ax-java-playbook

Use when writing Java code with `dev.axllm:ax` for the playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program.

Quality

82%

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

Quality

Content

80%

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

The body is lean, actionable, and well-structured with executable examples and concrete API pointers. It loses points for lacking an explicit validation/feedback loop in its workflow and for referencing bundle files that are absent from the skill bundle.

Suggestions

Add an explicit validation checkpoint for the regenerate-packages workflow (e.g., 'after regenerate, build and run examples/ to confirm; if they fail, fix AxIR and regenerate again') to lift workflow clarity.

Either include the referenced bundle files (API.md, axir-api.json, axir-capabilities.json, examples/) in the skill bundle or remove the dangling references so progressive disclosure is verifiable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — no preamble explaining what Java/Libraries/optimization are, and each section earns its place with no padding.	3 / 3
Actionability	Provides a copy-paste-ready 'Core Pattern' Java snippet, names concrete API symbols (Ax.optimize, AxPlaybook, AxGEPA), and points to runnable artifacts (examples/, API.md, axir-capabilities.json).	3 / 3
Workflow Clarity	'When To Use' lists use cases but there is no sequenced multi-step workflow, and for risky operations like regeneration the guardrails stop at 'update the compiler and regenerate' without an explicit validate->fix->retry checkpoint.	2 / 3
Progressive Disclosure	Sections are well organized and the body signals references to bundle artifacts (API.md, axir-api.json, axir-capabilities.json, examples/), but those referenced directories/files are not present in the bundle, so the navigation cannot be verified as real and one-level-deep.	2 / 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.

The description is concrete, complete, and well-scoped to a specific package with explicit use-when guidance. Its main weakness is jargon-heavy trigger terms that a user is unlikely to voice naturally.

Suggestions

Soften jargon in the trigger clause by pairing internal names like 'playbook()' with user-facing phrasing such as 'evolving prompts/programs' or 'learning from failed runs'.

Add common natural variations users might say (e.g., 'Java LLM programs', 'optimizing Java prompts') alongside the technical terms to improve trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (the enumerated capabilities) and when via the leading 'Use when writing Java code with dev.axllm:ax' trigger clause.	3 / 3
Trigger Term Quality	'Use when writing Java code' is a natural trigger, but terms like 'playbook()', 'context-engineering surface', and 'agent-bound verified evolution' are technical jargon missing common natural variations a user would actually say.	2 / 3
Distinctiveness Conflict Risk	Tied to a specific generated package 'dev.axllm:ax' with niche, domain-specific triggers, making it clearly distinguishable and unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 12 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-playbook/SKILL.md
Commit: fe8baf8

Reviewed: 5 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.