coverage of score 3.

2 / 3

Distinctiveness Conflict Risk

Scoping to 'Rust code with `axllm`' carves a clear niche tied to one specific generated package, making accidental triggering of unrelated skills unlikely.

3 / 3

Total

11

/

12

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.

Validation15 / 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
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.