ax-rust-gepa

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

Quality

77%

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-gepa/SKILL.md

Quality

Content

76%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.

The body is concise, well-structured, and points clearly to package documentation, with a concrete core pattern and useful guardrails. Its weaknesses are the lack of an explicit sequenced workflow with validation checkpoints and code examples that rely on undefined placeholders rather than being copy-paste ready.

Suggestions

Add a short numbered workflow (e.g., consult examples -> construct AxGEPA -> run optimize -> verify result) with an explicit validation/checkpoint step so workflow_clarity can exceed 3.

Replace or augment the core pattern with a more complete executable snippet that defines reflection_client, options, request, and evaluator or links directly to the specific example file that does.

Expand the Relevant API Surface with one-line signatures or a pointer to the exact section of API.md for each optimizer type, so the inline guidance is more actionable without breaking progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized with no concept explanations Claude already knows; every section (Package Facts, Core Pattern, API Surface, Guardrails) earns its place.	5 / 5
Actionability	Provides a concrete Rust core pattern and a named API surface, but the code uses undefined placeholders (reflection_client, options, request, evaluator) and is a pattern sketch rather than copy-paste ready; full detail is deferred to package docs.	4 / 5
Workflow Clarity	Triggers and a core two-line pattern are present and guardrails imply a loose order (check examples first), but there is no explicit sequenced multi-step workflow and no validation checkpoints for the optimization flow.	3 / 5
Progressive Disclosure	Clear section structure with well-signaled pointers to package docs (API.md, axir-api.json, axir-capabilities.json, examples/); as a sub-50-line skill this is appropriately organized, though the Relevant API Surface is terse and references point to package-internal rather than bundled files.	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.

The description is specific, trigger-rich, and occupies a clear niche, explicitly covering both what the skill does and when to use it. Its main limitation is that capabilities are listed as noun-concerns rather than concrete verb-actions, and the what/when guidance is blended into a single clause.

Dimension	Reasoning	Score
Specificity	Lists several specific capability areas ("GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts") tied to writing Rust code with axllm; these are concrete concerns rather than verb-actions, so it stops short of comprehensive coverage.	4 / 5
Completeness	Explicitly answers both what (writing Rust code with axllm for the listed concerns) and when ("Use when writing Rust code with `axllm` for...") with concrete triggers, but the what and when share one blended clause rather than distinct explicit statements.	4 / 5
Trigger Term Quality	Good keyword coverage with natural domain terms a user of this package would say ("Rust code", "axllm", "GEPA", "Pareto tradeoffs", "reflection clients", "metric budgets"), though synonyms and variations are absent.	4 / 5
Distinctiveness Conflict Risk	Clear niche combining Rust, axllm, and GEPA-specific concepts with distinct triggers, making conflict with other skills unlikely.	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: packages/rust/skills/ax-rust-gepa/SKILL.md
Commit: 781623e

Reviewed: 2 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.