Name: ax-go-refine
Rating: 60 (1 reviews)
Author: ax-llm

ax-go-refine

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.

Quality

70%

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-refine/SKILL.md

Quality

Content

62%

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

The content is concise and well-sectioned, but its actionability and progressive disclosure are undermined by references to bundle files (API.md, examples/, manifests) that are not present, and the API surface is listed without executable detail. Workflow guidance is implicit rather than an explicit sequenced process.

Suggestions

Either ship the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) or remove the references so navigation is not broken.

Add signatures or a minimal runnable example for the listed optimizer symbols so the API surface is copy-paste ready rather than bare names.

Replace the implicit guardrail ordering with an explicit numbered workflow (e.g. consult examples -> draft call -> verify against AxIR) with a validation checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — short sectioned lists and a minimal code snippet with no padding or explanation of concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	It offers a concrete two-line core pattern, but the 'Relevant API Surface' is a bare list of symbol names with no signatures or usage, and the referenced example/docs files (API.md, examples/) do not exist, leaving guidance incomplete and not copy-paste ready.	2 / 3
Workflow Clarity	Guardrails imply a sequence ('start from examples before inventing call shapes') but there is no explicit multi-step workflow or validation checkpoint for the optimization/refinement operations described.	2 / 3
Progressive Disclosure	The body points to bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) but no references/, scripts/, or assets/ directories exist, so the signaled navigation leads to missing one-level-deep material — effectively a broken reference chain.	1 / 3
	Total	8 / 12 Passed

Description

77%

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, complete with an explicit 'Use when' trigger, and distinctively scoped to a single Go package niche. Its main weakness is trigger-term naturalness — the action terms are technical jargon rather than language users would spontaneously say.

Suggestions

Add user-natural trigger phrasing alongside the technical terms, e.g. 'Use when improving generated Go outputs with evaluator feedback, scoring model responses, or iterating on candidates.'

Soften or gloss jargon like 'optimizer-backed refinement' with a plainer synonym a user might actually request.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns' — matching the anchor for naming several specific actions.	3 / 3
Completeness	Explicitly answers both what (reward-scored generation, iterative candidate improvement, evaluator feedback, optimizer-backed refinement) and when ('Use when writing Go code with the Ax package'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	It leads with a natural 'Use when writing Go code' trigger, but the remaining keywords ('reward-scored generation', 'optimizer-backed refinement') are technical jargon users would rarely say verbatim, missing common variations.	2 / 3
Distinctiveness Conflict Risk	The narrow tie to a specific Go package path and optimizer/refinement niche makes it clearly distinguishable and unlikely to trigger 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/go/skills/ax-go-refine/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.