Name: ax-go-gepa
Rating: 66.4 (1 reviews)
Author: ax-llm

ax-go-gepa

Use when writing Go code with `github.com/ax-llm/ax/packages/go` 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

Quality

Content

68%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 compact, well-organized reference body with an executable core snippet and clear pointers to deeper material. Its main weakness is workflow clarity — guidance is itemized rather than sequenced, with no validation checkpoints.

Suggestions

Add a short ordered usage sequence (e.g., 1. start from examples, 2. construct engine, 3. run Optimize, 4. inspect artifact) with an explicit verify/validate checkpoint so the workflow is sequenced rather than implied.

Make bundle references markdown links (e.g., [API.md](API.md), [examples/](examples/)) and ensure those files ship in the skill bundle so progressive disclosure is navigable.

Expand the Core Pattern to show constructing the evaluator/request so the example is copy-paste complete rather than requiring readers to fill gaps.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned with no concept padding and a minimal core code snippet, but the 'Relevant API Surface' partially duplicates symbols already implied by the Core Pattern, a minor instance of over-content that could be trimmed.	4 / 5
Actionability	It provides an executable two-line Go Core Pattern and names real API symbols plus pointers to API.md/examples, but the example omits key construction details (e.g., building the evaluator) and the referenced files are not bundled, leaving minor gaps.	4 / 5
Workflow Clarity	'When To Use' and 'Guardrails' imply an order but there is no explicit multi-step sequence and no validation checkpoints; the skill reads as reference material rather than a sequenced workflow.	3 / 5
Progressive Disclosure	Under 50 lines with clean sections and one-level-deep references (API.md, axir-api.json, examples/), but the references are plain paths rather than markdown links and the referenced files are not present in a bundle, a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

92%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 strong, specific description that ties a precise package path to a concrete capability list and opens with an explicit 'Use when' trigger. The only gap is trigger-term breadth — a few natural synonyms or file/extension variants would round it out.

Dimension	Reasoning	Score
Specificity	The description names the package and six concrete capabilities — 'GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts' — matching the anchor for multiple specific concrete actions with comprehensive coverage.	5 / 5
Completeness	It explicitly answers both what (writing Go code with the named package for the listed capabilities) and when ('Use when writing Go code with ...'), with concrete trigger phrasing.	5 / 5
Trigger Term Quality	'Use when writing Go code with github.com/ax-llm/ax/packages/go' is a natural practitioner trigger and 'GEPA'/'Pareto tradeoffs' are domain terms, but common synonyms and file/extension variants are missing, landing at good-but-not-comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The fully-qualified package path plus the narrow GEPA/Pareto niche make this clearly distinct with minimal risk of triggering for an unrelated skill.	5 / 5
	Total	19 / 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/go/skills/ax-go-gepa/SKILL.md
Commit: 781623e

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.