ax-python-agent-optimize

Use when writing Python code with `axllm` for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.

Quality

82%

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

72%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-structured skill with a concrete core pattern and useful guardrails. Its weaknesses are an under-specified code example, a missing sequenced workflow for the multi-step optimization process, and references to bundle files that are not actually provided.

Suggestions

Add a numbered workflow for optimization (e.g., mine weaknesses -> propose playbook changes -> pass verification gate -> persist artifacts) with an explicit validate/fix/retry checkpoint so workflow_clarity can exceed 3.

Make the Core Pattern example copy-paste ready by defining or annotating the placeholder variables (reflection_client, request, evaluator) rather than leaving them undefined.

Either ship the referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) in the bundle or note that they live in the generated package, so the references resolve and progressive_disclosure improves.

Dimension	Reasoning	Score
Conciseness	Lean and section-organized — 'Package Facts' is a tight bullet list, 'Core Pattern' is a minimal 3-line snippet — with no padding or re-explanation of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	Gives a concrete executable 'Core Pattern' (import AxGEPA, optimize) and lists real API symbols, but the snippet uses undefined placeholders ('reflection_client', 'request', 'evaluator') so it is not fully copy-paste ready; not 5 because of those minor gaps.	4 / 5
Workflow Clarity	'When To Use' and 'Guardrails' give rough guidance and even mention a 'verification gate', but there is no explicit sequenced workflow (mine -> propose -> verify -> persist) or validate/fix/retry loop for this multi-step optimization process; checkpoints are implicit.	3 / 5
Progressive Disclosure	Section structure is clear and references are signaled by name (API.md, axir-api.json, axir-capabilities.json, examples/), but those referenced files are absent from the bundle, so the one-level-deep references do not actually resolve and navigation is impaired; not 4/5 because references are non-functional.	3 / 5
	Total	15 / 20 Passed

Description

92%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, specific description with an explicit 'Use when' trigger and a clear niche. Its only weakness is trigger-term breadth, relying on specialized terms rather than the natural synonyms a broad user might say.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete capabilities — 'agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA' — matching the comprehensive-coverage anchor; not 4 because it enumerates more than several specific actions.	5 / 5
Completeness	Explicitly answers both what ('writing Python code with axllm for agent optimization, evaluators, judges, optimizer artifacts...') and when ('Use when writing Python code...'), matching the explicit what-and-when anchor with concrete triggers.	5 / 5
Trigger Term Quality	Has an explicit natural trigger ('Use when writing Python code') plus domain keywords, but leans on specialized terms (BootstrapFewShot, GEPA, axllm) rather than broad natural synonyms a user would say; not 5 because common synonyms are missing.	4 / 5
Distinctiveness Conflict Risk	Carves a clear niche around axllm agent optimization with GEPA/BootstrapFewShot — distinctive triggers unlikely to fire for the wrong skill, matching the clear-niche anchor.	5 / 5
	Total	19 / 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/python/skills/ax-python-agent-optimize/SKILL.md
Commit: 1abea97

Reviewed: 2 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.