Name: ax-go-gepa
Rating: 64 (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

76%

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/go/skills/ax-go-gepa/SKILL.md

Quality

Content

77%

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

The content is lean and well-organized for a simple skill, with a clear single-action flow and useful guardrails. Its weaknesses are an incomplete/inconsistent code example and references to bundle files that do not exist in the bundle.

Suggestions

Reconcile the Core Pattern code with the Relevant API Surface (consistent package qualifier and exact symbol names) and add the import line so the snippet is copy-paste ready.

Either provide the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) or remove/clarify the references, and signal them as markdown links if they exist.

Dimension	Reasoning	Score
Conciseness	The body is lean with dense bullets and no explanation of concepts Claude already knows; nearly every token earns its place, with only minor redundancy between the opening paragraph and the description.	3 / 3
Actionability	The Core Pattern gives a concrete Go snippet, but it is incomplete (no imports; reflectionClient/request/evaluator undefined) and inconsistent with the API Surface (ax.NewGEPA vs axllm.Optimize/axllm.AxGEPA), leaving key details missing.	2 / 3
Workflow Clarity	As a simple single-purpose skill, the When To Use -> Core Pattern -> Guardrails flow makes the single action unambiguous, and no risky batch/destructive operation requires validation checkpoints.	3 / 3
Progressive Disclosure	Sections are well organized, but the body references external files (API.md, axir-api.json, axir-capabilities.json, examples/) that are not present in the bundle and are listed as inline backtick facts rather than clearly signaled navigable links.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 well-targeted with an explicit Use-when trigger and a clear, distinctive niche tied to a specific package. Its main weakness is jargon-heavy trigger terms and feature-area nouns rather than concrete stated actions.

Suggestions

Add concrete verbs to describe actions (e.g., "Run, configure, and inspect the GEPA optimizer") rather than only listing feature-area nouns.

Soften the jargon with one or two user-natural phrasings (e.g., "optimize prompts", "compare candidate tradeoffs") alongside the technical terms.

Dimension	Reasoning	Score
Specificity	Names the domain (writing Go code with a specific package) and several concrete feature areas (GEPA, Pareto tradeoffs, reflection clients, metric budgets), but most are noun-phrases rather than concrete verbs/actions, so it is not a comprehensive list of specific actions.	2 / 3
Completeness	An explicit "Use when writing Go code with... for GEPA, Pareto tradeoffs..." clause answers both what the skill does and when to use it with an explicit trigger, matching the top anchor.	3 / 3
Trigger Term Quality	It has a fairly natural trigger ("writing Go code with [package path]"), but the bulk of terms (GEPA, Pareto tradeoffs, reflection clients, optimizer state) are deep technical jargon, and common user-facing variations are missing.	2 / 3
Distinctiveness Conflict Risk	The specific package path plus the narrow domain (GEPA optimizer, Pareto tradeoffs, reflection clients) forms a clear niche with distinct triggers that is unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 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/go/skills/ax-go-gepa/SKILL.md
Commit: 16c2119

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.