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

87%

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

82%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 concise, well-structured reference skill that assumes Claude's competence and points cleanly to deeper materials. Its main gaps are slightly descriptive (rather than fully executable) lifecycle guidance and references to bundle files that are not present.

Suggestions

Add one or two more complete runnable snippets (e.g., registering an observer or preloading forward-time skills) to lift actionability to copy-paste-ready.

Either include the referenced bundle files (API.md, axir-api.json, examples/) under references/ or rephrase the pointers so they don't reference non-bundled paths.

Dimension	Reasoning	Score
Conciseness	The body is lean and bullet-driven with no explanation of concepts Claude already knows; it assumes competence, and every section (Package Facts, Lifecycle, API Surface) earns its place with concrete facts and a tight code snippet.	5 / 5
Actionability	It provides an executable Core Pattern snippet and concrete file paths and API names, but much of the guidance (lifecycle/observer semantics) describes behavior rather than giving copy-paste-ready steps for the common cases. It is mostly executable with minor gaps, so 4 rather than 5.	4 / 5
Workflow Clarity	This is a reference/API skill rather than a destructive multi-step process, and the core build-then-forward action is unambiguous with clearly sequenced lifecycle bullets. It lacks explicit numbered steps or checkpoints, placing it just below the top anchor.	4 / 5
Progressive Disclosure	Sections are well-organized and point one level deep to API.md, axir-api.json, examples/, and a website. The body is just over 50 lines and the referenced bundle files (API.md, examples/) are not actually present in references/scripts/assets, leaving minor organization gaps, so 4 rather than 5.	4 / 5
	Total	17 / 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, well-scoped description that names the package and concrete capabilities while giving an explicit 'Use when' trigger. Its only weakness is slightly technical, jargon-leaning phrasing that misses a few natural synonyms a user might say.

Suggestions

Add a few natural synonyms or looser phrasings (e.g., 'agent recall', 'skill loading') so users who don't use the exact API terms still match.

Consider naming the package-coordinate trigger more colloquially (e.g., 'Use when building Ax agents in Java') to broaden natural-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain (Java, `dev.axllm:ax`) and lists multiple concrete capabilities — agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking — matching the 'multiple specific concrete actions; comprehensive coverage' anchor.	5 / 5
Completeness	It explicitly answers both 'what' (agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, used-skill tracking) and 'when' ('Use when writing Java code with `dev.axllm:ax`') with concrete trigger phrasing, matching the top anchor.	5 / 5
Trigger Term Quality	'Use when writing Java code with `dev.axllm:ax`' is a natural trigger phrase a user would say, with relevant keywords like agent memory and skill discovery, but a few natural synonyms are missing and the phrasing leans technical. It sits above the midpoint (good coverage, a few terms missing) but not fully comprehensive, so 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	It is tightly scoped to the `dev.axllm:ax` Java package and specific memory/skill features, giving it a clear niche with minimal conflict risk against other skills.	5 / 5
	Total	19 / 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: dec4f9e

Reviewed: 5 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.