ax-python-typesafe

Use when writing Python code with `axllm` for Typesafe Jev boolean/class signatures, value descriptions, configurable Noul conversion, native Noul/Choice/Score, structured criteria and hybrid generation.

Quality

68%

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-typesafe/SKILL.md

Quality

Content

57%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 an information-dense reference with good section structure and no padded explanations, but it falls short on execution readiness: the single snippet lacks setup, the referenced docs and examples are absent from the bundle, and there is no step-by-step flow or validation guidance for actually using the package.

Suggestions

Make the Core Pattern snippet self-contained (add imports and how `api_key` is obtained) so it can be run verbatim, or add a minimal no-key runnable variant.

Ship the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) or remove the dangling references and inline the minimal needed content.

Add a short numbered usage flow (pick signature type → choose no-key or provider transport → run example → adapt) with an explicit verification step for the output schema.

Dimension	Reasoning	Score
Conciseness	The body is dense and fact-packed with no explanation of concepts Claude already knows; every section carries package-specific information. Minor trim opportunities remain in the long Typesafe/Jev prose section and the inline API symbol dump, keeping it below anchor 5.	4 / 5
Actionability	There is one concrete code snippet (the 'Core Pattern' with `ai('typesafe', ...)` and `ax(...)`), but it lacks imports and setup so it is not copy-paste executable, and the promised example material ('examples/', 'src/examples/python/generation/') is not present in the bundle — matching the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	'When To Use' and the Guardrails give decision guidance (native vs typesafe vs hybrid, no-key vs provider-api examples), but there is no sequenced workflow or validation checkpoint; the rough selection flow sits between anchors 2 and 3, and no destructive/batch cap applies.	3 / 5
Progressive Disclosure	Sections are well organized and referenced files are clearly named in 'Package Facts', but none of the referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) exist in the bundle, and the 'Relevant API Surface' symbol list is inlined where a separate reference file would fit — matching the 'some structure but could be better organized' anchor.	3 / 5
	Total	13 / 20 Passed

Description

66%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 has an explicit 'Use when...' trigger and is highly distinctive thanks to package-specific terms, but it reads as a jargon feature inventory rather than a statement of concrete actions, which weakens both specificity and natural trigger-term coverage.

Suggestions

Lead with one or two concrete verbs describing what the skill does (e.g., 'Generate typed Python decision programs with `axllm` ...') before enumerating features.

Add natural-language synonyms users would actually type — 'boolean outputs', 'class labels', 'classification', 'structured criteria' — alongside the proprietary terms.

Trim the densest jargon run ('configurable Noul conversion, native Noul/Choice/Score') to the two or three capability phrases that most differentiate the skill.

Dimension	Reasoning	Score
Specificity	The description lists several concrete capability areas ("Typesafe Jev boolean/class signatures", "value descriptions", "configurable Noul conversion", "native Noul/Choice/Score", "structured criteria and hybrid generation"), but these are jargon feature-nouns rather than named actions, and what the skill actually does is only loosely implied — matching anchor 3 rather than 4.	3 / 5
Completeness	Both what and when are present: an explicit "Use when writing Python code with `axllm`" trigger plus an enumerated feature scope. Not a 5 because the 'what' is a feature list embedded in the when-clause rather than a clear standalone statement of what the skill does.	4 / 5
Trigger Term Quality	"Use when writing Python code with `axllm`" is a natural phrase, but most keywords ("Typesafe Jev", "Noul") are proprietary jargon; common user phrasings like "boolean outputs", "classification", or "structured outputs" are missing, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The niche is tightly anchored by the package name `axllm` and its proprietary concepts (Typesafe, Jev, Noul), giving distinct triggers with minimal risk of firing for unrelated skills; the broad 'Python code' phrase is sufficiently qualified by the package qualifier.	5 / 5
	Total	15 / 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-typesafe/SKILL.md
Commit: 3f630a0

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.