CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

Quality

71%

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

Quality

Content

38%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 demonstrates deep, precise knowledge of the package but is structured as a monolithic generated spec dump: enormous edge-case detail inlined in SKILL.md, almost no executable examples beyond a two-line snippet, and references to bundle files that are not actually present. It functions as documentation to read rather than a skill to act from.

Suggestions

Move the provider-decision details (OpenAI Decisions, Gemini Decisions) and the long Provider Forward Options subsections into separate reference files (e.g., references/decisions.md, references/forward-options.md) and keep one-line summaries with links in SKILL.md.

Add small, complete Go code examples for the headline use cases in 'When To Use' — attaching a typed tool, multi-sampling with a result picker, and a StreamingForward loop — instead of describing them only in prose.

Ship the files the body cites (API.md, axir-capabilities.json, examples/) in the bundle, or remove/repoint the citations so navigation matches reality.

DimensionReasoningScore

Conciseness

The body is a ~29KB wall of dense reference prose — single paragraphs of 300+ words exhaustively cataloging edge cases (surrogate-pair joining in stream deltas, JSON.stringify key ordering, DST gap/overlap timezone handling, header-override case sensitivity), most of which reads as a generated spec dump rather than what an agent needs at invocation time. While it never explains basic concepts, it is noticeably verbose with many padded sections, matching anchor 2 rather than 3.

2 / 5

Actionability

There is some concrete guidance — exact API names (`axllm.NewAx`, `SetSampleCount`, `SetResultPicker`, `axllm.Fn`), exact option spellings, and one two-line core-pattern snippet — but the common cases (tools, streaming, multi-sampling, result pickers) get no executable code, only descriptive prose, so guidance is incomplete relative to anchor 4.

3 / 5

Workflow Clarity

There is a recognizable topical sequence (When To Use → Core Pattern → provider details → options → API surface → Guardrails) and the guardrail 'Start from package examples for exact native syntax before inventing a new call shape' gives rough orientation, but no explicit multi-step workflow or validation checkpoints for the many fragile behaviors described (validation retries, correction loops, cancellation semantics).

3 / 5

Progressive Disclosure

The bundle contains no reference files at all, yet the body cites `API.md`, `axir-api.json`, `axir-capabilities.json`, and `examples/` that don't exist, while inlining hundreds of lines of provider-decision and session-management reference material that clearly belongs in separate files. Section headers exist, but the 'content that clearly belongs in separate files is inlined' clause of anchor 2 dominates over anchor 3's 'could be better organized'.

2 / 5

Total

10

/

20

Passed

Description

92%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: explicit 'Use when' trigger, comprehensive and specific capability list, third-person phrasing, and a distinct niche anchored by the exact package import path. The only minor gap is missing synonymous phrasing beyond the package's own terminology.

DimensionReasoningScore

Specificity

The description lists many concrete, specific capabilities — 'AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output parsing' — giving comprehensive coverage of the package's surface, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

It explicitly answers both questions: what ('writing Go code with `github.com/ax-llm/ax/packages/go` for AxGen programs, forward calls, ...') and when ('Use when writing Go code with...'), with a concrete trigger phrase tied to the specific package. Not below 5 since neither half is vague.

5 / 5

Trigger Term Quality

Good keyword coverage including the natural terms a user of this package would say: 'Go code', 'AxGen', 'forward calls', 'streaming', 'tools', 'output parsing'. It stops short of anchor 5 because it lacks synonyms or broader phrasing users might use instead of the package's own jargon (e.g., 'structured generation', 'LLM programs').

4 / 5

Distinctiveness Conflict Risk

The full import path `github.com/ax-llm/ax/packages/go` plus the AxGen-specific feature list carves out a clear niche; it is hard to imagine this triggering for an unrelated skill.

5 / 5

Total

19

/

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-gen/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.