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
59
67%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/200-agents-md/SKILL.mdQuality
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, when to use it, and includes explicit trigger phrases. The only minor issue is the use of second person ('adapts to your specific project needs', 'you need to'), which per the rubric guidelines should be penalized, but the overall quality is high with excellent specificity, trigger terms, and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generating AGENTS.md files, 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 AGENTS.md 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' plus explicit trigger phrases like 'Create AGENTS.md', 'Update AGENTS.md file'). | 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 variations of how users would request this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (AGENTS.md generation for Java repositories in the cursor-rules-java project). Unlikely to conflict with other skills due to the narrow domain and specific file type. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable high-level structure for an interactive AGENTS.md generation process, with good edge case handling. However, it critically lacks actionability — there are no concrete examples of what the generated AGENTS.md should look like, no template, no sample questions for the interactive phase, and no executable guidance. The skill essentially delegates all substantive content to a reference file that isn't available for evaluation.
Suggestions
Add a concrete example of what a generated AGENTS.md looks like (even a minimal template) so Claude knows the target output format without needing to read the reference file.
Include specific questions or a structured checklist for the 'interactive requirements capture' step, so the conversation flow is actionable rather than abstract.
Add a validation step after generation (e.g., 'Verify the generated AGENTS.md covers all required sections: role, tech stack, file structure, commands, Git workflow, boundaries') to improve workflow clarity.
Remove the redundant 'What is covered in this Skill?' section — this information is already conveyed by the workflow steps and the opening sentence.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanation (e.g., 'What is covered in this Skill?' section largely repeats information already conveyed by the workflow and title). The bullet list of coverage areas is somewhat redundant with the workflow steps. However, it's not egregiously verbose. | 2 / 3 |
Actionability | The skill provides no concrete code, commands, templates, or executable examples. It describes a process at a high level ('Run interactive requirements capture', 'Generate AGENTS.md artifact') but gives no specific guidance on what to actually produce, no example output format, no template structure, and defers everything to a reference file that isn't provided. | 1 / 3 |
Workflow Clarity | The four workflow steps are listed in a logical sequence and the edge cases provide some guardrails. However, there are no validation checkpoints, no feedback loops for error recovery, and the steps are too abstract — e.g., 'Run interactive requirements capture' doesn't specify what questions to ask or what constitutes completion. | 2 / 3 |
Progressive Disclosure | The skill references `references/200-agents-md.md` for detailed guidance, which is a good one-level-deep reference. However, no bundle files were provided, so we can't verify the reference exists or is well-structured. The main file itself contains content that could be tightened (the coverage list is redundant), and the reference is mentioned twice without clear differentiation of what's in each mention. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%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
26e9744
- Reviewed
Table of Contents
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.