Name: ax-go-agent-memory-skills
Rating: 65.60000000000001 (1 reviews)
Author: ax-llm

ax-go-agent-memory-skills

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.

Quality

82%

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

Quality

Content

78%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 lean, well-organized reference body that carries real package-specific semantics and clear pointers to runnable examples. The main weaknesses are the absence of executable syntax for the skill's core memory/skills options, an inconsistent package prefix in the sole code block, and version-migration detail inlined in the lifecycle section rather than isolated.

Suggestions

Add a minimal executable snippet showing constructor `skills` and forward-input `memories` usage with the actual native option-map key names, so the core features do not depend entirely on the external example file.

Reconcile the package prefix in the Core Pattern (`ax.NewAgent`) with the API surface section (`axllm.NewAgent`) and make the snippet self-contained by defining `llm`.

Move version-migration details ('Since 25.0.0...', 'a map saved by a 24.x port...') into a short 'Old formats / migration' note so the lifecycle section stays lean.

Dimension	Reasoning	Score
Conciseness	The body is dense and fact-per-line with no over-explanation of concepts Claude already knows, but the contextMap bullet carries version-sensitive migration detail ('Since 25.0.0...', 'a map saved by a 24.x port loads with its items...') outside any old-patterns or deprecated section, which the guidelines penalize.	4 / 5
Actionability	Concrete elements are present — a real Core Pattern code block, a named runnable example file, precise option semantics, and exact API names — but the snippet has an undefined `llm` and a package prefix inconsistent with the API section (`ax.NewAgent` vs `axllm.NewAgent`), and no syntax or option-map key names for the core memory/skills features, deferring entirely to external examples.	4 / 5
Workflow Clarity	There is no numbered sequence (reference-style skill), but the Guardrails encode an implicit ordered procedure — 'Start from package examples for exact native syntax before inventing a new call shape' followed by the verification avenue 'Use `no-key` examples for deterministic local checks' — giving a clear sequence with most checkpoints present and only minor validation gaps.	4 / 5
Progressive Disclosure	A well-sectioned ~60-line overview that appropriately defers bulk detail to one-level-deep, clearly signaled references ('API.md', 'axir-capabilities.json', 'examples/', the runnable example paths) with no nested references and easy navigation.	5 / 5
	Total	17 / 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, niche-targeted description with an explicit 'Use when' trigger and a concrete capability list anchored to a specific package. Its main limitation is that capabilities are named as noun phrases rather than actions, leaving the 'what' slightly implicit and missing a few natural synonyms.

Suggestions

Lead with a third-person action statement (e.g., 'Write Go agent code for loading memories, registering recall callbacks, and tracking skill usage') before the 'Use when' clause so the 'what' is explicit rather than implied by a noun list.

Add natural trigger synonyms such as 'golang' or 'Ax'/'AxAgent' alongside 'Go code' to broaden keyword coverage for users who name the library informally.

Dimension	Reasoning	Score
Specificity	The description lists five concrete capability areas ('agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking') tied to a specific package, but they are noun phrases rather than the explicit action statements of the anchor-5 example, and the 'what' each capability involves is left implicit.	4 / 5
Completeness	The 'when' is explicit and concrete ('Use when writing Go code with `github.com/ax-llm/ax/packages/go`'), and the 'what' is present via the capability list, but the what is implied by noun phrases rather than stated as what the skill does, fitting anchor 4 rather than the fully explicit anchor 5.	4 / 5
Trigger Term Quality	Natural phrases a user would say are present ('writing Go code', 'agent memory', 'skill discovery') alongside the exact import path a user would paste, but common synonyms like 'golang' or 'Ax'/'AxAgent' are missing and terms like 'loaded-skill state' are internal jargon rather than user vocabulary.	4 / 5
Distinctiveness Conflict Risk	It names one exact package plus niche features (recall callbacks, loaded-skill state, used-skill tracking), giving a clear trigger niche with minimal overlap risk against generic or sibling skills.	5 / 5
	Total	17 / 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-memory-skills/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.