CtrlK
BlogDocsLog inGet started
Tessl Logo

ax-java-flow

Use when writing Java code with `dev.axllm:ax` for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.

66

Quality

80%

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

Quality

Content

82%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise and highly actionable with executable Java flow patterns, but it lacks explicit validation/feedback checkpoints for the flows it constructs and its reference structure is more of a facts list than clearly signaled one-level navigation.

Suggestions

Add an explicit verification step (e.g. run a flow against the no-key transport and assert expected output) so the build-run flow has a checkpoint.

Convert the Package Facts references into clearly signaled one-level-deep links (e.g. '## API reference — see API.md') to improve navigation signaling.

Expand 'Relevant API Surface' to point at the specific API.md/axir-api.json sections rather than a single bare entry.

DimensionReasoningScore

Conciseness

The body is lean: short section headers, minimal prose, and code that earns every token, with no explanation of concepts Claude already knows and no padding.

3 / 3

Actionability

Multiple complete, executable Java code blocks (Ax.flow, execute/returns, forward) give copy-paste-ready patterns plus concrete pointer calls (e.g. `parallelFlow.forward(client, ...)`).

3 / 3

Workflow Clarity

Patterns are clearly laid out and sequenced, but there are no validation/verification checkpoints; the guidelines note missing feedback loops should cap this dimension at 2, and the only 'verify' step is an external example reference rather than an explicit in-skill checkpoint.

2 / 3

Progressive Disclosure

Sections are well-organized and references are present (`API.md`, `axir-api.json`, `examples/`, an external gallery URL), but they are not clearly signaled as one-level-deep navigation links and the 'Relevant API Surface' section is thin rather than a proper pointer structure.

2 / 3

Total

10

/

12

Passed

Description

77%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, complete with an explicit 'Use when' trigger, and highly distinctive due to the named package and Java/flow framing. Its main weakness is jargon-heavy trigger terms that a user may not naturally say.

Suggestions

Add a few natural-language trigger terms a user would actually say (e.g. 'Java workflow', 'Java LLM flow', 'AxFlow') alongside the technical jargon.

Consider reordering so the most common user phrasing leads, with `dev.axllm:ax` as a secondary qualifier rather than the opening clause.

DimensionReasoningScore

Specificity

Lists many specific concrete actions — 'writing Java code', 'flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components' — matching the rubric's multiple-specific-actions anchor.

3 / 3

Completeness

It answers both 'what' (writing Java code with `dev.axllm:ax` for the listed capabilities) and 'when' via an explicit 'Use when...' clause, meeting the top anchor.

3 / 3

Trigger Term Quality

It uses domain keywords ('Java code', 'flows', 'nodes') but leans on internal jargon (`dev.axllm:ax`, 'program graphs', 'optimizer components') rather than terms a user would naturally say, so coverage of natural phrasings is partial.

2 / 3

Distinctiveness Conflict Risk

The package coordinate `dev.axllm:ax` plus Java-specific flow/node framing carves out a clear niche unlikely to trigger for unrelated skills.

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.