CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

82%

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

SKILL.md
Quality
Evals
Security

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, high-signal reference skill that assumes competence, points to real package docs and runnable examples, and stays well organized without bundle-file nesting. The main improvement opportunities are moving inline version-migration notes into a compatibility section and adding one more inline call-shape example for the observer/state APIs.

DimensionReasoningScore

Conciseness

The body is dense and spec-like ('IDs and names are trimmed, malformed entries are skipped, valid empty content is preserved') with no explanations of concepts Claude already knows. It falls short of a 5 because the `contextMap` bullet inlines time-sensitive version-migration detail ('Since 25.0.0 the text and item ids follow... a map saved by a 24.x port loads...') outside any deprecated/old-patterns section.

4 / 5

Actionability

Provides one fully executable code snippet (`Ax.agent(...)`, `helper.forward(...)`), exact API symbol names, and concrete paths to runnable examples. Not a 5 because observer registration, catalog search, and state export have no inline call shapes, deferring entirely to the referenced package examples; well above pseudocode-level guidance, so not a 3.

4 / 5

Workflow Clarity

Guardrails give unambiguous procedural directives ('Start from package examples for exact native syntax', 'Use `no-key` examples for deterministic local checks', 'Treat AxIR as the source of generated package truth'), and the skill involves no destructive or batch operations that would demand validation checkpoints. It is not a 5 because the multi-faceted API surface lacks explicit sequencing across task types.

4 / 5

Progressive Disclosure

A standalone, well-organized SKILL.md of roughly 60 lines whose deeper material (`API.md`, `axir-api.json`, `examples/`) lives in the generated package and is clearly signaled at one level of depth with no nesting. Per the simple-skill guidance, well-organized sections with no need for bundle files merit a 5.

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-scoped description with an explicit 'Use when' trigger and five concrete capability keywords. Its main limitation is that the 'what' is conveyed only as a purpose list rather than an explicit action statement, and a few natural synonym triggers are absent.

DimensionReasoningScore

Specificity

Lists five concrete capability areas ('agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking') plus the exact package coordinate, matching the 'several specific actions with minor gaps' anchor. Not a 5 because capabilities are named as feature nouns rather than concrete actions the skill performs.

4 / 5

Completeness

The 'when' is explicit ('Use when writing Java code with `dev.axllm:ax`'), and a 'what' is implied through the 'for agent memory, ...' purpose list. The what is never stated as a clear action the skill takes, so it does not reach the explicit both-what-and-when clarity of a 5.

4 / 5

Trigger Term Quality

Natural terms users would say are present ('Java', 'agent memory', 'skill discovery'), giving good keyword coverage. A few natural variations are missing (e.g., 'AxAgent', 'skills catalog', 'memories'), keeping it below the comprehensive-synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

Tightly scoped to Java with a specific generated package (`dev.axllm:ax`) and specific subsystems (memory, skill discovery, observers), giving a clear niche with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

17

/

20

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.

Validation — 15 / 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

Path

packages/java/skills/ax-java-agent-memory-skills/SKILL.md

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.