Name: ax-go-gepa
Rating: 59.2 (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

74%

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

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.

A concise, well-organized overview that respects token budget and assumes Claude's intelligence. It falls short on executability and structure: the core code pattern is fragmentary and inconsistent with the stated API surface, and all referenced bundle files are missing from the skill directory.

Suggestions

Replace the placeholder-laden Core Pattern with one complete, executable example (imports, reflection-client setup, request, evaluator) drawn from the package's examples, and reconcile the ax vs axllm package-prefix inconsistency with the 'Relevant API Surface' list.

Include the referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) in the bundle, or inline the minimal API details needed to run the optimizer if the files will not ship with the skill.

Add a short numbered workflow (create reflection client → define evaluator and metric budget → run Optimize → inspect Pareto front / candidate state) so the sequencing implied by 'When To Use' becomes an explicit, checkable process.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: every line is a package fact, a terse two-line code pattern, or a directive guardrail, with no padding or explanations of concepts Claude already knows.	5 / 5
Actionability	The Core Pattern snippet uses undefined placeholders (reflectionClient, request, evaluator) with no imports or runnable example, and it contradicts the 'Relevant API Surface' section (ax.NewGEPA vs axllm.AxGEPA). Referenced detail files (API.md, axir-api.json, examples/) are absent from the bundle, leaving the guidance concrete in shape but incomplete and non-executable.	3 / 5
Workflow Clarity	Partial sequencing exists ('Use BootstrapFewShot before GEPA', the core pattern, guardrails) but there is no multi-step workflow for running an optimization end-to-end and no validation checkpoints, matching the anchor for a present-but-checkpoint-missing sequence.	3 / 5
Progressive Disclosure	Sections are well-organized and under 50 lines, and references are clearly signaled in 'Package Facts', but every referenced file (API.md, axir-api.json, axir-capabilities.json, examples/) is missing from the bundle, so the navigation structure points nowhere and key API detail is neither inline nor available.	3 / 5
	Total	14 / 20 Passed

Description

73%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 distinct, well-targeted description with an explicit trigger clause and strong domain-specific keywords. Its main weakness is action specificity: it names what the skill covers as topic nouns rather than stating concrete actions the skill performs.

Suggestions

Lead with one or two concrete actions (e.g., 'Run the GEPA optimizer, inspect Pareto fronts, and track metric budgets when writing Go code with github.com/ax-llm/ax/packages/go') so the 'what' is as explicit as the 'when'.

Add common trigger variations such as 'Pareto front', 'prompt optimization', or 'reflection-based optimization' to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain precisely ('Go code with `github.com/ax-llm/ax/packages/go`') and enumerates specific topics (GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, artifacts), but its only action is the generic 'writing Go code' — it lists capability nouns rather than concrete actions like running the optimizer or inspecting artifacts.	3 / 5
Completeness	An explicit 'Use when writing Go code with...' clause answers the when clearly, and the topic list weakly conveys the what, but the description never states a concrete action the skill performs, so it does not fully meet the anchor requiring both clearly and explicitly.	4 / 5
Trigger Term Quality	Good keyword coverage with terms users of this niche would naturally say (Go, GEPA, Pareto, optimizer, metric budgets) plus the exact package path; missing common variations such as 'Pareto front' or 'prompt optimization', so it falls just short of the comprehensive-synonym anchor.	4 / 5
Distinctiveness Conflict Risk	The description targets a single specific Go package and the GEPA optimization workflow, giving it a clear niche 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/go/skills/ax-go-gepa/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.