performance-analysis

Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms

2.77x

Quality

57%

Does it follow best practices?

Impact

97%

2.77x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/performance-analysis/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with rich executable examples, but it is a verbose monolith padded with redundancy and platitudes, and its batch auto-fix workflow lacks explicit validation checkpoints. Splitting detail into reference files and trimming boilerplate would materially improve it.

Suggestions

Move the full CI/CD YAML, JS analysis script, ASCII report mockups, and detailed metric catalogs into separate reference files, leaving SKILL.md a concise overview with one-level-deep links.

Add an explicit validate-then-retry checkpoint to the `--fix` workflow (e.g. re-run bottleneck detection after applying fixes and confirm impact improved before proceeding).

Trim padding: remove the 'Self-Learning Intelligence' marketing text, collapse near-duplicate command examples, and cut Best-Practice/Troubleshooting platitudes that restate commands already shown.

Dimension	Reasoning	Score
Conciseness	The body has an efficient executable core (commands, options, JSON formats) but is heavily padded with redundancy: near-duplicate example sets, full CI/CD YAML and JS scripts, ASCII report mockups, 'Self-Learning Intelligence' marketing fluff, and Best-Practice/Troubleshooting platitudes that restate known commands, so it is mostly efficient with significant unnecessary context.	2 / 3
Actionability	It provides fully executable, copy-paste-ready guidance throughout: concrete `npx claude-flow` commands with flags, MCP call examples with arguments, complete CI/CD YAML, a runnable JS script, and concrete JSON result schemas, exceeding the pseudocode/incomplete threshold.	3 / 3
Workflow Clarity	Capabilities are sequenced into clear numbered sections and flows, but the risky batch `--fix` auto-optimization path has no explicit validation checkpoint or verify-after-fix loop (only implicit best-practice advice), which caps workflow clarity at 2 for destructive/batch operations.	2 / 3
Progressive Disclosure	It is a single ~560-line monolithic file with no bundle references (references/scripts/assets absent), and the only links are external/sibling paths; content that belongs in separate reference files (full scripts, CI/CD config, detailed metric catalogs) is inline, though internal sectioning is reasonable.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 conveys the skill's domain and core actions and is scoped to Claude Flow swarms, but it omits an explicit 'Use when...' trigger and relies on somewhat abstract action nouns. It is competent but not exemplary, scoring 2 across all dimensions.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when analyzing Claude Flow swarm performance, diagnosing slow tasks, or optimizing agent coordination.'

Replace abstract action nouns with sharper concrete verbs and add common user phrasings like 'profiling', 'slow agents', and 'metrics' to improve trigger term coverage.

Sharpen distinctiveness by naming the specific artifacts produced (e.g. 'generates HTML/JSON performance reports and applies safe auto-fixes') so it is less likely to overlap with generic monitoring skills.

Dimension	Reasoning	Score
Specificity	The description names concrete actions in a domain ('bottleneck detection', 'optimization recommendations', 'performance analysis'), but these are abstract action nouns rather than vivid concrete operations like 'extract text, fill forms, merge documents', so it names the domain and some actions without being comprehensive.	2 / 3
Completeness	It clearly states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance for when Claude should invoke it, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	It includes relevant natural terms ('performance analysis', 'bottleneck detection', 'Claude Flow swarms') but lacks common variations a user might say such as 'profiling', 'slow', 'speed up', or 'metrics', so keyword coverage is partial.	2 / 3
Distinctiveness Conflict Risk	Scoping to 'Claude Flow swarms' gives it a niche, but 'performance analysis' is a broad capability that could overlap with other monitoring/analysis skills, so it is somewhat specific yet could still conflict.	2 / 3
	Total	8 / 12 Passed

Validation

75%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 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
relative_links	Relative link issues: 5 suspicious	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	12 / 16 Passed

Repository: ruvnet/ruvector
Path: .claude/skills/performance-analysis/SKILL.md
Commit: 6a6c39e

Reviewed: about 13 hours ago

Table of Contents

Discovery Implementation Validation

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.