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

66%

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/python/skills/ax-python-agent-optimize/SKILL.md

Quality

Content

61%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.

The body is lean, well-structured, and points clearly to package artifacts, but its core code example uses undefined placeholders and it omits an explicit sequenced optimization workflow with validation checkpoints for a batch operation. Tightening the example and adding a validated workflow would most improve it.

Suggestions

Make the Core Pattern copy-paste ready by defining or stubbing `reflection_client`, `request`, and `evaluator` (e.g. a minimal AxAgent and eval callback) so the example runs.

Add a short sequenced optimization workflow with an explicit verification checkpoint (e.g. mine failures -> propose playbook -> run verification gate -> only persist passing proposals -> bound by budget/dataset rows).

Either bundle the referenced artifacts (API.md, axir-api.json, examples/) or clarify they ship with the `axllm` package so navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is terse and section-organized with bulleted facts that respect Claude's competence; only minor trimming is possible (the opening line restates the description), matching the 'efficient; minor instances of over-explanation' anchor.	4 / 5
Actionability	The Core Pattern shows a real import and real method calls, but `reflection_client`, `request`, and `evaluator` are undefined placeholders, leaving it template-like rather than copy-paste ready, which fits the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	'When To Use' lists use cases and a verification-gate idea is mentioned, but optimization (a batch operation) lacks a sequenced workflow with explicit validation checkpoints; the batch-operation cap therefore holds this at 3.	3 / 5
Progressive Disclosure	Sections are well-organized and external materials (API.md, axir-api.json, examples/) are clearly signaled in Package Facts, but the referenced files are not bundled with the skill, leaving minor organization gaps versus a fully self-contained overview.	4 / 5
	Total	14 / 20 Passed

Description

71%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.

The description is specific and well-targeted to a clear niche with explicit 'Use when...' trigger guidance, but its trigger terms lean heavily technical and lack natural synonyms a user would say. Strengthening trigger phrasing would lift completeness and trigger-term quality.

Suggestions

Add natural-language trigger phrases a user might actually say (e.g. 'optimize an agent', 'add evaluators', 'few-shot prompt optimization') alongside the technical terms.

Reframe capability nouns as concrete verbs (e.g. 'evolve agent playbooks', 'build evaluator callbacks', 'run GEPA optimization') to raise action specificity.

Dimension	Reasoning	Score
Specificity	The description names the domain and lists several concrete capabilities ('agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA'), though these are nouns/features rather than verb-driven actions, leaving minor gaps versus a fully comprehensive action list.	4 / 5
Completeness	Both 'what' (writing Python code with axllm for the listed capabilities) and 'when' ('Use when writing Python code with `axllm` for agent optimization...') are explicitly present, but the trigger phrasing leans technical and could be more concrete/natural.	4 / 5
Trigger Term Quality	Relevant keywords like 'agent optimization', 'evaluators', and 'judges' appear, but the heavy technical jargon ('BootstrapFewShot', 'GEPA', 'optimizer artifacts') and absence of common synonyms or natural user phrasings mirror the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The niche is sharply defined (axllm Python agent optimization with GEPA/BootstrapFewShot), giving it distinct triggers and minimal overlap risk with other skills.	5 / 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: packages/python/skills/ax-python-agent-optimize/SKILL.md
Commit: 781623e

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.