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. Part of the skills-for-java project
59
48%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/003-agents-installation/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description is functional and clearly scoped, with an explicit 'Use when' clause and a distinct niche that minimizes conflict risk. Its main weaknesses are moderate specificity in listing concrete actions and limited coverage of natural trigger terms users might employ. The description could benefit from additional user-facing keywords and slightly more detail on what the embedded agent definitions contain or do.
Suggestions
Add natural trigger term variations such as 'set up agents', 'configure agent definitions', 'copy agents', or 'agent installation' to improve discoverability.
Rewrite in third person voice (e.g., 'Installs embedded robot agents into .cursor/agents or .claude/agents...') instead of second person ('you need to') to align with style guidelines.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a specific domain (installing embedded robot agents) and mentions concrete actions like selecting destination interactively and copying agent definitions, but the actions are somewhat narrow and could be more clearly enumerated as distinct capabilities. | 2 / 3 |
Completeness | The description explicitly answers both 'what' (install embedded robot agents by copying definitions from project assets) and 'when' ('Use when you need to install the embedded robot agents into either .cursor/agents or .claude/agents'), with a clear 'Use when...' clause at the start. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like '.cursor/agents', '.claude/agents', 'embedded robot agents', and 'project assets', but these are fairly technical. Users might say things like 'install agents', 'set up agents', or 'configure agent definitions' which aren't covered. The term 'skills-for-java' provides project context but isn't a natural trigger. | 2 / 3 |
Distinctiveness Conflict Risk | This is a very specific niche task — installing embedded robot agents into specific directory paths (.cursor/agents or .claude/agents) from project assets. It's unlikely to conflict with other skills due to its narrow, well-defined scope. | 3 / 3 |
Total | 10 / 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 is essentially a thin pointer to a reference file with high-level constraints but no actionable content in the body itself. It lacks concrete commands, a clear step-by-step workflow, and any validation/verification steps. The content describes intent rather than providing executable guidance.
Suggestions
Add a concrete step-by-step workflow: 1) Ask user for target directory, 2) List source files from the assets path, 3) Copy files with specific commands/code, 4) Report what was created vs overwritten.
Include the actual source path and expected file names of the six-agent bundle so Claude knows exactly what to copy without needing to discover it.
Add a validation step after installation (e.g., verify all six files exist in the target directory and report success/failure).
Provide an example interaction showing the user prompt and expected output so Claude knows the exact format to follow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary filler like 'What is covered in this Skill?' bullet list that largely restates the constraints section. The 'When to use this skill' section is keyword-stuffing for matching rather than adding value. | 2 / 3 |
Actionability | No concrete code, commands, or executable steps are provided. The skill describes what must happen at a high level but doesn't show how to do it—no file copy commands, no directory creation, no example interaction flow. | 1 / 3 |
Workflow Clarity | There is no sequenced workflow. The constraints mention asking the user and copying files, but there's no step-by-step process, no validation checkpoint for successful copy, and no error handling guidance for overwrite scenarios. | 1 / 3 |
Progressive Disclosure | There is a reference to a detailed file (references/003-agents-installation.md), which is good progressive disclosure. However, the SKILL.md itself provides almost no actionable overview content, making the reference feel like a redirect rather than a complement to a useful summary. | 2 / 3 |
Total | 6 / 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.
9ec21dd
Table of Contents
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.