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

ax-gepa

This skill helps an LLM generate correct AxGEPA optimization code using @ax-llm/ax. Use when the user asks about AxGEPA, GEPA, Pareto optimization, multi-objective prompt tuning, reflective prompt evolution, validationExamples, maxMetricCalls, or optimizing a generator, flow, or agent tree.

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

82%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 highly actionable, well-structured codegen skill with complete canonical examples and useful decision/troubleshooting guidance. Main improvements would be deduplicating maxMetricCalls guidance and converting the local-path example list into bundled reference files or removing it.

Suggestions

Consolidate the recurring maxMetricCalls guidance (currently spread across Defaults, Critical Rules, Budgeting, and Troubleshooting) into one authoritative statement to tighten conciseness.

Replace or remove the "Good Example Targets" list of absolute paths (/Users/vr/src/ax/...) since they are not navigable bundled references; either ship the examples as files under references/ or drop the section.

Add an explicitly numbered optimize workflow (define metric -> run optimize -> inspect bestScore/paretoFront -> applyOptimization -> serialize) with a validation checkpoint before applyOptimization to lift workflow_clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence (no conceptual padding about what GEPA or TypeScript is), but maxMetricCalls and a few defaults recur across Defaults, Critical Rules, Budgeting, and Troubleshooting, giving minor redundancy that keeps it just below the lean anchor.	4 / 5
Actionability	Two complete, copy-paste-ready canonical examples (scalar and Pareto) plus metric patterns and result-handling snippets cover the common cases with executable, typed code, matching the fully-executable anchor.	5 / 5
Workflow Clarity	A clear logical sequence (defaults -> critical rules -> metric-selection decision flow -> canonical patterns -> result handling -> troubleshooting) with validation present via validationExamples, bestScore, and troubleshooting error recovery; not a 5 because the sequence is not explicitly numbered with checkpoints.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections with no nested references, and no bundle files exist to split; it stays at 4 rather than 5 because the 260-line body keeps all patterns inline and the "Good Example Targets" list points to non-navigable absolute local paths rather than bundled references.	4 / 5
	Total	17 / 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 strong, niche-specific description that clearly answers both what and when with comprehensive trigger terms. It could be sharpened by naming more distinct actions and trimming the broadest trigger to reduce overlap with general ax codegen.

Dimension	Reasoning	Score
Specificity	Names the domain (AxGEPA optimization codegen via @ax-llm/ax) and one concrete action ("generate correct AxGEPA optimization code"), but does not enumerate several distinct actions, matching the anchor that names the domain with 1-2 concrete actions.	3 / 5
Completeness	It explicitly states both what ("generate correct AxGEPA optimization code using @ax-llm/ax") and when ("Use when the user asks about...") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	The "Use when the user asks about AxGEPA, GEPA, Pareto optimization, multi-objective prompt tuning, reflective prompt evolution, validationExamples, maxMetricCalls, or optimizing a generator, flow, or agent tree" clause offers strong keyword coverage with synonyms (AxGEPA/GEPA), though it mixes API parameter names with natural phrases.	4 / 5
Distinctiveness Conflict Risk	The AxGEPA/GEPA/Pareto triggers carve a clear niche, but the broadening phrase "optimizing a generator, flow, or agent tree" creates minor overlap risk with a general @ax-llm/ax codegen skill, fitting the mostly-distinct anchor.	4 / 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: website/static/typescript/.well-known/agent-skills/ax-gepa/SKILL.md
Commit: 1abea97

Reviewed: ~20 hours 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.