Name: ax-go-llm
Rating: 59.2 (1 reviews)
Author: ax-llm

ax-go-llm

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for using the generated Ax package, factory functions, package docs, examples, and API reference.

Quality

74%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/go/skills/ax-go-llm/SKILL.md

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.

A well-structured quick reference with concrete code and genuinely useful guardrails, held back by a heavy inline symbol dump that duplicates its own referenced docs and by vague, unlinked cross-references. Tightening the API surface to curated entry points and turning file names into real links would raise both conciseness and disclosure scores.

Suggestions

Trim 'Relevant API Surface' to a handful of top-level entry points per category and point to `API.md`/`axir-api.json` for the full list, removing the duplicated `AxOwnedClientFactory.OwnedWorkerFactory` entry.

Convert bare file names into path-qualified links (e.g. [API.md](API.md), [examples/](examples/)) and give the 'language-specific AI skill' reference an actual path or skill name.

Delete the opening paragraph that restates the frontmatter description, and make the 'Core Pattern' snippet fully executable (add the `os` import) with the import alias consistent with the API surface listing.

Dimension	Reasoning	Score
Conciseness	The prose is lean and avoids explaining concepts Claude already knows, but the opening paragraph repeats the frontmatter description, and the 'Relevant API Surface' section inlines ~50 symbol names (with `AxOwnedClientFactory.OwnedWorkerFactory` listed twice) that duplicate the referenced `API.md`/`axir-api.json`, which could be tightened or trimmed to entry points.	3 / 5
Actionability	The 'Core Pattern' gives near copy-paste Go code and 'Guardrails' gives concrete decision rules (provider-api only with credentials, no-key for deterministic checks); gaps keep it below 5 — the snippet omits the `os` import, and the code uses an `ax.` import alias while the API surface lists the same functions as `axllm.*`, an inconsistency that could mislead.	4 / 5
Workflow Clarity	As a single-purpose quick-reference skill it is well organized with an implicit sequence in Guardrails (start from examples, choose transport by credential availability); it lacks explicit validation checkpoints or a stated lookup order (examples → API.md → write code), so it does not reach 5.	4 / 5
Progressive Disclosure	Sections are clear and Package Facts names `API.md`, `axir-api.json`, `axir-capabilities.json`, and `examples/`, but the references are bare backtick names with no paths or links, the pointer 'Find ordered or adaptive provider-balancing guidance in the language-specific AI skill' names neither a path nor a skill, and the large inline API symbol list is content that belongs in the referenced files.	3 / 5
	Total	14 / 20 Passed

Description

73%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 highly distinctive, trigger-rich description that names the exact Go package, but its capability phrasing is grammatically muddled ('for using') and noun-heavy, weakening what it concretely does. Restructuring to lead with capability verbs followed by the 'Use when' clause would lift it to top level.

Suggestions

Rewrite to lead with concrete capability verbs, e.g. 'Write Go code against the generated Ax package `github.com/ax-llm/ax/packages/go`: call factory functions for signatures, providers, agents, flows, and optimizers using the package docs and examples.' followed by the 'Use when...' clause.

Fix the 'Use when writing Go code with X for using...' construction — the second 'using' is redundant and makes the what/when split unclear.

Add natural trigger variations such as 'Golang' or 'Ax for Go' to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain precisely ('writing Go code with `github.com/ax-llm/ax/packages/go`') but the capability statement is a list of nouns ('factory functions, package docs, examples, and API reference') rather than concrete actions, and the 'for using the generated Ax package' construction obscures what the skill actually does.	3 / 5
Completeness	It has an explicit 'Use when...' trigger clause and a what-statement, so both elements are present as in the anchor-4 example; the 'what' is a resource list phrased as 'for using the generated Ax package, factory functions...' rather than clear capability verbs, keeping it below the 'clearly and explicitly answers both' bar of 5.	4 / 5
Trigger Term Quality	Natural terms users would say are present ('Go code', 'examples', 'API reference', the package import path), giving good keyword coverage; common variations like 'Golang' or 'ax-llm' are missing, so it is not at the comprehensive-synonym level of a 5.	4 / 5
Distinctiveness Conflict Risk	Naming the exact generated package path `github.com/ax-llm/ax/packages/go` and the Go language carves out a clear niche with distinct triggers and minimal conflict risk against other Ax or language skills.	5 / 5
	Total	16 / 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: packages/go/skills/ax-go-llm/SKILL.md
Commit: 3f630a0

Reviewed: 3 days 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.