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

75%

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%

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

The body is concise and well-organized with a concrete code snippet, but it lacks a sequenced optimization workflow with validation checkpoints and its referenced bundle files (API.md, examples/, etc.) are not present. Actionability is partial because the core code uses undefined placeholders.

Suggestions

Add a sequenced optimization workflow with explicit validation checkpoints (e.g., mine failures → propose playbook entries → run verification gate → only persist passing entries), including a validate→fix→retry feedback loop.

Replace the placeholder core pattern with a complete, copy-paste-ready example that defines `reflection_client`, `options`, `request`, and `evaluator`, or add signatures/usage for the symbols in 'Relevant API Surface'.

Provide the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) under references/ or assets/, or remove the dangling references so progressive disclosure points to real files.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned into short bullets with no padding of concepts Claude already knows; every section earns its place, though the opening line lightly restates the description.	3 / 3
Actionability	The Core Pattern gives real Rust code, but `reflection_client`, `options`, `request`, and `evaluator` are undefined placeholders and the 'Relevant API Surface' is only a list of symbol names without signatures or a complete example, so guidance is concrete but incomplete.	2 / 3
Workflow Clarity	'When To Use' lists tasks and a 'verification gate' is mentioned, but there is no sequenced multi-step optimization workflow with explicit validate→fix→retry checkpoints; for an iterative/batch optimization skill the missing feedback loop caps this at 2.	2 / 3
Progressive Disclosure	Sections are cleanly organized and point one level deep to API.md, axir-api.json, axir-capabilities.json, and examples/, but none of those bundle files actually exist in references/scripts/assets, so the well-signaled references are not backed by real files.	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.

The description is concise and clearly states both what the skill does and when to use it, with a distinctive niche and an explicit trigger clause. Its main weakness is that several trigger terms (BootstrapFewShot, GEPA) are internal jargon rather than phrases users naturally say.

Dimension	Reasoning	Score
Specificity	Names the domain and enumerates multiple concrete capabilities ('agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA'), matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	An explicit 'Use when writing Rust code with `axllm` for...' clause states both what it does and when to use it, matching the anchor that answers both what AND when with explicit triggers.	3 / 3
Trigger Term Quality	'agent optimization', 'evaluators', 'judges', and 'Rust code' are natural for this niche, but 'BootstrapFewShot' and 'GEPA' are library-internal jargon a user would not naturally say, so it sits at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The combination of `axllm`, agent optimization, BootstrapFewShot, and GEPA in Rust is a narrow, distinctive niche unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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-agent-optimize/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.