performance-analysis

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

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

63%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 content is richly actionable with concrete commands, examples, and integration code, and workflows are clearly sequenced with validation guidance for the risky --fix path. Its main weakness is verbosity and total lack of progressive disclosure — a ~550-line monolith that inlines full scripts, sample reports, and CI config instead of splitting them into referenced files.

Suggestions

Move the full JS custom-analysis script, CI/CD YAML, sample report mockups, and detailed metrics/option tables into separate files under references/ and link to them from SKILL.md to apply progressive disclosure.

Trim the emoji-art sample output and the complete output-format mockup to a compact representative excerpt; keep only what Claude needs to interpret results.

Add an explicit validate→fix→retry loop for the --fix batch operation (detect, review flagged changes, apply, re-run detection to confirm improvement) to lift workflow clarity to a 5.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose (~550 lines) and inlines large padded blocks that do not all earn their tokens — a full emoji-art sample report, a complete custom JS analysis script, a full CI/CD YAML, and complete output-format mockups. While not explaining concepts Claude already knows, the sheer volume of illustrative padding matches anchor 2 (several unnecessary padded sections) more than the tighter anchor 3.	2 / 5
Actionability	Guidance is fully executable and copy-paste ready: concrete commands with documented options and defaults, multiple worked examples per capability, MCP integration calls, a JS integration script, and a CI/CD YAML. This matches anchor 5 (fully executable, copy-paste ready, covering common cases) and is above anchor 4 only by degree of coverage.	5 / 5
Workflow Clarity	Each capability is clearly sequenced (command syntax, options, examples, output) and the --fix batch operation has validation guidance ('Always review before applying --fix', 'Test fixes in development first', 'Monitor impact after changes'). This fits anchor 4 (clear sequence with most checkpoints, minor gaps); it is not anchor 5 because there is no explicit validate→fix→retry feedback loop, and not anchor 3 because checkpoints for the risky --fix path are present rather than absent.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent) and the SKILL.md is a monolithic document with good section headers but everything inlined — full scripts, sample reports, option references, and CI config that would belong in separate reference files. This matches anchor 3 (some structure but content that should be separate is inline) rather than anchor 2 only because the section structure itself is well organized.	3 / 5
	Total	14 / 20 Passed

Description

53%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 states a clear 'what' tied to a specific product niche but omits any 'when to use' trigger guidance, capping completeness. Trigger terms are only partially natural and lack common synonyms. Distinctiveness is reasonably strong thanks to the Claude Flow swarms scoping.

Suggestions

Add an explicit 'Use when ...' clause naming natural trigger phrases (e.g., profiling swarm operations, diagnosing slow agent coordination, generating performance reports).

Broaden trigger-term coverage with synonyms users actually say — 'profiling', 'metrics', 'slow tasks', 'agent utilization' — rather than relying on the product term 'swarms'.

Replace the padding word 'Comprehensive' with one more concrete capability (e.g., 'generating HTML/JSON reports') to lift specificity.

Dimension	Reasoning	Score
Specificity	Names the domain ('performance analysis ... for Claude Flow swarms') and lists 2-3 actions ('bottleneck detection', 'optimization recommendations', 'performance analysis'), but these are high-level categories rather than the concrete operations seen in the anchor 4/5 examples; the qualifier 'Comprehensive' adds no specificity. It sits above anchor 2 (which only names the domain) but below anchor 4 (which lists several specific concrete actions).	3 / 5
Completeness	It clearly states what the skill does (analysis, bottleneck detection, optimization recommendations) but provides no 'Use when...' clause or equivalent trigger guidance; per the rubric a missing explicit trigger caps completeness at 3. It is not anchor 2 because the 'what' is concrete, and not anchor 4 because 'when' is entirely absent rather than weakly present.	3 / 5
Trigger Term Quality	It includes some relevant keywords a user might say ('performance analysis', 'bottleneck') but pairs them with product-specific jargon ('Claude Flow swarms') and omits common natural variations/synonyms ('profiling', 'metrics', 'speed up', 'slow'). This matches anchor 3 (some relevant keywords but missing common variations) rather than anchor 4's broader coverage.	3 / 5
Distinctiveness Conflict Risk	Scoping to 'Claude Flow swarms' gives it a clear niche with mostly-distinct triggers and only minor overlap risk with general monitoring/profiling skills. It is above anchor 3 (which could still overlap with similar skills) but below anchor 5 because the generic 'performance analysis/bottleneck' framing could still collide with adjacent performance skills.	4 / 5
	Total	13 / 20 Passed

Validation

81%

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 — 13 / 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: 3 missing, 2 suspicious	Warning

	Total	13 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/performance-analysis/SKILL.md
Commit: b14c79e

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.