ax-python-gen

Use when writing Python code with `axllm` for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.

Quality

80%

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

68%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 reference skill with executable core examples and clear package facts. Its main gaps are the absence of an explicit validation-gated workflow and runnable examples for the secondary features (tools, streaming, assertions).

Suggestions

Add a short sequenced workflow with a validation checkpoint (e.g., run a no-key example, inspect the trace, then validate output) so multi-step usage has explicit feedback loops.

Provide runnable code snippets for the secondary capabilities (tools, streaming, assertions, output parsing) instead of only naming them in the API surface list.

Convert the inline package-file mentions (`API.md`, `axir-api.json`, `examples/`) into clearly signaled one-level-deep navigation links so detail is easy to discover.

Dimension	Reasoning	Score
Conciseness	Lean, package-specific facts and bullets with no generic concept explanations; the 'Provider Forward Options' paragraph is dense but conveys API behavior rather than padding. Not a 5 because a few sentences could be tightened.	4 / 5
Actionability	The 'Core Pattern' gives copy-paste-ready executable code and 'Multi-Sampling' shows concrete API forms, but tools, streaming, and assertions are named without runnable examples. Not a 5 due to those gaps; not a 3 because the main path is executable.	4 / 5
Workflow Clarity	The body is organized as feature documentation with a starting 'Core Pattern' and 'Guardrails' directives, but there is no sequenced multi-step workflow with explicit validation checkpoints. The guardrails serve only as implicit checks, matching the 'steps present but checkpoints implicit' anchor.	3 / 5
Progressive Disclosure	Well-organized sections (When To Use, Package Facts, Core Pattern, etc.) with inline references to package files like `API.md`, `axir-api.json`, and `examples/`. No bundle files exist in references/scripts/assets, and references are signaled inline rather than as navigation links, keeping it just below a 5.	4 / 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 that names the package and enumerates concrete capabilities while providing an explicit 'Use when' trigger. The only weakness is jargon-heavy trigger phrasing without synonyms or file extensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing' — giving comprehensive coverage of the package's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (writing Python code with axllm for AxGen programs and the listed features) and 'when' via the 'Use when writing Python code with `axllm`...' trigger clause.	5 / 5
Trigger Term Quality	Good domain keyword coverage ('Python code', 'axllm', 'AxGen', 'streaming', 'tools') that users of this package would naturally say, but jargon-heavy with no synonyms or file extensions. Not a 5 because common variations like '.py' or synonyms are absent; not a 3 because coverage is broader than 'some relevant keywords'.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (the generated `axllm`/AxGen package) with distinct, package-specific triggers, making conflict with other skills minimal.	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-gen/SKILL.md
Commit: 781623e

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.