Name: ax-go-agent-optimize
Rating: 62.4 (1 reviews)
Author: ax-llm

ax-go-agent-optimize

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.

Quality

78%

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-agent-optimize/SKILL.md

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 lean, well-organized overview that respects token budget and clearly delimits the package's API surface. It is weakened by a non-executable core code pattern with no worked example, the absence of any step sequence or validation checkpoints for an optimization run, and references to bundle files that do not exist.

Suggestions

Replace the two-line Core Pattern with one complete, runnable example (imports, a real evaluator callback, and a call to Optimize) drawn from the package examples.

Add a short ordered workflow for an optimization run — e.g., pick example, define evaluator, run Optimize with explicit budget, inspect/persist artifacts — with a verification checkpoint before keeping playbook proposals.

Ensure cited files ('API.md', 'axir-api.json', 'axir-capabilities.json', 'examples/') actually ship in the bundle, or drop the citations and inline the one or two facts actually needed.

Dimension	Reasoning	Score
Conciseness	The body is lean fact-lines ('Language: Go.', 'Real network support: yes.', 'Scripted no-key transport support: yes.') with no padding and no explanation of concepts Claude already knows. Every token earns its place, matching the anchor-5 example.	5 / 5
Actionability	The Core Pattern snippet ('engine := ax.NewGEPA(reflectionClient, nil); result := engine.Optimize(request, evaluator)') uses undefined variables and is a shape hint rather than executable code, and the cited 'examples/' are not present in the bundle. This matches anchor 3: 'pseudocode instead of executable code; missing key details' — above 2 because real API names and file pointers are given, below 4 because no complete, runnable example exists.	3 / 5
Workflow Clarity	A rough sequence is present (create engine, call Optimize) and a 'verification gate' is mentioned in When To Use, but no ordered steps or checkpoints for running a bounded optimization exist. Anchor 3 ('sequence present but checkpoints missing or implicit') fits — not 2 because the Core Pattern is a coherent, if minimal, sequence.	3 / 5
Progressive Disclosure	The ~40-line body is well organized into tight sections, but it cites 'API.md', 'axir-api.json', 'axir-capabilities.json', and 'examples/' that are not present in the bundle (no references/, scripts/, or assets/ directories exist). Anchor 4 applies: good structure with minor organization gaps, since the cited navigation targets are unverifiable.	4 / 5
	Total	15 / 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.

A well-scoped, specific description with an explicit 'Use when' trigger and distinctive niche terms. Its main weakness is that the 'what' is folded into the 'when' clause and a few listed terms are terse topic labels rather than concrete capabilities.

Suggestions

State the 'what' explicitly before the trigger, e.g., 'Write and optimize Go agents with github.com/ax-llm/ax/packages/go: create evaluator callbacks, persist optimizer artifacts, and evolve verified playbooks.'

Expand terse trigger labels like 'evaluators, judges' into natural user phrasings (e.g., 'custom evaluators', 'optimizer artifacts', 'few-shot examples') to broaden trigger matching.

Dimension	Reasoning	Score
Specificity	The description lists several concrete capability areas tied to a named package — 'agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA' — matching the 'several specific actions; minor gaps' anchor. It falls short of 5 because terse items like 'evaluators, judges' name topics rather than fully concrete actions.	4 / 5
Completeness	The 'when' is explicit ('Use when writing Go code with github.com/ax-llm/ax/packages/go for ...') and a 'what' is embedded in that clause. It is not 5 because the 'what' leans on the 'when' phrasing rather than independently stating what the skill does.	4 / 5
Trigger Term Quality	'Go code', 'agent optimization', 'evaluators', 'BootstrapFewShot', and 'GEPA' are the natural terms a user in this niche would say, giving good keyword coverage. Not 5 because common variations and synonyms (e.g., 'optimizer', 'few-shot prompting', 'playbook evolution' phrasings) are not comprehensively covered.	4 / 5
Distinctiveness Conflict Risk	The package path 'github.com/ax-llm/ax/packages/go' plus distinctive terms 'BootstrapFewShot' and 'GEPA' establish a clear niche with minimal conflict risk against other skills.	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/go/skills/ax-go-agent-optimize/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.