performance-analysis
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms
57
37%
Does it follow best practices?
Impact
97%
2.77xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/performance-analysis/SKILL.mdQuality
Discovery
32%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 identifies a specific domain (Claude Flow swarms) and lists high-level capabilities, but lacks a 'Use when...' clause, which is a significant gap for skill selection. The trigger terms are somewhat relevant but miss natural user language variations, and the actions described remain at an abstract level rather than listing concrete operations.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks about swarm performance, slow agents, task throughput, or wants to optimize a Claude Flow swarm configuration.'
Include more specific concrete actions, e.g., 'Profiles agent execution times, identifies task queue bottlenecks, analyzes inter-agent communication overhead, and suggests parallelism or routing improvements.'
Add natural keyword variations users might use, such as 'slow swarm', 'agent latency', 'swarm profiling', 'task throughput', or 'swarm debugging'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Claude Flow swarms) and lists some actions (performance analysis, bottleneck detection, optimization recommendations), but these are somewhat high-level and not fully concrete—e.g., it doesn't specify what kinds of bottlenecks, what metrics are analyzed, or what form recommendations take. | 2 / 3 |
Completeness | The description answers 'what does this do' at a moderate level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also only moderately detailed, this scores at 1. | 1 / 3 |
Trigger Term Quality | Includes relevant terms like 'performance analysis', 'bottleneck detection', 'optimization', and 'Claude Flow swarms', but misses common natural variations users might say such as 'slow swarm', 'swarm profiling', 'agent performance', 'throughput', or 'latency'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Claude Flow swarms' provides some niche specificity, but 'performance analysis' and 'optimization recommendations' are generic enough to potentially overlap with other performance or optimization skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable guidance with concrete CLI commands and code examples, which is its primary strength. However, it is severely bloated—containing extensive sample outputs, redundant category listings, generic best practices, and complete scripts that should be in separate files. The lack of explicit validation workflows for destructive operations (--fix) and the monolithic structure significantly reduce its effectiveness as a skill document.
Suggestions
Reduce content to ~100 lines by moving sample outputs, CI/CD YAML, custom scripts, and troubleshooting into separate referenced files (e.g., EXAMPLES.md, CI-INTEGRATION.md, TROUBLESHOOTING.md)
Remove generic best practices (e.g., 'Learn from each analysis', 'Share with team regularly') that Claude already knows and don't add skill-specific value
Add an explicit validation workflow for the --fix flag: detect → review output → confirm → apply fix → verify improvement
Eliminate redundant listings of bottleneck categories that appear in multiple sections (metrics analyzed, common patterns, optimization recommendations all overlap)
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines. Contains extensive sample outputs, redundant examples, and sections like 'Best Practices' and 'Continuous Optimization' that are generic advice Claude already knows. The CI/CD YAML, custom analysis scripts, and detailed troubleshooting sections bloat the document significantly without adding proportional value. Many sections repeat similar information (e.g., bottleneck categories listed multiple times). | 1 / 3 |
Actionability | Provides fully executable CLI commands, concrete MCP function calls with parameters, complete JavaScript scripts, CI/CD YAML configurations, and specific command-line options with clear syntax. All examples are copy-paste ready with real flags and arguments. | 3 / 3 |
Workflow Clarity | While individual commands are clear, there's no explicit multi-step workflow with validation checkpoints for the overall analysis process. The 'Analyze and Auto-Fix' flow lacks a validation step between detection and fixing. The best practices section mentions 'always review before applying --fix' but this isn't integrated into the workflow as an explicit checkpoint. The --fix flag performs destructive operations without a clear verify-then-apply sequence. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with everything inline. Despite referencing external files in 'See Also' section, the SKILL.md itself contains ~400+ lines of detailed content including full sample reports, complete CI/CD configs, and custom scripts that should be in separate referenced files. The 'See Also' links use absolute paths suggesting poor organization, and no bundle files are provided to support the references. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (581 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- ruvnet/ruvector
- Commit
c2089c4
- 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.