Name: ax-gepa
Rating: 68.8 (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

83%

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

Quality

Content

77%

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 executable canonical examples and good troubleshooting feedback loops. Its weaknesses are mild cross-section redundancy and a single-file, inline-heavy structure with non-portable example-target paths.

Suggestions

Consolidate the recurring validationExamples/maxMetricCalls budgeting advice into one section to remove cross-section repetition and tighten conciseness.

Move the long canonical examples and the full AxGEPA options block into reference files (e.g., references/examples.md) and link to them from the body to improve progressive disclosure.

Replace the non-portable absolute paths in 'Good Example Targets' with repo-relative paths or remove the section, since those paths are not usable bundle references.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining concepts Claude already knows, but the same guidance (validationExamples sizing and maxMetricCalls budgeting) is restated across 'Use These Defaults', 'Critical Rules', 'Budgeting and Validation', and 'Troubleshooting', so it could be tightened; this matches 'mostly efficient but could be tightened' rather than the lean top anchor.	2 / 3
Actionability	Two complete, copy-paste-ready canonical TypeScript examples (scalar and Pareto), plus executable metric patterns, result-handling, and options code blocks provide fully concrete, executable guidance.	3 / 3
Workflow Clarity	Decision flow is clearly organized (defaults -> critical rules -> metric selection -> canonical patterns -> result handling -> budgeting) and the Troubleshooting section supplies explicit error-to-fix feedback loops (e.g., 'maxMetricCalls too small: increase it', 'partial apply: use applyOptimization').	3 / 3
Progressive Disclosure	Sections are well-organized and navigable, but the skill is a single 260-line file with long inline canonical examples and an options block that could be split into reference files, and the 'Good Example Targets' list uses non-portable absolute local paths (/Users/vr/src/...) that are not real bundle references.	2 / 3
	Total	10 / 12 Passed

Description

90%

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, specific description with an explicit 'Use when' clause and excellent natural trigger-term coverage. The only soft spot is specificity, since it centers on a single action (generate optimization code) rather than enumerating several distinct concrete actions.

Suggestions

Broaden specificity by listing a few distinct concrete actions (e.g., tune a generator/flow, run multi-objective Pareto optimization, apply and persist optimized programs) rather than framing everything as 'generate optimization code'.

Dimension	Reasoning	Score
Specificity	Names the domain and the core action ('generate correct AxGEPA optimization code using @ax-llm/ax') plus targets (generator, flow, agent tree), but it is essentially one action with several trigger targets rather than a list of multiple distinct concrete actions, so it matches the 'names domain and some actions' anchor rather than the top anchor.	2 / 3
Completeness	Explicitly answers both what ('generate correct AxGEPA optimization code using @ax-llm/ax') and when ('Use when the user asks about ...'), with an explicit 'Use when' clause and multiple triggers.	3 / 3
Trigger Term Quality	Strong, natural coverage of terms a user would actually say when needing this skill: 'AxGEPA, GEPA, Pareto optimization, multi-objective prompt tuning, reflective prompt evolution, validationExamples, maxMetricCalls'.	3 / 3
Distinctiveness Conflict Risk	A clearly delineated niche (AxGEPA/GEPA optimization for @ax-llm/ax) with distinctive, specific triggers that are unlikely to fire 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: website/static/typescript/.well-known/agent-skills/ax-gepa/SKILL.md
Commit: 7911e27

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.