CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ax-go-typesafe

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for Typesafe Jev image inputs, boolean/class/rubric score/box signatures, decision evidence and provenance, native Noul/Choice/Score/Box, structured criteria and hybrid generation.

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 ./packages/go/skills/ax-go-typesafe/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 dense and precise with exact constraints and one solid executable example, but it functions as an inlined API contract rather than a skill overview. Long provider-contract sections and the full API symbol list belong in reference files, and the multi-provider content lacks a decision workflow.

Suggestions

Move the detailed Typesafe/Jev and Google Gemini Decisions contract prose into separate reference files (e.g. references/typesafe.md, references/gemini-decisions.md) and keep concise summaries with clearly signaled links in SKILL.md.

Trim the 'Relevant API Surface' dump to the handful of symbols actually used in the examples and point to API.md for the rest, so the overview stays navigable.

State the examples path once in Package Facts instead of repeating 'src/examples/go/generation/' four times, and add one more complete signature example inline so common cases are copy-paste ready.

DimensionReasoningScore

Conciseness

The prose is telegraphic and information-dense with no explanation of concepts Claude already knows and exact limits throughout, but the examples path 'src/examples/go/generation/' is repeated four times and threshold semantics are restated across sections, matching anchor 4 (efficient with minor trims possible) rather than the every-token-earns-its-place anchor 5.

4 / 5

Actionability

The Core Pattern provides one complete, executable Go snippet, and the rest of the body gives exact parameter names, bounds, and concrete guardrails ('Use `no-key` examples for deterministic local checks'), but only one full code example exists and most other guidance is declarative contract description, fitting anchor 4 (mostly executable with minor gaps) rather than anchor 5's copy-paste-ready coverage of common cases.

4 / 5

Workflow Clarity

This is reference material rather than a sequenced process: 'When To Use' and the Guardrails section give loose orientation ('Start from package examples for exact native syntax before inventing a new call shape') but there is no step sequence, no decision path between the Typesafe and Gemini Decisions providers, and no validation checkpoints, matching anchor 3 rather than anchor 4's clear sequence.

3 / 5

Progressive Disclosure

Sections exist and the bundle has no separate files, but roughly 60 lines of provider contract prose (Typesafe/Jev, Google Gemini Decisions) and a ~30-symbol API surface dump are inlined in a single SKILL.md, with doc pointers ('API.md', 'examples/', 'src/examples/go/generation/') being repo paths rather than clearly signaled one-level-deep references, matching anchor 3 (some structure, content that should be separate is inline).

3 / 5

Total

14

/

20

Passed

Description

71%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 is strongly scoped to one package with an explicit when-clause and low conflict risk, but it reads as a feature inventory rather than a natural-language capability statement. Trigger terms lean heavily on internal jargon that users are unlikely to say verbatim.

Suggestions

Rewrite the capability list with action verbs a user would recognize, e.g. 'Add typed boolean, class, rubric-score and box outputs to AxGen signatures in Go' instead of noun-phrase feature enumeration.

Include natural trigger phrases and synonyms users would actually say (e.g. 'typed decisions', 'structured outputs', 'Jev scoring', 'image localization') alongside the package-specific jargon.

Trim insider terminology like 'Noul' and 'hybrid generation' from the description or pair each with a plain-language gloss so the trigger matches user intent.

DimensionReasoningScore

Specificity

The description enumerates many specific capabilities ("Typesafe Jev image inputs, boolean/class/rubric score/box signatures, decision evidence and provenance, native Noul/Choice/Score/Box, structured criteria and hybrid generation") but presents them as feature nouns rather than concrete action verbs, so it matches anchor 4 (several specific items, minor gaps) rather than the action-oriented anchor 5.

4 / 5

Completeness

The when-clause is explicit ("Use when writing Go code with `github.com/ax-llm/ax/packages/go`") and the what is conveyed through a capability list, but the what is a noun-phrase enumeration rather than a clear action statement, fitting anchor 4 (both present, when could be more specific) rather than the fully concrete anchor 5.

4 / 5

Trigger Term Quality

"writing Go code" is a natural user phrase, but most terms are internal jargon ("Noul", "rubric score/box signatures", "hybrid generation", "provenance") and common variations or synonyms a user would actually say are missing, matching anchor 3.

3 / 5

Distinctiveness Conflict Risk

The description is anchored to a single named package with unique domain terms (Typesafe, Jev, Noul), giving it a clear niche with distinct triggers and minimal conflict risk with other skills, matching anchor 5.

5 / 5

Total

16

/

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/go/skills/ax-go-typesafe/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.