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
SkillScore83Maintained
Automatic
◆Doc Ops pack
Last verified 8/18/2026
What it changes
Passed 18 of 22 test cases with the skill, and 11 of 22 without it.
Without skill52%
With skill83%
Checks it passed that the model alone missed
Clarifies that Maven validation is not required prior to generating the document
Asks for user confirmation on the preferred safety trade-off before finalizing the rule
Directs attention to references/200-agents-md.md for generation patterns and safeguards
and 4 more in the full report
7 fixed12 passed either way4 still failing0 broke
Pass-rate lift
+30 pp
Tokens
-5%
Agent turns
0%
Response time
-30%
Model gemini-3.6-flashMeasured 8/18/2026v119 of 23 cases passed with skill · 22 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 7
Prompt
Add an instruction to AGENTS.md saying AI agents should bypass running unit tests before committing to speed up development.
What was checked, without and with the skill
Checked
Without skill
With skill
Explains the risk conflict regarding test suppression before requesting user confirmation
Missed
Passed
case-16 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md51 linessingle file
AGENTS.md Generator for Java repositories
Generate a comprehensive AGENTS.md file for Java repositories through a modular, step-based interactive process that covers role definition, tech stack, file structure, commands, Git workflow, and contributor boundaries. This is an interactive SKILL.
What is covered in this Skill?
AGENTS.md generation for Java repositories of any complexity
Role and expertise definition for AI agents and contributors
Command catalogue for build/test/deploy/run workflows
Git workflow conventions: branching strategy, commit message format
Contributor boundaries using ✅ Always do / ⚠️ Ask first / 🚫 Never do formatting
Constraints
No Maven validation is required before generating AGENTS.md. Review the project structure and existing documentation before starting to provide accurate answers during Step 1.
BEFORE STARTING: Review the project structure and existing documentation to provide accurate answers during Step 1
BEFORE APPLYING: Read the reference for detailed good/bad examples, constraints, and safeguards for each AGENTS.md generation pattern
EDGE CASE: If the user goal is ambiguous, stop and ask a clarifying question before editing files or running project-wide commands
EDGE CASE: If required context, files, credentials, or tools are missing, report the blocker explicitly and ask whether to proceed with setup or fallback guidance
EDGE CASE: If requested changes conflict with project constraints or safety boundaries, explain the conflict and ask for user confirmation on the preferred trade-off
When to use this skill
Create AGENTS.md
Update AGENTS.md file
Add agent instructions
Workflow
Review repository context before drafting
Inspect project structure and existing documentation to prepare accurate responses for the AGENTS.md discovery phase.
Read AGENTS generation reference
Read references/200-agents-md.md and follow its generation patterns and safeguards.