agent-performance-monitor

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

2.43x

Quality

15%

Does it follow best practices?

Impact

100%

2.43x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-performance-monitor/SKILL.md

Quality

Content

22%

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

The body is an oversized, monolithic dump of non-executable JavaScript class skeletons plus a smaller set of usable CLI commands. It lacks a sequenced workflow with validation and does not split detail into reference files.

Suggestions

Trim the class skeletons to the essential, runnable pieces and remove the duplicate YAML block and Agent Profile; keep only what Claude cannot infer.

Provide executable, self-contained examples (define or import the referenced helpers, or replace them with concrete CLI/library calls).

Add a numbered workflow with validation checkpoints (e.g. collect metrics -> analyze -> validate thresholds -> alert) and move the detailed class references into files under references/.

Dimension	Reasoning	Score
Conciseness	The ~660-line body is padded with illustrative class scaffolding, redundant section comments, a duplicate YAML frontmatter block, and an Agent Profile that restates the description — far beyond what Claude needs to act.	1 / 3
Actionability	The "Operational Commands" bash snippets (e.g. "npx claude-flow performance-report") are executable, but the bulk of the code references undefined classes (CPUBottleneckDetector, MLAnomalyDetector, CircularBuffer) and undefined mcp.* helpers, making it skeleton/pseudocode rather than copy-paste ready.	2 / 3
Workflow Clarity	Content is organized by capability, not as a sequenced process; there are no validation checkpoints or feedback loops for what is a complex multi-step monitoring operation.	1 / 3
Progressive Disclosure	Section headings give it some structure, but everything is inline in a single 670-line monolith with no reference files (references/scripts/assets are empty) — content that clearly should be split out is not.	2 / 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 templated, near-empty string that names a domain but states no concrete capabilities and provides no trigger guidance. It reads as boilerplate rather than a usable skill trigger.

Suggestions

Replace the description with concrete third-person actions, e.g. "Collects real-time metrics, detects bottlenecks, monitors SLA compliance, and flags anomalies."

Add an explicit trigger clause such as "Use when the user asks about agent/swarm performance, bottlenecks, SLA compliance, or resource utilization."

Drop the meta invocation syntax ("invoke with $...") from the description; that belongs in usage docs, not the trigger text.

Dimension	Reasoning	Score
Specificity	The phrase "Agent skill for performance-monitor" names a domain but lists zero concrete actions (no collection, analysis, or monitoring verbs), matching the vague/abstract anchor rather than the "names domain and some actions" anchor above.	1 / 3
Completeness	It offers only a weak "what" ("Agent skill for performance-monitor") and entirely omits any "Use when..." or equivalent trigger guidance, so it fails to answer either half clearly.	1 / 3
Trigger Term Quality	"invoke with $agent-performance-monitor" is invocation syntax rather than natural keywords a user would say; no terms like "performance", "metrics", "SLA", or "bottleneck" appear in the description.	1 / 3
Distinctiveness Conflict Risk	The performance-monitor niche is specific, but the templated "Agent skill for X - invoke with $X" phrasing is generic and could overlap with similarly-named skills, so it is not a clearly distinct niche.	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
Path: .agents/skills/agent-performance-monitor/SKILL.md
Commit: 26c35b5

Reviewed: about 16 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.