003-agents-installation
Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination interactively and copying the embedded agent definitions from project assets. This should trigger for requests such as Install embedded agents; Bootstrap .cursor/agents; Bootstrap .claude/agents; Copy robot agents. Part of cursor-rules-java project
85
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 well-crafted skill description that clearly communicates what the skill does (installs embedded robot agents into specific directories), when to use it (with explicit trigger phrases), and provides enough specificity to distinguish it from other skills. The inclusion of multiple natural trigger phrases and the explicit 'Use when' clause make it effective for skill selection. Minor improvement could be made by slightly tightening the prose, but overall it's strong.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists specific concrete actions: installing embedded robot agents, selecting destination interactively, copying embedded agent definitions from project assets, and specifies the target directories (.cursor/agents, .claude/agents). | 3 / 3 |
Completeness | Clearly answers both 'what' (install embedded robot agents into .cursor/agents or .claude/agents by copying definitions from project assets) and 'when' (explicit 'Use when' clause plus 'This should trigger for' with specific example requests). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms that users would actually say: 'Install embedded agents', 'Bootstrap .cursor/agents', 'Bootstrap .claude/agents', 'Copy robot agents'. These cover multiple natural phrasings a user might use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: installing embedded robot agents into specific agent directories. The specific directory paths (.cursor/agents, .claude/agents) and the concept of 'embedded robot agents' from 'cursor-rules-java project' make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has a well-structured workflow with appropriate gating and validation steps, making it safe for an interactive file-copying operation. However, it lacks concrete actionable details (no actual file lists, no example commands, no output format examples) and defers too much to the reference file. Some sections are mildly redundant, with the 'What is covered' list overlapping the workflow.
Suggestions
Add a concrete example of the expected agent file list or at least a sample filename pattern so Claude knows what to copy without relying entirely on the reference file.
Include an example of the expected checklist output format in step 3 to make the reporting step fully actionable.
Remove the 'What is covered' bullet list since it duplicates information already present in the workflow section and constraints.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary explanation like the 'What is covered' section which largely duplicates the workflow, and phrases like 'This is an interactive skill' and 'Deterministic copy' add little value for Claude. | 2 / 3 |
Actionability | The workflow steps are clear in intent but lack concrete executable commands or code examples. There are no actual file paths for the embedded agents, no copy commands, and no example of what the checklist output should look like. The real actionable content is deferred to the reference file. | 2 / 3 |
Workflow Clarity | The three-step workflow is clearly sequenced with explicit validation checkpoints: wait for confirmation before copying, warn before overwriting, and report results with a checklist. The constraint about not copying until destination is confirmed acts as a proper gate. | 3 / 3 |
Progressive Disclosure | There is a clear reference to a single external file (references/003-agents-installation.md) which is good one-level-deep disclosure. However, no bundle files were provided to verify the reference exists, and the SKILL.md defers almost all concrete detail to that reference, making the skill body somewhat hollow without it. | 2 / 3 |
Total | 9 / 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
ef4eba3
- 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.