ax-python-gepa

Use when writing Python code with `axllm` for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts.

Quality

77%

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-gepa/SKILL.md

Quality

Content

76%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 concise, well-structured, and gives a concrete core code pattern plus clear guardrails. Its weaknesses are placeholder variables in the example code and the absence of explicit validation checkpoints or feedback loops for optimization workflows.

Suggestions

Replace the placeholders in the Core Pattern (reflection_client, request, evaluator) with minimal realistic values or a one-line note showing how each is constructed so the example is copy-paste runnable.

Add an explicit validation/verification step for optimization runs (e.g., inspecting the Pareto front or checking metric-budget exhaustion before declaring success) to create a feedback loop.

Either include the referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) in the bundle or note that they ship inside the generated `axllm` package so the references are not dead ends.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized into compact sections (Package Facts, Core Pattern, API Surface, Guardrails) with no padding or explanation of concepts Claude already knows; every token earns its place.	5 / 5
Actionability	Provides a concrete Core Pattern code block and points to executable examples and API docs, but the code uses undefined placeholders (reflection_client, request, evaluator) leaving minor gaps for copy-paste use.	4 / 5
Workflow Clarity	The sections imply a loose sequence (When To Use -> Core Pattern -> API Surface -> Guardrails) and the Guardrails act as soft checks, but there are no explicit validation checkpoints or error-recovery loops for optimization runs.	3 / 5
Progressive Disclosure	Good structure with clearly signaled references to API.md, axir-api.json, axir-capabilities.json, and examples/, and the body is well-sectioned; however those referenced files are not present in the bundle, a minor organization gap.	4 / 5
	Total	16 / 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.

The description is specific and well-targeted to a clear niche, with explicit 'Use when' guidance and a concrete capability list. Its main weakness is that the 'what does this do' framing is merged into the trigger clause rather than standing alone.

Suggestions

Lead with a standalone concrete action clause (e.g., 'Writes and runs Python code with the `axllm` package for GEPA optimization.') before the 'Use when' clause to separate 'what' from 'when'.

Add a few more natural synonyms or file/extension triggers users might say (e.g., 'optimizer', 'prompt optimization') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (Python code with `axllm`) and lists several specific capabilities (GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, artifacts), with only minor gaps in concrete action coverage.	4 / 5
Completeness	Both 'what' (the listed capability areas) and 'when' ('Use when writing Python code with `axllm` for...') are present, but the 'what' is blended into the trigger clause rather than stated as standalone concrete actions.	4 / 5
Trigger Term Quality	Good keyword coverage including `axllm`, GEPA, Pareto tradeoffs, and reflection clients that users of this package would naturally say, though a few common variations are missing.	4 / 5
Distinctiveness Conflict Risk	The niche is clear and distinctive (`axllm`, GEPA) with trigger terms unlikely to fire for unrelated skills, giving minimal conflict risk.	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/python/skills/ax-python-gepa/SKILL.md
Commit: 781623e

Reviewed: 1 day 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.