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. Part of the skills-for-java project

Quality

53%

Does it follow best practices?

Impact

Pending

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

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.

This is a well-structured description that clearly states what the skill does and when to use it, with a specific niche (AGENTS.md for Java repos) that minimizes conflict risk. The main weakness is trigger term coverage — it relies on users knowing the term 'AGENTS.md' rather than including alternative phrasings users might naturally use. The description also uses second person ('your specific project needs') which is a minor style issue but doesn't severely impact functionality.

Suggestions

Add alternative trigger terms users might naturally say, such as 'agent instructions', 'repository documentation', 'coding guidelines file', or 'project contributor guide'

Rephrase to third person voice — replace 'you need to' and 'your specific project needs' with something like 'Generates an AGENTS.md file for Java repositories... adapts to the specific project's needs'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 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 ('Use when you need to generate an AGENTS.md file for a Java repository').	3 / 3
Trigger Term Quality	Includes some relevant keywords like 'AGENTS.md', 'Java repository', 'tech stack', 'Git workflow', but misses common user phrasings. Users might say 'agent instructions', 'project documentation', 'coding guidelines', or 'repository setup docs' which aren't covered.	2 / 3
Distinctiveness Conflict Risk	Very specific niche: AGENTS.md generation for Java repositories. The combination of AGENTS.md + Java + specific coverage areas makes it highly distinctive and unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Implementation

22%

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

This skill content reads more like a feature description or README than an actionable skill. It claims to be a step-based interactive process but defines zero steps, provides no templates or examples, and defers all concrete guidance to a reference file. The content fails to give Claude enough information to actually perform the task without relying entirely on the external reference.

Suggestions

Add the actual step-by-step interactive workflow directly in the SKILL.md (e.g., Step 1: Gather project info, Step 2: Define roles, Step 3: Map file structure, etc.) with clear instructions for each step.

Include a concrete example of a generated AGENTS.md snippet or template so Claude knows the expected output format.

Add validation checkpoints — e.g., 'Confirm tech stack details with user before proceeding to file structure mapping.'

Remove the redundant 'What is covered' section and fold any unique information into the workflow steps themselves.

Dimension	Reasoning	Score
Conciseness	The skill has some unnecessary verbosity — the 'What is covered' bullet list largely restates the opening sentence, and the constraints section has some redundancy (e.g., 'Review the project structure' appears twice). However, it's not egregiously padded.	2 / 3
Actionability	The skill provides no concrete steps, commands, code, templates, or examples for generating an AGENTS.md file. It describes what the skill covers but never instructs how to do it — all actual guidance is deferred to the reference file.	1 / 3
Workflow Clarity	Despite claiming to be a 'step-based interactive process,' no steps are actually defined in the skill content. There is no sequence, no validation checkpoints, and no workflow structure — just a description that steps exist somewhere.	1 / 3
Progressive Disclosure	There is a clear reference to a detailed file (references/200-agents-md.md), which is good. However, the SKILL.md itself contains almost no actionable overview content — it's essentially an empty shell pointing to the reference, making the split feel like the main content is missing rather than appropriately delegated.	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: 9ec21dd

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.