CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

70%

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-context/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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 overview with a real code pattern and useful guardrails, but it is weakened by an example that is not fully executable and by references to bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) that do not exist, leaving the progressive-disclosure navigation broken.

Suggestions

Make the core pattern executable by showing how `llm` is obtained (e.g., a concrete Ax given-generation/llm construction) so the snippet is copy-paste ready.

Provide the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) or remove the references from Package Facts so signaled navigation actually resolves.

Replace the loose 'When To Use' heuristics with an explicit decision procedure (e.g., a small routing table mapping task type -> contextMap/contextPolicy/optimization/recall) to improve workflow clarity.

DimensionReasoningScore

Conciseness

The body is lean and well-sectioned, assuming Claude's competence without explaining what Java or agents are; the core pattern, package facts, API surface, and guardrails each earn their tokens. It is not the level-2 case because no unnecessary explanation or padding is present.

3 / 3

Actionability

Provides a concrete Java core pattern and a named API surface, but the example is not copy-paste ready — `llm` is referenced but never defined, and exact call shapes are deferred to (non-existent) `examples/`. It falls short of level 3's 'fully executable, copy-paste ready' anchor.

2 / 3

Workflow Clarity

The 'When To Use' section offers three routing heuristics ('Choose between', 'Avoid mixing', 'Route'), giving a loose decision guide, but there is no sequenced decision procedure or validation checkpoints. It is above level 1 because criteria are listed, but lacks the explicit sequence of level 3.

2 / 3

Progressive Disclosure

The body is well-organized into clear sections and signals external references (API.md, axir-api.json, axir-capabilities.json, examples/), but none of those bundle files actually exist on disk, so the one-level-deep navigation promise is unfulfilled. It avoids level 1 (no wall of text, no nested references) but cannot reach level 3 because the signaled references do not resolve.

2 / 3

Total

9

/

12

Passed

Description

75%

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-structured description with an explicit 'Use when' trigger and a clear, distinctive niche tied to a specific package. It is held back from the top by feature-noun phrasing and technical jargon rather than natural user-facing action terms.

DimensionReasoningScore

Specificity

Names the domain (Java with `dev.axllm:ax`) and several capabilities (context maps, trajectory context policy, offline optimization ACE/GEPA, memory recall), but these are feature-category nouns rather than verb-framed concrete actions like the level-3 anchor ('extract', 'fill', 'merge').

2 / 3

Completeness

Clearly states what it does ('deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall') and includes an explicit 'Use when' trigger ('Use when writing Java code with `dev.axllm:ax`'), satisfying both what and when.

3 / 3

Trigger Term Quality

Contains relevant natural keywords ('Java code', `dev.axllm:ax`) a user of this package would say, but is padded with technical jargon ('trajectory context policy', 'ACE/GEPA', 'long-context agents') that most users would not naturally voice.

2 / 3

Distinctiveness Conflict Risk

The combination of Java plus the specific package `dev.axllm:ax` carves a clear niche with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

10

/

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.