Name: ax-signature
Rating: 69.6 (1 reviews)
Author: ax-llm

ax-signature

This skill helps an LLM generate correct DSPy signature code using @ax-llm/ax. Use when the user asks about signatures, s(), f(), field types, string syntax, fluent builder API, validation constraints, or type-safe inputs/outputs.

Quality

85%

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

78%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 dense, highly actionable reference with executable examples throughout and a clear selection flow between the four creation methods. It is slightly verbose from duplicated sections and inlines material that would benefit from being split into bundle files.

Suggestions

Move the bulk of the Signature Gallery and Fluent API Reference into reference bundle files (e.g. references/signature-gallery.md, references/fluent-api.md), keeping only a few representative examples inline in SKILL.md.

Consolidate the duplicated content between 'Common Patterns' / 'Examples' and the Signature Gallery / 'Critical Rules' to remove restated rules and patterns.

Promote the 'when to use which form' guidance in 'Critical Rules' into a short numbered decision workflow so the selection between string, fluent, Standard Schema, and hybrid forms is sequenced explicitly.

Dimension	Reasoning	Score
Conciseness	Mostly lean — compact tables, a tight grammar spec, and a gallery of one-line signatures — but 'Common Patterns' repeats gallery constructs and 'Critical Rules' restates earlier rules, so minor trimming is possible.	4 / 5
Actionability	Abundant copy-paste-ready code: signatures stated to 'parse with s() as written', fluent and Standard Schema examples, and a complete validation example covering the common cases.	5 / 5
Workflow Clarity	'Four Ways to Create Signatures' and the ordering guidance in 'Critical Rules' give a clear selection flow, but as a reference skill it lacks explicit validation checkpoints; no destructive/batch operations are present so no cap applies.	4 / 5
Progressive Disclosure	Well-organized sections and clearly signaled external example URLs, but no bundle files exist and a large reference (gallery, fluent API reference, validation) is inlined that could live in separate files.	3 / 5
	Total	16 / 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, well-structured description that concretely states what the skill does and when to use it with specific trigger phrases. Only minor room for improvement in substituting a few technical tokens with more natural user phrasings.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — 'generate correct DSPy signature code', field types, string syntax, fluent builder API, validation constraints, and type-safe inputs/outputs — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('helps an LLM generate correct DSPy signature code using @ax-llm/ax') and when ('Use when the user asks about...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural coverage ('signatures', 'field types', 'validation constraints', 'type-safe inputs/outputs') plus the literal API tokens s() and f(), though the latter are technical jargon rather than phrasings a user would naturally say.	4 / 5
Distinctiveness Conflict Risk	A clearly bounded niche (DSPy signatures for @ax-llm/ax) with API-specific triggers, making conflict with unrelated 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: website/static/typescript/.well-known/agent-skills/ax-signature/SKILL.md
Commit: 1abea97

Reviewed: ~19 hours 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.