CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-go-signature

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

63

Quality

79%

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 ./website/static/go/.well-known/agent-skills/ax-go-signature/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 core signature patterns are well-taught with tight, concrete Go examples and sensible guardrails. Weaknesses concentrate in the 'Typesafe / Jev' section, which dumps dense provider-spec prose inline with no code examples, and in references to files (API.md, examples/) that are not part of the skill bundle, plus a naming inconsistency (axllm.S vs ax.NewSignature) in the API surface list.

Suggestions

Move the Typesafe/Jev provider specification (thresholds, probability tolerances, label limits) into a separate reference file and keep only a short usage snippet with a pointer in SKILL.md.

Resolve or qualify the referenced paths: either ship API.md, axir-api.json, and examples/ inside the skill bundle, or state explicitly that they live in the package repository so navigation does not dead-end.

Fix the API surface naming inconsistency (axllm.S/axllm.FieldType/axllm.Tool vs the ax. prefix used in all code examples) and add one complete runnable Jev example so the typesafe section is as actionable as the signature patterns.

DimensionReasoningScore

Conciseness

The pattern sections are lean and code-first, but the 'Typesafe / Jev' section is ~17 lines of dense spec prose (threshold defaults, 0.01 probability tolerance rules, floating-point summation allowances) that reads like a compressed reference dump. This matches 'mostly efficient but could be tightened' rather than the minor-trim level 4; the rest of the body is not padded, so it stays above 2.

3 / 5

Actionability

Concrete Go snippets cover the common cases (string contract, class field, native AxSignature record, ToJSONSchema, signature reuse) and point to runnable examples. Gaps keep it below 5: snippets are fragments with undefined variables (client, inputs in program.Forward), the Jev section describes API calls (trueThreshold, describe_values) with no code at all, and 'Relevant API Surface' lists axllm.S/axllm.FieldType which conflicts with the ax. prefix used in every example.

4 / 5

Workflow Clarity

A pattern-reference skill with clear organization (When To Use, Core Pattern, More Patterns, Guardrails) and explicit checkpoints in Guardrails ('Start from package examples for exact native syntax before inventing a new call shape'). No destructive or batch operations require validation loops, but the Jev usage flow is unsequenced and there is no error-recovery guidance, so it does not reach 5.

4 / 5

Progressive Disclosure

References are listed under Package Facts (API.md, axir-api.json, examples/, external URL), but no bundle directories (references/, scripts/, assets/) exist, so those paths are not resolvable within the skill. Meanwhile the dense Jev spec content that clearly belongs in a separate reference file is inlined. This fits 'some structure but content that should be separate is inline'; structure is present (above 2) but organization gaps and unresolvable paths keep it below 4.

3 / 5

Total

14

/

20

Passed

Description

87%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 description: it names the exact package, states several concrete capabilities, and opens with an explicit 'Use when' clause tied to writing Go code with that package. The only weakness is modest coverage gaps (class outputs, native constraints) relative to what the body actually teaches.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes' — matching the anchor for several specific actions with minor gaps; it omits capabilities the body covers (class outputs, native constraint records), so it falls short of comprehensive 5.

4 / 5

Completeness

Explicitly answers both: what ('string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes') and when ('Use when writing Go code with `github.com/ax-llm/ax/packages/go`') with concrete trigger phrases, matching the anchor for clearly and explicitly answering both.

5 / 5

Trigger Term Quality

Good natural keyword coverage: 'Go code', 'string signatures', 'JSON schema', 'validation', plus the package import path users of this library would mention. A few natural terms are missing (e.g., 'Ax', 'prompts', 'schema generation'), keeping it below 5.

4 / 5

Distinctiveness Conflict Risk

Pinned to a single Go package by import path and language, giving it a clear niche with distinct triggers and minimal conflict risk, even against sibling skills for the same library in other languages.

5 / 5

Total

18

/

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
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.