Name: ax-go-agent
Rating: 58.4 (1 reviews)
Author: ax-llm

ax-go-agent

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.

Quality

68%

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-agent/SKILL.md

Quality

Content

68%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 a compact, well-structured reference with a concrete code pattern and explicit guardrails, scoring well on conciseness, actionability, and progressive disclosure. Its main gap is workflow clarity: it offers no sequenced build/validate procedure for assembling and verifying an Ax agent.

Suggestions

Add a short numbered workflow (e.g. pick an example → adapt the Core Pattern → wire tools/MCP → run with no-key transport to verify → switch to provider-api) with an explicit validation checkpoint.

Resolve the API-name inconsistency between `ax.NewAgent` in Core Pattern and `axllm.NewAgent` in Relevant API Surface so the example is copy-paste correct.

Turn the referenced artifacts (`API.md`, `axir-api.json`, `examples/`) into clearly signaled one-level-deep links (e.g. 'See [API.md](API.md) for full method docs') and ship them as bundle files, or drop the references.

Dimension	Reasoning	Score
Conciseness	The body is lean — short bullet lists and a single code snippet with no padding or explanations of basic concepts — though the intro sentence slightly restates the frontmatter description and a few Package Facts could be trimmed.	4 / 5
Actionability	A concrete executable Core Pattern snippet and a named Relevant API Surface give mostly actionable guidance, but the example is a fragment and there is an inconsistency (`ax.NewAgent` vs `axllm.NewAgent`) plus no fully runnable program.	4 / 5
Workflow Clarity	The skill presents a pattern plus guardrails rather than a sequenced procedure; there is no explicit multi-step workflow with validation checkpoints for building and verifying an agent end-to-end.	3 / 5
Progressive Disclosure	The body is under 50 lines with clear well-organized sections (When To Use, Package Facts, Core Pattern, API Surface, Guardrails), but referenced files like `API.md`, `axir-capabilities.json`, and `examples/` are named as facts rather than as clearly signaled navigation links and are not present as bundle files.	4 / 5
	Total	15 / 20 Passed

Description

67%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 a single dense sentence that explicitly pairs a trigger ('Use when writing Go code with [package]') with a comprehensive feature list, giving good completeness and distinctiveness. Its main weakness is trigger-term quality: most listed terms are internal jargon rather than phrases users naturally say.

Suggestions

Add natural-language trigger phrases users would actually say (e.g. 'Go agent', 'Ax agent in Go', 'delegate to a child agent') alongside the technical terms.

Convert the noun-list of capabilities into concrete action verbs (e.g. 'build agents, delegate to child agents, attach tools and MCP clients, cite evidence') to lift specificity from 4 to 5.

Broaden the 'when' clause with multiple concrete triggers (e.g. 'Use when building RLM agents in Go, wiring MCP clients, or requiring citation evidence') to push completeness to 5.

Dimension	Reasoning	Score
Specificity	Names many concrete capability areas ('agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping'), but they are noun-listed features under a single 'writing Go code' verb rather than distinct action verbs, leaving minor coverage gaps.	4 / 5
Completeness	Both 'what' (the capability list) and 'when' ('Use when writing Go code with [package]') are explicitly present, but the 'when' trigger is a single broad condition rather than concrete varied trigger phrases.	4 / 5
Trigger Term Quality	The natural phrase 'writing Go code' is present, but most other terms (MCP, citations, playbook, executor, envelopes) are domain jargon users would rarely say verbatim, and common synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	Pinning to the specific package `github.com/ax-llm/ax/packages/go` gives a clear niche with minimal conflict risk, though the broad 'writing Go code' trigger could overlap with other Go skills.	4 / 5
	Total	15 / 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-agent/SKILL.md
Commit: 781623e

Reviewed: 2 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.