ax-rust-gepa

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

Quality

80%

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-gepa/SKILL.md

Quality

Content

75%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 lean, well-organized overview with excellent token efficiency, clear guardrails, and good one-level-deep reference signaling. Its main weakness is actionability: the core code pattern is a non-executable skeleton and the runnable examples it defers to are not in the bundle, and there is no verification step for generated code.

Suggestions

Make the Core Pattern a complete runnable example (imports, a concrete evaluator and request) or point to a specific example file path that exists in the bundle.

Include the key referenced files (API.md, examples/) in the skill bundle, or trim references to only what ships.

Add a lightweight verification step (e.g., run a no-key example or `cargo check`) to validate generated code before presenting it.

Dimension	Reasoning	Score
Conciseness	The ~40-line body is terse, factual bullets ('Language: Rust', 'Real network support: yes') with zero padding and no explanation of concepts Claude already knows. Every token earns its place, matching the lean anchor 5.	5 / 5
Actionability	The 'Core Pattern' snippet is a two-line skeleton with unbound placeholders (`reflection_client`, `options`, `request`, `evaluator`) — no imports, no evaluator construction, not copy-paste runnable — and the concrete alternatives it points to (`examples/`, `API.md`) are not present in this bundle. Fits anchor 3 (incomplete concrete guidance, pseudocode-like rather than executable); not 4 because the primary code example is not executable.	3 / 5
Workflow Clarity	Sections are clearly organized, and ordering cues exist ('Start from package examples ... before inventing a new call shape', 'Use BootstrapFewShot before GEPA'), but there is no explicit step sequence or verification checkpoint for the code produced. Fits anchor 4 (clear structure, minor validation gaps); not 5 because no validation/verification step is given, and not capped at 3 since no destructive or batch operations are involved.	4 / 5
Progressive Disclosure	The body is a well-organized under-50-line overview whose references (`API.md`, `axir-api.json`, `examples/`) are one level deep and clearly signaled in 'Package Facts' — but none of those files exist in the bundle (no references/, scripts/, or assets/ directories). Fits anchor 4 (good structure, minor organization gaps); not 5 because navigation relies on files absent from the bundle.	4 / 5
	Total	16 / 20 Passed

Description

78%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 concise, distinct description with an explicit 'Use when' trigger and the right technical keywords for its niche. It could better separate what the skill does from when to use it, and state concrete actions (run the optimizer, inspect artifacts) rather than topic nouns.

Suggestions

Split into a capability statement with action verbs ('Runs the GEPA optimizer, inspects GEPA artifacts, tracks metric budgets and Pareto fronts') followed by the 'Use when' clause.

Add natural trigger synonyms and concrete artifacts users might mention (e.g., 'playbook', 'BootstrapFewShot', 'candidate evaluation', 'axllm package').

Dimension	Reasoning	Score
Specificity	Names the domain ('writing Rust code with `axllm`') plus several specific focus areas ('GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts'), but only one action verb — the rest are topics rather than concrete actions. Matches anchor 4 (several specific items, minor gaps); not 5 because it lacks concrete action verbs per area like 'run the optimizer' or 'inspect artifacts'.	4 / 5
Completeness	An explicit 'Use when writing Rust code with `axllm` for...' trigger is present, and the 'what' (write Rust code with the axllm package) is present but folded into the same clause rather than stated as a distinct capability list. Anchor 4 fits ('both what and when; when could be more specific'); not 3 because the when-clause is explicit, not weakly implied.	4 / 5
Trigger Term Quality	'GEPA', 'Pareto tradeoffs', 'reflection clients', 'metric budgets', and 'optimizer state' are natural terms a user needing this skill would say. Good keyword coverage but missing common synonyms or variations (e.g., 'prompt optimization', 'playbook', 'candidate'), so it fits anchor 4 rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Rust + `axllm` + GEPA is a narrow, clearly delineated niche with distinct technical triggers; it would virtually never fire for the wrong skill. Matches anchor 5 (clear niche with distinct triggers, minimal conflict risk).	5 / 5
	Total	17 / 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-gepa/SKILL.md
Commit: 3f630a0

Reviewed: 3 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.