performance-analysis

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

2.77x

Quality

61%

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%Weight 40%Scale 1-5

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

The body is highly actionable with abundant executable commands and integration examples, but it is over-long for a SKILL.md, inlines material that belongs in separate reference files, and lacks explicit validation checkpoints around the destructive --fix operation.

Suggestions

Add an explicit validation/feedback loop for --fix (e.g. detect -> review proposed fixes -> apply in dev -> re-measure -> verify improvement) to lift workflow clarity above 3.

Move the bulk API reference, sample output blocks, CI/CD YAML, and the custom analysis script into separate reference files referenced one level deep from SKILL.md.

Trim promotional material (e.g. the 'Self-Learning Intelligence' section) and redundant sample outputs to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The ~580-line body is mostly concrete commands and outputs but is padded with promotional fluff ('Self-Learning Intelligence'), large sample ASCII/markdown/JSON output blocks, and a full CI/CD YAML plus a custom analysis script that could be trimmed; not 2 because most material is actionable rather than conceptual filler.	3 / 5
Actionability	Provides copy-paste-ready commands with flags, MCP integration code, a CI/CD workflow, and a complete custom analysis script covering the common cases; fully executable guidance.	5 / 5
Workflow Clarity	Quick Start and Fix Strategy give a rough sequence, but the destructive/batch '--fix' path has no explicit validation checkpoint (validate -> review -> retry), so per the rubric cap workflow clarity at 3; not below 3 because steps are listed and ordered.	3 / 5
Progressive Disclosure	Good section headers provide structure, but all reference material (API/options, sample outputs, CI/CD, full scripts) is inlined in one monolithic file with no bundle files, and 'See Also' links point to paths outside the bundle that do not exist; not 2 because internal sectioning is clear.	3 / 5
	Total	14 / 20 Passed

Description

58%Weight 40%Scale 1-5

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 what the skill does with several concrete, domain-scoped actions, but omits any explicit 'Use when' trigger guidance, which caps its completeness. Trigger-term coverage is relevant but lacks the natural phrasings a user would say.

Suggestions

Add an explicit 'Use when ...' clause listing natural triggers (e.g. 'Use when a Claude Flow swarm is slow, when investigating bottlenecks, or when generating performance reports').

Include common-synonym trigger terms users actually say ('slow', 'speed up', 'profiling', 'latency') alongside the technical terms.

Tighten 'Comprehensive performance analysis' into a more concrete action to push specificity toward 5.

Dimension	Reasoning	Score
Specificity	Names three concrete actions ('bottleneck detection', 'optimization recommendations', 'performance analysis') scoped to Claude Flow swarms, with only minor coverage gaps; falls short of 5 because 'comprehensive performance analysis' is a somewhat generic umbrella action.	4 / 5
Completeness	Clearly states what the skill does but provides no 'Use when...' trigger clause; per the rubric a missing explicit trigger guidance caps completeness at 3, and this is not below 3 since the 'what' is concrete.	3 / 5
Trigger Term Quality	Relevant domain keywords are present but missing common natural variations a user would actually say (e.g. 'slow swarm', 'speed up', 'profiling', 'why is my swarm lagging'); not below 3 because the included terms are apt for the niche.	3 / 5
Distinctiveness Conflict Risk	The 'for Claude Flow swarms' qualifier carves a distinct niche with low conflict risk against unrelated skills; not 5 because 'performance analysis' broadly could overlap with general profiling/monitoring skills.	4 / 5
	Total	14 / 20 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: 74d2a60

Reviewed: 3 days 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.