agent-performance-monitor

Agent skill for performance-monitor - invoke with $agent-performance-monitor

2.43x

Quality

—

Does it follow best practices?

Impact

100%

2.43x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

27%

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

The body is a monolithic, verbose dump of illustrative architecture code with no progressive disclosure and no real workflow checkpoints. Its only genuinely actionable part is the small block of claude-flow CLI commands, while the rest is non-executable scaffolding that should be moved into reference files.

Suggestions

Collapse the SKILL.md body to a concise overview of capabilities plus the executable claude-flow CLI commands, and move the class architecture into reference files under references/.

Make code examples executable and self-contained or explicitly mark illustrative scaffolding as pseudocode, rather than presenting partial class definitions that call undefined dependencies.

Add a sequenced operational workflow with validation checkpoints (e.g., collect -> validate metrics -> analyze -> alert) so monitoring tasks have explicit feedback loops.

Dimension	Reasoning	Score
Conciseness	The body is roughly 670 lines of illustrative JavaScript class definitions padded with restating comments ('// Advanced metrics collection system', '// Multi-dimensional metrics collection') and architectural detail Claude already understands, far exceeding a lean overview.	1 / 3
Actionability	The 'Operational Commands' bash section ('npx claude-flow performance-report --format detailed --timeframe 24h') is concrete and executable, but the bulk of the content is class scaffolding that references undefined types and mcp.* calls, so it is not copy-paste runnable.	2 / 3
Workflow Clarity	Capabilities are loosely sequenced as numbered sections (1-4), but there is no executable multi-step workflow and no validation or feedback checkpoints despite monitoring/batch-style operations, capping clarity at 2.	2 / 3
Progressive Disclosure	There are no bundle files in references/, scripts/, or assets/ and the body references none; the entire capability surface sits as a monolithic inline wall of code rather than an overview pointing to one-level-deep reference files.	1 / 3
	Total	6 / 12 Passed

Description

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 frontmatter description is a low-information template string that names the domain without concrete actions, natural triggers, or an explicit use-when clause. It reads as boilerplate rather than guidance that would help a user or Claude select this skill.

Suggestions

Replace the description with concrete actions in third person, e.g. 'Collects real-time system and agent metrics, detects bottlenecks, and monitors SLA compliance.'

Add an explicit trigger clause such as 'Use when investigating performance issues, tracking SLA violations, or diagnosing resource bottlenecks in a swarm.'

Drop the 'invoke with $agent-performance-monitor' invocation hint and include natural user-facing keywords (metrics, bottleneck, latency, SLA, anomaly).

Dimension	Reasoning	Score
Specificity	The phrase 'Agent skill for performance-monitor' names a domain but lists no concrete actions (e.g., collect metrics, detect bottlenecks, monitor SLA); it is abstract template language. The imperative 'invoke with' is second-person voice, which would already push specificity below the floor, so it remains 1.	1 / 3
Completeness	It gives only a weak 'what' (an agent skill for performance monitoring) and entirely lacks a 'Use when...' or equivalent 'when' trigger clause, so neither half is adequately answered.	1 / 3
Trigger Term Quality	'invoke with $agent-performance-monitor' is an invocation hint, not natural language a user would say; the only term, 'performance-monitor', is internal jargon and there are no common variations like 'metrics', 'bottleneck', or 'SLA'.	1 / 3
Distinctiveness Conflict Risk	'performance-monitor' provides a recognizable niche, but the generic 'Agent skill for X' framing could still overlap with other optimization/resource/monitoring skills rather than carving a distinct trigger space.	2 / 3
	Total	5 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (677 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ruvnet/claude-flow
Commit: 03d4f84

Reviewed: 2 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.