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

88%

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

86%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, well-structured body: package facts, a concrete core code pattern, the relevant API surface, and actionable guardrails with no padding. The main gaps are undefined placeholders in the Core Pattern snippet and the absence of an explicit validation/feedback loop for the evolution and run-end learning workflows.

Dimension	Reasoning	Score
Conciseness	Every line is a package fact ("Runtime profiles: `javascript-quickjs`, `python-pyodide`"), an API pointer ("Optimizers: `Ax.optimize`, `Ax.playbook`..."), a compact code pattern, or a guardrail ("Treat AxIR as the source of generated package truth"). There is no explanation of concepts Claude already knows and nothing to trim.	5 / 5
Actionability	The Core Pattern gives real, concrete Java ("AxPlaybook pb = Ax.playbook(program, java.util.Map.of(\"studentAI\", llm));") and the guardrail "Start from package examples for exact native syntax" directs to runnable examples. It is not a 5 because `llm`, `examples`, and `metricFn` in the snippet are undefined placeholders, so it is not copy-paste ready; not a 3 because the code is executable Java, not pseudocode, and key API names are given.	4 / 5
Workflow Clarity	The Core Pattern implies a clear sequence (create program -> attach playbook -> evolve) and guardrails act as checkpoints ("Start from package examples ... before inventing a new call shape"; "if package docs disagree with source code, update the compiler and regenerate packages"). It is not a 5 because the evolve/verify and run-end learning workflows lack an explicit validate-fix-retry loop, and not a 3 because sequencing and most checkpoints are present.	4 / 5
Progressive Disclosure	The ~43-line body is cleanly sectioned (When To Use, Package Facts, Core Pattern, Relevant API Surface, Guardrails) with one-level, clearly labeled pointers to package artifacts ("Package API docs: `API.md` and `axir-api.json`", "Runnable examples: `examples/`"). No bundle files are needed at this size, fitting the small-skill exception for a well-organized layout.	5 / 5
	Total	18 / 20 Passed

Description

87%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 description: explicit "Use when..." trigger tied to a specific language and package coordinate, with a concrete list of the package's capability areas. The only weakness is that some capability phrasing (e.g., "context-engineering surface") reads as feature-area jargon rather than plain actions, which slightly limits natural trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("writing Java code with `dev.axllm:ax`") and lists several concrete capability areas: "the playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program". It is not a 5 because items like "context-engineering surface" and "agent-bound verified evolution" name feature areas rather than concrete actions, and not a 3 because coverage spans multiple specific capabilities with only minor gaps.	4 / 5
Completeness	It explicitly answers both: the "what" is the package's playbook surface ("playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program") and the "when" is an explicit trigger clause ("Use when writing Java code with `dev.axllm:ax` for..."). It fits the top anchor rather than 4 because the when-clause is already explicit and specific, not merely present.	5 / 5
Trigger Term Quality	"Use when writing Java code with `dev.axllm:ax`" plus natural terms like "playbook()", "evolution", "online updates", and "rendering" match what a user of this package would actually say. It is not a 5 because there are no synonyms or common variations of the trigger terms (e.g., alternate package-coordinate or playbook phrasings), and not a 3 because coverage is good rather than merely partial.	4 / 5
Distinctiveness Conflict Risk	The combination of "Java", the specific package coordinate `dev.axllm:ax`, and "playbook()" carves out a clear niche with distinct triggers and minimal conflict risk with other skills. It is not a 4 because no meaningful overlap with closely related skills is apparent from the text.	5 / 5
	Total	18 / 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: website/static/java/.well-known/agent-skills/ax-java-playbook/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.