CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-go-typesafe

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for Typesafe Jev boolean/class signatures, value descriptions, configurable Noul conversion, native Noul/Choice/Score, structured criteria and hybrid generation.

58

Quality

73%

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-typesafe/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A dense, information-rich reference with accurate, highly specific constraints and a solid core code example, but it is reference-shaped rather than workflow-shaped. The native and hybrid sections lack executable examples, the giant API surface list belongs in the (missing) API.md bundle file, and no verify-your-code step ties the guidance together.

Suggestions

Add short executable Go snippets for the native Noul/Choice/Score client and the two-program hybrid pattern, mirroring the Core Pattern block, so every major mode has a copy-paste starting point.

Move the ~40-symbol "Relevant API Surface" list into the referenced API.md (and actually ship API.md, axir-api.json, axir-capabilities.json, and examples/ in the bundle), keeping only the 5–10 most-used symbols in SKILL.md.

Add an explicit verification step to the Guardrails, e.g. "After writing a signature, run the no-key examples for a deterministic local check before hitting a live provider", converting the implicit checkpoint into a stated sequence.

DimensionReasoningScore

Conciseness

The body is dense and free of padding about concepts Claude already knows; nearly every sentence carries package-specific constraints (thresholds, tolerances, label counts). Minor trims are possible: the C++ aside ("C++ uses valueDescriptions on its existing field descriptors") is irrelevant to a Go skill, and triple naming-variant enumerations ("describe_values / describeValues / DescribeValues") add tokens without adding information.

4 / 5

Actionability

There is one real, mostly complete Go code block (the Core Pattern with NewAI/NewAx/Forward) and very concrete parameter constraints, but the native Noul/Choice/Score client and the two-program hybrid pattern — which occupy roughly 40% of the body — get no executable example, and the Core Pattern omits the import statement. The guidance defers to "start from package examples" rather than showing the call shapes.

3 / 5

Workflow Clarity

Selection rules ("Use Jev for typed decisions... Use native questions for probabilities... Compose a separate generative program") and Guardrails give decision guidance and pre-flight checks, but there is no explicit sequence or verification loop for the coding task — e.g., "run the no-key examples to confirm the signature works" is implied by a Guardrail, never stated as a step. The document reads as a reference, not a sequenced workflow with checkpoints.

3 / 5

Progressive Disclosure

References are clearly signaled in one place (Package Facts lists `API.md`, `axir-api.json`, `axir-capabilities.json`, `examples/`) and are one level deep, but none of these files exist in the skill's bundle, and the ~40-symbol "Relevant API Surface" list is exactly the bulk content that belongs in the referenced API.md rather than inlined in SKILL.md.

3 / 5

Total

13

/

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 distinctive, well-targeted description with an explicit trigger clause and a concrete capability inventory. Its main weakness is jargon density: terms like "Noul" and "Jev" are meaningless to anyone not already inside the package, and the capability list reads as feature nouns rather than actions.

Suggestions

Rewrite the capability list as actions in plain language, e.g. "Generate typed boolean/class decisions, native probability and scoring questions, and hybrid generation programs in Go".

Add one or two plain-language triggers users might actually type (e.g., "when the user mentions Jev, Noul, typesafe signatures, or scoring with ax in Go") to broaden natural-term coverage.

Briefly gloss the package-specific jargon ("Typesafe Jev (the ax typed-decision API)") so the description communicates what the skill does even to readers who don't know the internal terminology.

DimensionReasoningScore

Specificity

The description enumerates several concrete capabilities ("boolean/class signatures, value descriptions, configurable Noul conversion, native Noul/Choice/Score, structured criteria and hybrid generation") tied to a specific package, but it reads as a jargon-dense feature inventory rather than a list of actions, and "Noul conversion" is opaque to anyone outside the package.

4 / 5

Completeness

Both what and when are present: an explicit "Use when writing Go code with `github.com/ax-llm/ax/packages/go`" trigger plus an enumerated capability list. It falls short of a 5 because the "what" is an opaque feature list and the when-clause is a single condition that could name more concrete triggers (e.g., mentions of Jev, typesafe signatures, or native scoring).

4 / 5

Trigger Term Quality

It includes good natural trigger terms a user of this library would say ("writing Go code", the package path, "Typesafe", "Score", "criteria", "hybrid generation"), but relies heavily on internal jargon ("Jev", "Noul") and misses plainer synonyms like classification or scoring.

4 / 5

Distinctiveness Conflict Risk

The description is pinned to one exact package path with distinctive internal terms (Jev, Noul), giving it a clear niche with minimal risk of triggering for an unrelated skill.

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
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.