ax-java-agent-context

Use when writing Java code with `dev.axllm:ax` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./packages/java/skills/ax-java-agent-context/SKILL.md

Quality

Content

72%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-organized body with a concrete core code pattern and useful guardrails. Its main weaknesses are the missing decision guidance for the skill's stated purpose (choosing among four feature areas) and references to package files that are not present in the bundle.

Suggestions

Add explicit decision criteria for the skill's core task — e.g., a short mapping of task type (persistent corpus vs. within-run compaction, offline optimization vs. runtime recall) to contextMap/contextPolicy/optimization/recall.

Make the Core Pattern self-contained by showing how `llm` is constructed or obtained, and add one runnable snippet per feature area rather than a single pattern plus name-only API lists.

Fix the reference layer: either include the cited files (API.md, axir-capabilities.json, examples/) in the bundle as one-level-deep references with clear signaling, or remove the citations and inline the minimal needed details.

Dimension	Reasoning	Score
Conciseness	The ~45-line body is lean throughout — terse "Package Facts" ("Real network support: yes."), a single core code pattern, and guardrails with no explanations of concepts Claude already knows; every section earns its place.	5 / 5
Actionability	The Core Pattern provides near-executable Java (`Ax.agent(...)` / `helper.forward(llm, ...)`), but the `llm` variable is undefined in the snippet and the "Relevant API Surface" section is name-only lists with no usage examples.	4 / 5
Workflow Clarity	The skill's core task is choosing among contextMap, contextPolicy, optimization, and recall, yet no decision criteria or task-to-feature mapping is given; guardrails ("Start from package examples…", "Use no-key examples for deterministic local checks") act only as implicit checkpoints.	3 / 5
Progressive Disclosure	The body cites "API.md", "axir-api.json", "axir-capabilities.json", and "examples/" as deeper material, but none of these files exist in the bundle (no references/, scripts/, or assets/ directories), so navigation to the referenced layer is broken despite well-organized sections.	3 / 5
	Total	15 / 20 Passed

Description

71%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 well-scoped description with an explicit trigger clause and strong distinctiveness anchored to a specific package. Its weaknesses are jargon-heavy trigger terms without natural synonyms and a "what" that is only implicitly stated through the "use when" phrasing.

Suggestions

State the what directly (e.g., "Guides selection of context maps, trajectory context policy, offline optimization, and memory recall for Java Ax agents") before the Use-when clause, so both what and when are independently explicit.

Soften jargon-heavy triggers with natural synonyms users would actually say (e.g., "context handling", "prompt optimization", "agent memory") alongside the technical terms.

Add common user phrasings such as "long-context", "agent context", or file/package identifiers ("dev.axllm:ax", "ax-java") that a user would naturally mention when needing this skill.

Dimension	Reasoning	Score
Specificity	The description lists several concrete capability areas — "deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall" — but "deciding between" frames them as choices rather than concrete executable actions, leaving minor gaps in coverage.	4 / 5
Completeness	An explicit "Use when writing Java code with `dev.axllm:ax`" clause answers the when clearly, and the what (deciding between four feature areas) is present, but the what is embedded in the when-clause rather than stated as a direct statement of the skill's actions.	4 / 5
Trigger Term Quality	Relevant keywords like "Java", "optimization", and "memory recall" are present, but "trajectory context policy" and "ACE/GEPA" are niche jargon and common variations or synonyms users would naturally say are missing.	3 / 5
Distinctiveness Conflict Risk	The description is anchored to the specific package `dev.axllm:ax`, Java, and long-context agents — a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	16 / 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-context/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.