ax-rust-gepa

Use when writing Rust code with `axllm` for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts.

Quality

88%

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

Quality

Content

77%

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

A concise, well-organized body with a clear core pattern and useful guardrails. Actionability is capped by an illustrative (not copy-paste) code snippet, and progressive disclosure is limited because the referenced external files are not bundled.

Suggestions

Make the Core Pattern code copy-paste ready by showing how reflection_client, options, request, and evaluator are constructed, or link directly to the specific example file that constructs them.

Bundle the referenced materials (API.md, axir-api.json, axir-capabilities.json, examples/) so the body's external references resolve to real files, or note inline which reference each task needs.

Add a brief verification step (e.g., run a no-key example to confirm the optimizer wiring) so the workflow has an explicit checkpoint for confirming correctness.

Dimension	Reasoning	Score
Conciseness	The body is lean with no generic concept explanations, every section earns its place, and it assumes Claude's competence — matching the anchor for lean, efficient content where every token earns its place.	3 / 3
Actionability	The Core Pattern shows a concrete call shape but its variables (reflection_client, options, request, evaluator) are unbound and not copy-paste ready, leaving it as useful illustrative guidance rather than fully executable code.	2 / 3
Workflow Clarity	The Core Pattern gives an unambiguous two-step sequence (construct engine, then optimize) and the Guardrails act as checkpoints (start from examples, use no-key for checks, validate against AxIR); for this simple-task skill the guidance is unambiguous.	3 / 3
Progressive Disclosure	References to API.md, axir-api.json, axir-capabilities.json, and examples/ are well-signaled and one level deep, but the bundle contains only SKILL.md so these referenced paths cannot be verified as present, capping the score.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 description with an explicit 'Use when' trigger and a clear, distinctive Rust/axllm/GEPA niche. It answers what and when concisely with no fluff.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete capability areas — 'GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts' — matching the anchor for listing multiple specific concrete capabilities.	3 / 3
Completeness	It explicitly states both what it does (writing Rust code with axllm for those tasks) and when to use it via an explicit 'Use when' clause, matching the anchor that requires both what AND when.	3 / 3
Trigger Term Quality	It opens with 'Use when writing Rust code with `axllm`' and surfaces the natural terms a user would say (GEPA, Pareto tradeoffs, reflection clients, metric budgets), giving good coverage rather than jargon-only phrasing.	3 / 3
Distinctiveness Conflict Risk	The niche is tightly scoped to Rust + axllm + GEPA optimization, making it unlikely to fire for unrelated skills and clearly distinguishable.	3 / 3
	Total	12 / 12 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-gepa/SKILL.md
Commit: fe8baf8

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.