ax-rust-agent-optimize

Use when writing Rust code with `axllm` for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.

Quality

73%

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 ./packages/rust/skills/ax-rust-agent-optimize/SKILL.md

Quality

Content

65%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.

An admirably terse, well-organized body that avoids over-explanation entirely, but it defers nearly all operational detail (API docs, runnable examples) to files that are not present in the bundle, leaving the Core Pattern as non-executable pseudo-shape. Adding a complete, compilable example and an explicit verify-then-apply workflow would make it substantially more actionable.

Suggestions

Include one complete, compilable example in the body (imports, a constructed AxGEPA engine, an evaluator callback, and an optimize call) instead of the placeholder-variable Core Pattern, since examples/ is not present in the bundle.

Add a short numbered optimization workflow with an explicit validation checkpoint (e.g., mine failures → generate proposals → run verification gate → only then persist playbook/artifacts) so the verification gate is operational rather than named.

Either ship the referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) in the bundle or inline the minimal API signatures needed for the common cases, so deferred references resolve.

Dimension	Reasoning	Score
Conciseness	Lean and well-sectioned; assumes Claude's competence with terse facts ("Runtime profiles: `javascript-quickjs`", "Real network support: yes") and guardrails ("Treat AxIR as the source of generated package truth") — every token earns its place with no padded explanations.	5 / 5
Actionability	The "Core Pattern" snippet ("engine.optimize(request, evaluator)?") is a call-shape sketch with undefined variables rather than executable code, and "Relevant API Surface" is a bare list of names without signatures or a runnable example.	3 / 5
Workflow Clarity	"When To Use" names the tasks ("Mine grounded weaknesses from failed agent tasks and keep only playbook proposals that pass the verification gate") but no sequenced optimization workflow or validation checkpoints are given; the verification gate is mentioned, never operationalized.	3 / 5
Progressive Disclosure	In-body structure is clear with well-signaled references ("API.md", "axir-api.json", "examples/"), but none of the referenced files exist in the bundle — navigation defers to absent material, breaking the disclosure chain.	3 / 5
	Total	14 / 20 Passed

Description

70%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 highly distinctive description with strong trigger terms for its niche, but it is essentially one long "use when" clause: the concrete capability list conveys the domain without ever stating what the skill does. Adding a leading what-statement (e.g., "Writes/optimizes AxAgent Rust code...") would lift completeness.

Dimension	Reasoning	Score
Specificity	Lists several specific areas — "agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA" — though these are topic nouns rather than action verbs, leaving minor coverage gaps.	4 / 5
Completeness	The "when" is explicit ("Use when writing Rust code with `axllm` for agent optimization...") but the "what" is only implied through the topic list; the description never states what the skill itself does.	3 / 5
Trigger Term Quality	Includes natural domain keywords a user in this niche would say ("Rust", "axllm", "agent optimization", "evaluators", "judges", "BootstrapFewShot", "GEPA") but misses a few natural variations like "AxAgent", "playbook", or "optimizer".	4 / 5
Distinctiveness Conflict Risk	A clear, tightly defined niche (Rust + `axllm` + BootstrapFewShot/GEPA) with distinct triggers and minimal risk of firing for unrelated skills.	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: packages/rust/skills/ax-rust-agent-optimize/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.