ax-java-agent-memory-skills

Use when writing Java code with `dev.axllm:ax` for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.

Quality

81%

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

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.

A lean, information-dense reference body that stays on package-specific facts and points to runnable examples, with only one executable snippet and mostly descriptive lifecycle semantics. Its main gaps are the absence of an explicit workflow with validation checkpoints and a dense inline version-compatibility paragraph that would fit better in a migration/old-patterns note.

Suggestions

Move the 24.x/25.0.0 contextMap compatibility detail into a short 'Old patterns / migration' subsection so version-sensitive history does not sit in the main lifecycle flow.

Add one or two more executable snippets (e.g. registering an onLoadedSkills observer and an exportRuntimeState/restoreRuntimeState round-trip) so the common cases are copy-paste ready rather than only described.

Turn the implicit workflow into an explicit short sequence with checkpoints, e.g. '1. Find the closest runnable example, 2. Adapt its call shape, 3. Verify behavior with a no-key example before touching provider credentials'.

Dimension	Reasoning	Score
Conciseness	The body is dense and lean with no explanations of concepts Claude already knows, but the inline version-history detail ('Since 25.0.0 the text and item ids follow TypeScript's format... a map saved by a 24.x port loads with its items') is time-sensitive content that belongs in a deprecated/old-patterns section rather than the main flow.	4 / 5
Actionability	It provides an executable core-pattern snippet, concrete runnable example paths ('src/examples/java/long-agents/SkillsAndMemoryAssistantExample.java'), and specific API names, but only one code example (without imports) and the Lifecycle section is descriptive semantics rather than instructions.	4 / 5
Workflow Clarity	There is no explicit multi-step sequence or validation checkpoint; operational ordering is only implicit in the guardrails ('Start from package examples for exact native syntax before inventing a new call shape') and the state-shape warning ('Do not interchange the two shapes') has no verification step. The skill is a multi-capability reference, so the simple-skill exception does not apply.	3 / 5
Progressive Disclosure	The body is well-sectioned and defers detail to one-level-deep package artifacts ('API.md', 'axir-api.json', 'examples/'), but those references are backticked names rather than clearly signaled links, and dense reference detail (the contextMap versioning paragraph) is inlined in SKILL.md.	4 / 5
	Total	15 / 20 Passed

Description

87%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: it pairs an explicit and specific trigger clause with a concrete list of the package's memory and skill capabilities, in third person and without padding. Its only weaknesses are the absence of action verbs and a few missing synonyms and sub-capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('writing Java code with `dev.axllm:ax`') and lists five concrete capability areas ('agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking'), but they are noun phrases rather than actions and omit observers, relevance ranking, and state export, leaving minor coverage gaps.	4 / 5
Completeness	It explicitly answers both parts: a concrete trigger ('Use when writing Java code with `dev.axllm:ax`') and a concrete what (the five capability areas), matching the good-example pattern of trigger clause plus capability list.	5 / 5
Trigger Term Quality	Terms like 'Java code', 'agent memory', 'skill discovery', and 'used-skill tracking' are natural phrases for this package's users, but common variations or synonyms (e.g. 'recall', 'AxAgent') are missing.	4 / 5
Distinctiveness Conflict Risk	A specific package ID combined with agent memory/skill-tracking vocabulary carves out a clear niche with minimal risk of triggering for unrelated skills.	5 / 5
	Total	18 / 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/java/skills/ax-java-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.