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

60%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/200-agents-md/SKILL.md

Quality

Discovery

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.

This is a strong description that clearly communicates what the skill does (generates AGENTS.md files for Java repos covering specific aspects), when to use it (with explicit trigger phrases), and its niche context (cursor-rules-java project). The description is detailed, uses natural trigger terms, and is highly distinctive. One minor note is that it uses second person ('your specific project needs') which could be improved, but overall the description is well-crafted.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and outputs: generating an AGENTS.md file covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries, through a modular step-based interactive process.	3 / 3
Completeness	Clearly answers both 'what' (generate an AGENTS.md file covering conventions, tech stack, file structure, commands, Git workflow, contributor boundaries via modular interactive process) and 'when' (explicit trigger phrases like 'Create AGENTS.md', 'Update AGENTS.md file', 'Add agent instructions').	3 / 3
Trigger Term Quality	Includes natural trigger terms users would say: 'Create AGENTS.md', 'Update AGENTS.md file', 'Add agent instructions', 'Java repository', and 'cursor-rules-java'. These cover common phrasings well.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive — targets a very specific artifact (AGENTS.md) for a specific ecosystem (Java repositories) within a named project (cursor-rules-java). Unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

20%

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

This skill is essentially a high-level outline that defers all substantive content to an external reference file that isn't provided. It lacks any concrete examples, executable code, template snippets, or specific guidance that would make it actionable. The content is also verbose relative to its information density, with generic edge-case handling and restated descriptions padding the token count.

Suggestions

Add a concrete example of a minimal AGENTS.md output so Claude knows the target format without needing to read the reference file.

Replace the abstract workflow steps with specific, actionable instructions — e.g., what questions to ask in step 3, what sections to generate in step 4, with a template skeleton.

Remove generic edge-case handling (ask clarifying questions, report blockers) that Claude already knows how to do, and the 'What is covered' section that restates the description.

Include the bundle reference file (references/200-agents-md.md) or inline the most critical patterns/examples so the skill is self-sufficient for basic use.

Dimension	Reasoning	Score
Conciseness	The content is verbose and explains things Claude already knows. The 'What is covered' section restates the description, the constraints section includes generic edge-case handling that Claude inherently understands (ask clarifying questions, report blockers), and the bullet lists are padded with unnecessary context like 'This is an interactive SKILL' and 'of any complexity'.	1 / 3
Actionability	There is no concrete, executable guidance anywhere in the skill. No code examples, no template snippets, no specific commands, no sample AGENTS.md output. The workflow steps are abstract descriptions ('Gather role, tech stack...', 'Create AGENTS.md with...') rather than actionable instructions. All real content is deferred to a reference file that isn't provided.	1 / 3
Workflow Clarity	The workflow has a clear 4-step sequence (review → read reference → interactive capture → generate), which provides reasonable ordering. However, there are no validation checkpoints, no feedback loops for error recovery, and no concrete details about what each step actually entails. The steps read more like phase labels than actionable instructions.	2 / 3
Progressive Disclosure	The skill references a single external file (references/200-agents-md.md) which is appropriate one-level-deep disclosure. However, the bundle file is not provided, making it impossible to verify the reference exists or is useful. The main file itself contains too little actionable content — it's essentially an empty shell that delegates everything to the reference, which inverts the progressive disclosure pattern (overview should be self-sufficient for basic use).	2 / 3
	Total	6 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: jabrena/cursor-rules-java
Commit: 762cb86

Reviewed: 2 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.