performance-analysis

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

4.65x

Quality

50%

Does it follow best practices?

Impact

93%

4.65x

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

50%Weight 40%Scale 1-3

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 concrete commands, MCP examples, and CI integration, but it is severely over-long: monolithic and padded with full report mockups, a JS script, and option catalogs that belong in separate reference files. Workflow sequencing is present but lacks explicit validation feedback loops for the destructive '--fix' and batch CI operations.

Suggestions

Move the ASCII output mockup, sample markdown report, full Node.js analysis script, and CI/CD YAML into separate reference files (e.g. references/report-template.md, references/ci-integration.md) and link to them one level deep from the overview.

Add explicit validation checkpoints to the '--fix' workflow (e.g. 'Run detection, review proposed fixes, apply to a dev swarm, re-detect to confirm improvement, then roll forward') and to the CI threshold job (fail-build criteria and re-run guidance).

Trim the inline metrics catalogs and 'Related Commands'/'See Also' lists to the essential triggers, since Claude can derive routine command help from the tool itself.

Dimension	Reasoning	Score
Conciseness	The ~554-line body is padded with an ASCII report mockup, a full sample markdown report, a complete Node.js analysis script, CI/CD YAML, and exhaustive option/metric catalogs that Claude does not need in-context, fitting 'verbose; padded with unnecessary context'.	1 / 3
Actionability	It provides fully executable, copy-paste-ready commands (e.g. 'npx claude-flow bottleneck detect --swarm-id swarm-123 -t 24h'), MCP calls, CI YAML, and a working JS script, fitting 'fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	Capabilities are sequenced into numbered sections with command syntax and examples, but the destructive/batch '--fix' and CI threshold workflows lack explicit validate-then-checkpoint feedback loops, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The body is a monolithic document with sample reports, scripts, and CI config inline and no bundle files; sectioning is decent but content that should be split into separate reference files is inline, fitting 'some structure but content that should be separate is inline'.	2 / 3
	Total	8 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 states the skill's purpose clearly and is scoped to Claude Flow swarms, but it omits any explicit 'use when' trigger guidance and relies on domain-level actions rather than sharply concrete operations. It is functional but generic, lacking the trigger terms and completeness that would let Claude reliably select it.

Suggestions

Add an explicit 'Use when ...' clause naming natural user triggers, e.g. 'Use when diagnosing slow swarm tasks, agent communication delays, or when planning performance optimization for Claude Flow swarms'.

Replace abstract action words with concrete operations the skill performs, such as 'detects communication/processing/memory/network bottlenecks, generates HTML/JSON performance reports, and auto-applies topology and caching fixes'.

Broaden trigger-term coverage with phrasings users actually say (e.g. 'slow agents', 'task latency', 'swarm performance', 'cache hit rate', 'profiling').

Dimension	Reasoning	Score
Specificity	Names concrete actions ('performance analysis', 'bottleneck detection', 'optimization recommendations') but these are domain-level abstractions rather than multiple distinct concrete operations, fitting 'names domain and some actions but not comprehensive'.	2 / 3
Completeness	It clearly states what the skill does but provides no 'when should Claude use it' trigger; per guidelines a missing 'Use when...' clause caps completeness at 2.	2 / 3
Trigger Term Quality	'performance analysis' and 'bottleneck' are genuine user terms, but coverage lacks common variations and there is no natural trigger phrasing, fitting 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	Scoping to 'Claude Flow swarms' gives a clear niche, but without explicit distinct triggers it could still overlap with general monitoring skills, fitting 'somewhat specific but could still overlap'.	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 (564 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/agentic-flow
Path: .claude/skills/performance-analysis/SKILL.md
Commit: d3735a3

Reviewed: 11 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.