ax-rust-refine

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

Quality

64%

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-refine/SKILL.md

Quality

Content

57%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 compact, well-sectioned reference skill with real API symbols and a concrete core snippet. Its main weaknesses are incomplete executable detail in the code example and references to bundle files that are not actually present.

Suggestions

Make the core snippet self-contained by showing how reflection_client, options, request, and evaluator are constructed, or clearly label it as a pattern to adapt.

Add a brief feedback loop for the refinement workflow (optimize → inspect evaluator feedback → adjust → re-run) to improve workflow clarity.

Either provide the referenced `API.md`, `axir-api.json`, `axir-capabilities.json`, and `examples/` bundle files, or remove the references so navigation is not broken.

Dimension	Reasoning	Score
Conciseness	Lean bullet-based body with a short code snippet and minimal over-explanation ("Use the generated package API, examples, and manifests"), matching anchor 4; not 5 because the intro line restates the description and "When To Use" slightly overlaps the opening.	4 / 5
Actionability	Provides a concrete `AxGEPA::new(...).optimize(...)` snippet and a real API-surface list, but the snippet uses undefined inputs (reflection_client, options, request, evaluator) and several guardrails are abstract ("Treat AxIR as the source of generated package truth"), matching anchor 3.	3 / 5
Workflow Clarity	Only an implicit loose sequence (examples → API → guardrails) with no explicit checkpoints or feedback loops, matching anchor 3; not 4 because no validation steps are present even though the skill involves iterative refinement where they would help.	3 / 5
Progressive Disclosure	Well-organized section headers suit a short skill, but the body references `API.md`, `axir-api.json`, `axir-capabilities.json`, and `examples/` that do not exist in the bundle, so references are signaled but not verifiable, matching anchor 3.	3 / 5
	Total	13 / 20 Passed

Description

71%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 specific, well-triggered description with a clear "Use when..." clause and distinct niche. It would score higher with more natural user-facing trigger phrasing and slightly more concrete action verbs.

Suggestions

Add natural synonyms a user would actually say (e.g., "improve", "refine", "iterate on" Rust/LLM outputs) alongside the technical terms.

Broaden the "when" clause beyond a single package to cover the underlying intent (refining or improving generated outputs) to reduce reliance on the `axllm` keyword.

Dimension	Reasoning	Score
Specificity	Names the domain (Rust + `axllm`) and lists several concrete actions — "reward-scored generation", "iterative candidate improvement", "evaluator feedback", "optimizer-backed refinement patterns" — with only minor coverage gaps, matching anchor 4 rather than 5 since the actions are abstract pattern names rather than fully concrete operations.	4 / 5
Completeness	Explicitly answers both what (refinement patterns for Rust axllm) and when ("Use when writing Rust code with `axllm`"), satisfying the no-cap rule; not a 5 because the "when" is narrow and tied to a single package rather than a range of trigger scenarios.	4 / 5
Trigger Term Quality	Includes a natural "Use when writing Rust code" trigger and package keyword `axllm`, but leans on jargon ("reward-scored", "optimizer-backed") and misses common user phrasings like "improve/refine my LLM outputs", matching anchor 3 rather than 4.	3 / 5
Distinctiveness Conflict Risk	Highly specific niche (Rust + the `axllm` package + refinement/optimizer patterns) with distinct triggers and minimal overlap with other skills, matching anchor 5.	5 / 5
	Total	16 / 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-refine/SKILL.md
Commit: 1abea97

Reviewed: ~18 hours 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.