CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-go-gen

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing.

56

Quality

70%

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

Quality

Content

50%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, factually rich reference that clearly signals where deeper docs live, but it behaves as an inlined API specification rather than a navigable skill: no complete executable example, no sequenced workflow, heavy cross-language prose, and bundle references that point at files not included.

Suggestions

Add one complete runnable Go example (imports, client/LLM construction, Forward call, reading output) so the Core Pattern is copy-paste ready rather than a two-line fragment with an undefined `llm`.

Move the option-by-option spec in 'Provider Forward Options' and the multi-language 'Astra Session Work' detail into reference files (or trim to Go-relevant facts), keeping SKILL.md as an overview with well-signaled links.

Present a short ordered workflow for the common case (define signature -> construct program -> attach tools -> forward -> parse/validate output) with an explicit check against the package examples.

DimensionReasoningScore

Conciseness

There is no padding of concepts Claude already knows — every line is package-specific — but the prose is extremely dense with very long run-on sentences, constant 'as in TypeScript' repetitions, and an off-scope 'Astra Session Work' section detailing Python/C++/Java/Rust behavior in a Go-titled skill. It could be tightened substantially and trimmed of cross-language detail, matching 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the minor-trim level of 4.

3 / 5

Actionability

Concrete API names, option spellings, defaults, error messages, and one code snippet ('program := ax.NewAx(...)' / 'program.Forward(llm, ...)') are given, but the snippet references an undefined `llm` and no complete executable example (imports, client construction, running) exists anywhere in the body. This sits between pseudocode-level (3) and mostly-executable guidance (4); the missing runnable example keeps it at 3.

3 / 5

Workflow Clarity

The body is organized as a reference spec (When To Use, Core Pattern, option-by-option sections) rather than a sequenced process; there is no stepwise build-a-program flow and no validation checkpoints, though 'Guardrails' supplies some do/don't rules. Sequence is implicit and checkpoints absent, matching anchor 3.

3 / 5

Progressive Disclosure

Section headers are clear and doc paths are clearly signaled ('API.md and axir-api.json', 'Capability manifest: axir-capabilities.json', 'Runnable examples: examples/'), but roughly 40 lines of option-by-option API spec in 'Provider Forward Options' and the multi-language session detail belong in separate reference files — and none of the cited files (API.md, examples/, manifests) actually ship in the bundle. Some structure, but content that should be separate is inline.

3 / 5

Total

12

/

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 strong description with an explicit trigger clause, a distinctive package-scoped niche, and a comprehensive capability list. Its main weakness is that the 'what' is expressed as a noun list fused into the 'when' clause rather than as clear action statements.

Suggestions

Lead with a distinct action statement of what the skill does (e.g., 'Writes Go structured-generation programs with...') before the 'Use when' clause so the what/when split is explicit.

Add the capability terms users are most likely to mention but are currently missing, such as 'structured generation' and MCP tool attachment.

DimensionReasoningScore

Specificity

Names the domain (Go code with the `github.com/ax-llm/ax/packages/go` package) and lists nine concrete capabilities ('forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing'). Not 5 because capabilities are listed as nouns rather than actions and MCP/tool integration coverage is incomplete; well above 3's 1-2 actions.

4 / 5

Completeness

Has an explicit 'Use when writing Go code...' trigger clause, and the capability list answers 'what' — but the what is folded into the when clause rather than stated separately as a concrete action statement ('helps an agent write...' appears only in the body, not the description). Not 5 because the what/when split is implicit.

4 / 5

Trigger Term Quality

Good natural keywords users would say: 'Go code', 'AxGen', 'streaming', 'multi-sampling', 'tools', plus the exact package import path. Not 5 because common variations like 'structured generation', 'Ax', or '.go files' are missing; far above the generic-jargon anchors.

4 / 5

Distinctiveness Conflict Risk

The exact import path `github.com/ax-llm/ax/packages/go` and 'AxGen' are unique identifiers; no other skill would plausibly trigger for these terms, so conflict risk is minimal.

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.