200-agents-md

Use when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries — through a modular, step-based interactive process that adapts to your specific project needs. This should trigger for requests such as Create AGENTS.md; Update AGENTS.md file; Add agent instructions. Part of cursor-rules-java project

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

A well-organized, concise interactive-generation skill with a clear step sequence, edge-case checkpoints, and clean one-level-deep progressive disclosure into a real reference file. Its only gap is actionability: the body's executable specifics (exact commands/templates) live entirely in the reference rather than being illustrated inline.

Suggestions

Add one compact inline example of a generated AGENTS.md fragment (e.g., a sample Commands bash block or a filled Boundaries section) so the body demonstrates the expected output format directly.

Include at least one concrete, copy-pasteable command (e.g., a representative `./mvnw clean verify` build/test line) in the body alongside the deferred reference, since the skill centers on documenting commands.

Name the exact reference section or anchor (e.g., 'Step 1 question template' or 'Output Structure') when pointing to references/200-agents-md.md so navigation into the detail file is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — short bullets, terse workflow steps, and no padding explaining what AGENTS.md or Java is; every section earns its place.	3 / 3
Actionability	Guidance is concrete in structure (named sections, ✅/⚠/🚫 boundary format, "review project structure") but lacks executable specifics in the body itself — the actual commands, code, and detailed templates are deferred to the reference rather than given inline.	2 / 3
Workflow Clarity	A clear four-step sequence (review context → read reference → run interactive capture → generate artifact) with explicit EDGE CASE checkpoints that stop and ask before editing files or running project-wide commands, plus file-existence handling in the reference's safeguard.	3 / 3
Progressive Disclosure	The SKILL.md is an overview that points one level deep to a real, well-signaled reference file ("Read references/200-agents-md.md"), with the detailed templates and question bank correctly kept out of the body; the referenced file exists in the bundle.	3 / 3
	Total	11 / 12 Passed

Description

100%

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, third-person description that names concrete actions, lists natural trigger phrases, and explicitly pairs what-and-when. It is concise yet complete with a clear, narrow Java/AGENTS.md niche unlikely to conflict with other skills.

Dimension	Reasoning	Score
Specificity	It enumerates multiple concrete generation actions — "covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries" through a concrete "modular, step-based interactive process", going well beyond a single vague action.	3 / 3
Completeness	It answers both "what" (generate an AGENTS.md covering the listed sections) and "when" ("Use when you need to generate an AGENTS.md file for a Java repository") with an explicit trigger clause and example requests.	3 / 3
Trigger Term Quality	Natural user phrasings are explicitly listed ("Create AGENTS.md; Update AGENTS.md file; Add agent instructions") alongside the domain term "AGENTS.md", giving good coverage of phrases a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The niche is sharply scoped to "AGENTS.md file for a Java repository" with Java-specific triggers (Maven/Gradle, Spring Boot), making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: jabrena/cursor-rules-java
Commit: 86eb63d

Reviewed: 4 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.