CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-go-ai

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers.

68

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is token-efficient, third-person, and well-organized into decision-oriented sections, but it relies on a single small code snippet and points to bundle files (API.md, axir-capabilities.json, examples/) that are not present. The main gaps are thin in-skill executable examples for routing/balancing and unbacked external references.

Suggestions

Add at least one executable code example for the router and the adaptive balancer workflow, not just the NewAI client snippet, so the core routing guidance is copy-paste ready.

Provide the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, and the examples/ directory) or remove the references, so progressive disclosure is backed by real files rather than dangling links.

Insert an explicit validation step in the workflow (e.g., run a no-key example first to confirm provider request mapping before using real credentials) to add a feedback checkpoint to the routing/balancing flow.

DimensionReasoningScore

Conciseness

Lean bullets with no padding or explanation of concepts Claude already knows; the only conceptual detail (Thompson sampling, reliability/latency/cost/deadline) is package-specific knowledge Claude lacks, so every token earns its place.

3 / 3

Actionability

Provides one concrete executable snippet (the NewAI core pattern) plus specific symbol names and example paths, but the routing/balancing workflows are conveyed as descriptive prose with no executable code, so guidance is concrete but incomplete rather than copy-paste ready.

2 / 3

Workflow Clarity

Decision rules and a recommended example progression ('Start with examples/adaptive_balancer_no_key ... then use the cataloged provider-backed example') give a clear sequence, but there are no explicit validation/feedback checkpoints, capping it below 3.

2 / 3

Progressive Disclosure

Section structure is well-organized and references are clearly signaled in Package Facts, but the referenced files (API.md, axir-api.json, axir-capabilities.json, examples/) are absent from the bundle and an inline 'Relevant API Surface' dump would belong in the missing API.md, leaving the disclosure promise unbacked by actual structure.

2 / 3

Total

9

/

12

Passed

Description

100%

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 concise, uses third person, and clearly pairs an explicit 'Use when' trigger with a specific enumeration of capabilities keyed to a distinct package. It is a strong, well-targeted description with no notable weaknesses.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — "provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers, and balancers" — matching the 'multiple specific concrete actions' anchor rather than naming only a domain and a few actions.

3 / 3

Completeness

Explicitly answers both: what (writing Go code with the named package for the listed capabilities) and when via the literal 'Use when' clause, so 'when' is explicit rather than merely implied as it would be at level 2.

3 / 3

Trigger Term Quality

Natural, developer-facing terms a user would actually say ("writing Go code", provider names OpenAI/Gemini/Anthropic, "routers", "balancers") give good coverage; not a 2 because it goes well beyond 'some relevant keywords' with a broad spread of relevant triggers.

3 / 3

Distinctiveness Conflict Risk

Anchored on a specific package import 'github.com/ax-llm/ax/packages/go' plus named providers, giving a clear niche unlikely to trigger for unrelated Go skills.

3 / 3

Total

12

/

12

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.

Validation15 / 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.