run-system-diagnostics
Run ACB (Anypoint Code Builder) system diagnostics to check if the machine meets minimum specifications and apply Windows optimizations if needed
74
61%
Does it follow best practices?
Impact
98%
1.84xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/mule-development/run-system-diagnostics/SKILL.mdQuality
Discovery
67%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 clearly communicates specific capabilities around ACB system diagnostics and Windows optimizations, establishing a distinct niche. However, it lacks an explicit 'Use when...' clause and could benefit from more natural trigger terms that users might actually say when experiencing issues.
Suggestions
Add a 'Use when...' clause such as 'Use when the user mentions ACB performance issues, system requirements, hardware compatibility, or Anypoint Code Builder running slowly'.
Include additional natural trigger terms like 'slow performance', 'system requirements', 'hardware check', 'ACB setup', or 'troubleshooting ACB'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'run system diagnostics', 'check if the machine meets minimum specifications', and 'apply Windows optimizations'. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (run diagnostics, check specs, apply optimizations), but lacks an explicit 'Use when...' clause or trigger guidance. The when is only implied by the nature of the actions described. | 2 / 3 |
Trigger Term Quality | Includes relevant terms like 'ACB', 'Anypoint Code Builder', 'system diagnostics', 'minimum specifications', and 'Windows optimizations'. However, it misses common user phrasings like 'slow performance', 'system requirements', 'hardware check', or 'ACB not working'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche: ACB/Anypoint Code Builder system diagnostics and Windows optimizations. This is unlikely to conflict with other skills due to the highly specific tool name and narrow scope. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels in actionability with concrete, executable commands and clear threshold values, and has a well-structured multi-step workflow with proper validation and user permission gates. However, it is excessively verbose—explaining things Claude already knows, repeating instructions, and inlining all platform-specific details into a single monolithic file that would benefit greatly from progressive disclosure via separate reference files.
Suggestions
Reduce verbosity by removing explanatory comments Claude doesn't need (e.g., 'This creates a 1GB test file required for IOPS testing', 'Returns bytes, divide by 1073741824 to get GB') and trust Claude to interpret commands from their flags.
Split platform-specific sections (Windows optimizations, macOS commands) into separate referenced files (e.g., WINDOWS_OPTIMIZATIONS.md, MACOS_COMMANDS.md) to keep the main SKILL.md as a concise overview.
Consolidate repeated display instructions ('IMMEDIATELY display a table') into a single output format section rather than restating it in multiple steps.
Remove redundant notes like 'For non-Windows systems, do NOT mention Windows-specific optimizations at all'—Claude can infer this from the OS detection step.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~150+ lines with significant redundancy. It explains obvious concepts (what NVMe is, what IOPS testing does, how to divide bytes to get GB), repeats display instructions multiple times, and includes excessive hand-holding that Claude doesn't need (e.g., 'Note: DiskSpd requires a pre-existing file to test against'). Many instructions describe intent rather than just providing the commands. | 1 / 3 |
Actionability | The skill provides fully executable PowerShell and macOS commands for every diagnostic step, specific DiskSpd commands with exact flags, concrete threshold values (10,000 IOPS read, 8,000 IOPS write), exact file paths, and specific PowerShell commands for Defender exclusions and power plan changes. All commands are copy-paste ready. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (detect OS → gather info → compare specs → Windows optimizations → output). It includes validation checkpoints (verify diskspd.exe exists after extraction, check existing exclusions before adding new ones), error recovery (handle download failures gracefully, handle admin privilege errors), and explicit user permission gates before destructive/system-modifying operations. | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to external files. The Windows-specific optimizations (IOPS testing, Defender exclusions, power plan) could easily be split into separate referenced documents. The macOS and Windows command sets inline make the file very long and hard to navigate. No bundle files are provided to support splitting, but the content itself is poorly organized for its length. | 1 / 3 |
Total | 8 / 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
- mulesoft/mulesoft-dx
- Commit
32e2b58
- 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.