CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-python-signature

Use when writing Python code with `axllm` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/python/skills/ax-python-signature/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 front half of the body is excellent, executable pattern guidance, but the back half is a dense spec dump for three provider subsystems with no code and no supporting bundle files. Splitting the provider sections into references and adding runnable examples would raise most dimensions.

Suggestions

Move the Typesafe/Jev, OpenAI Decisions, and Google Gemini Decisions sections into separate reference files (e.g., references/typesafe.md, references/openai-decisions.md) and keep only a short summary plus link in SKILL.md, fixing the progressive disclosure and conciseness gaps.

Add small executable code snippets for at least the common decision-evidence and provider cases, or bundle the referenced examples/ directory so the cited paths (src/examples/python/generation/) actually resolve.

Tighten the edge-case specification (byte/pixel limits, header names, tolerance rules) into tables or short bullet lists so the retained content earns its token cost.

DimensionReasoningScore

Conciseness

The pattern sections are tight, but the Typesafe/Jev, OpenAI Decisions, and Gemini Decisions sections are ~100 lines of dense edge-case specification (e.g., "Ax enforces 16 MiB per decoded image, 32 MiB per request... Jev enforces 256-1568 pixels per side") that could be significantly tightened or moved out of SKILL.md; it never explains concepts Claude already knows, so it sits above the verbose anchor but well short of efficient.

3 / 5

Actionability

Core Pattern and More Patterns provide executable, copy-paste code for the common signature cases, but the three large provider sections offer declarative spec with no runnable code, and their example paths (src/examples/python/generation/) do not exist in the bundle, leaving concrete guidance incomplete for most of the content.

3 / 5

Workflow Clarity

There is a sensible progression (When To Use, Core Pattern, patterns, Guardrails with "Start from package examples"), but no sequenced procedure or validation checkpoints for the provider workflows the body documents, so an agent must assemble its own process.

3 / 5

Progressive Disclosure

Section headers and external links provide some structure, but the three provider specification sections are inlined material that clearly belongs in separate reference files, and the referenced files (API.md, axir-api.json, examples/) are not present in any bundle directory.

3 / 5

Total

12

/

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.

A strong, specific description with an explicit Use-when clause, concrete capability list, and low conflict risk. Its main gaps are missing capability areas present in the body and a slightly thin set of trigger phrase variations.

DimensionReasoningScore

Specificity

The description lists five concrete capability areas ("string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes"), matching the several-specific-actions anchor; it is not comprehensive since major subsystems covered by the body (decision evidence, provider integrations) are omitted.

4 / 5

Completeness

It explicitly answers both what (the five listed capabilities) and when ("Use when writing Python code with `axllm`"), but the when clause is a single condition without multiple concrete trigger phrases, so it falls short of the clearly-explicit-triggers anchor.

4 / 5

Trigger Term Quality

Terms like "Python code", "axllm", "string signatures", "JSON schema", and "validation" are natural phrases a user of this package would say, giving good keyword coverage, though a few common variants (e.g., AxGen, prompt program, decisions) are missing.

4 / 5

Distinctiveness Conflict Risk

The description is tightly scoped to the `axllm` package with domain-specific terminology, giving it a clear niche with minimal risk of triggering for unrelated skills.

5 / 5

Total

17

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

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-signature/SKILL.md

Reviewed

Table of Contents

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.