CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

65

Quality

78%

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/java/skills/ax-java-agent-memory-skills/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

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 assumes competence and avoids filler. It is held back by mostly behavioral descriptions of capabilities rather than executable examples for each, and by the absence of explicit validation checkpoints in its workflows.

Suggestions

Add small in-body executable snippets for the most common capabilities (e.g., forwarding with memories, registering onUsedSkills) rather than describing them behaviorally, to lift actionability.

Add an explicit validation/verification step to at least one risky workflow — e.g., confirm a no-key example round-trips before relying on a provider request mapping — to give workflow clarity a checkpoint.

Inline a one-line concrete example next to each 'Relevant API Surface' entry so the surface list is actionable rather than a bare name reference.

DimensionReasoningScore

Conciseness

The body is dense reference material that assumes Claude's competence — it never explains what agent memory or callbacks are — so it matches the lean-and-efficient anchor rather than the padded 2-anchor.

3 / 3

Actionability

A concrete executable 'Core Pattern' code block is present, but most capabilities are described behaviorally ('Forward-time skills override...', 'observer errors are ignored') without in-body runnable examples, matching the 'some concrete guidance but incomplete' anchor.

2 / 3

Workflow Clarity

Sections are logically ordered and guardrails give procedural hints, but there are no explicit validation checkpoints or feedback loops for the described operations, fitting the 'sequence present but checkpoints missing or implicit' anchor rather than a 3.

2 / 3

Progressive Disclosure

A single well-organized overview file with clearly-labeled sections and one-level-deep, clearly-signaled pointers to package docs and examples, matching the clear-overview anchor; no nested or monolithic structure is present.

3 / 3

Total

10

/

12

Passed

Description

85%

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, specific description with an explicit trigger and a distinct package-scoped niche. Its only weakness is that several capability keywords are internal framework jargon rather than natural user phrasings, slightly limiting trigger-term quality.

DimensionReasoningScore

Specificity

Enumerates five concrete capabilities — 'agent memory,' 'recall callbacks,' 'dynamic skill discovery,' 'loaded-skill state,' and 'used-skill tracking' — matching the anchor for multiple specific concrete actions, not the partial list of a 2.

3 / 3

Completeness

An explicit 'Use when...' clause answers when, and the capability list answers what, satisfying the anchor for clearly answering both what AND when with explicit triggers.

3 / 3

Trigger Term Quality

The 'Use when writing Java code' trigger and the `dev.axllm:ax` package pin are natural, but most capability terms ('recall callbacks,' 'loaded-skill state,' 'used-skill tracking') are framework-internal jargon rather than phrasings users would naturally say, so it lands at 'some relevant keywords but missing common variations.'

2 / 3

Distinctiveness Conflict Risk

The niche is pinned to the specific generated package `dev.axllm:ax` for agent memory and skills in Java, making it unlikely to trigger for the wrong skill per the clear-niche anchor.

3 / 3

Total

11

/

12

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.

Validation15 / 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
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.