agent-performance-monitor

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

2.43x

Quality

29%

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

30%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 a large pseudo-architectural catalog: mostly non-executable JavaScript class sketches with undefined helper dependencies, a duplicated stray frontmatter block (lines 6–11) that should not be in the body, and no ordered workflow or validation checkpoints. Only the bash command section and the prose integration-point lists are concretely usable. The skill would benefit most from being rewritten as a short overview plus executable commands and reference files.

Suggestions

Replace the pseudocode class catalog with executable guidance: keep the npx claude-flow commands, add real metric-collection and analysis procedures, and delete the stub classes that depend on undefined helpers (mcp.agent_list, CircularBuffer, CPUBottleneckDetector).

Define an ordered workflow for using the agent (e.g. collect baseline metrics → analyze bottlenecks → check SLA thresholds → alert/escalate) with explicit validation checkpoints, instead of an unsequenced capability taxonomy.

Move the class implementations and MCP integration detail into references/ files linked from a concise SKILL.md overview, and remove the duplicate frontmatter block at the top of the body.

Dimension	Reasoning	Score
Conciseness	The ~670-line body is dominated by padded stub classes (MetricsCollector, BottleneckAnalyzer, SLAMonitor, ResourceTracker, AnomalyDetector, DashboardProvider) whose method bodies mostly restate section titles, matching 'Noticeably verbose; several unnecessary explanations or padded sections'. Not anchor 1 because it does not explain concepts Claude already knows.	2 / 5
Actionability	The 'Operational Commands' section gives concrete npx claude-flow commands, but the bulk of the body is pseudocode with undefined dependencies (mcp.agent_list, CircularBuffer, CPUBottleneckDetector, this.getCPUUsage(), EnsembleDetector) — matching 'Some concrete guidance but incomplete; pseudocode instead of executable code'. Not anchor 4 because almost none of the JavaScript is runnable as written.	3 / 5
Workflow Clarity	The body is a capability catalog with no step sequence anywhere and no validation checkpoints, matching 'Steps missing or incoherent; no sequence; no validation'. Even the 'MCP Integration Hooks' section describes monitoring tasks rather than an ordered procedure, so it does not reach anchor 2's 'rough sequence present'.	1 / 5
Progressive Disclosure	Section headers provide real structure, but roughly 600 lines of class implementations that clearly belong in separate reference files are inlined in a single monolithic SKILL.md with no bundle files (references/, scripts/, assets/ are all absent), matching 'Some structure but could be better organized; content that should be separate is inline'. Not anchor 4 because nothing is split out and navigation is by scrolling, not references.	3 / 5
	Total	9 / 20 Passed

Description

28%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 is boilerplate metadata ('Agent skill for performance-monitor - invoke with $agent-performance-monitor') that identifies the domain but conveys no capabilities, no usage triggers, and no natural keywords. A second, richer description ('Real-time metrics collection, bottleneck analysis, SLA monitoring and anomaly detection') is stranded in the body's stray frontmatter block instead of the actual frontmatter. This is a near-failure description that would rarely be surfaced when needed.

Suggestions

Replace the boilerplate with concrete actions from the body's own capability list, e.g. 'Collects real-time system and agent metrics, detects bottlenecks, monitors SLA compliance, and flags anomalies in swarm performance.'

Add an explicit trigger clause: 'Use when the user mentions performance, latency, throughput, SLA compliance, or bottleneck analysis for agent swarms.'

Fold in natural trigger-term variants (metrics, resource utilization, response time, anomaly) so the skill is discoverable from the ways users actually phrase these needs.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for performance-monitor - invoke with $agent-performance-monitor' names the domain but lists zero concrete actions or capabilities, matching 'Names the domain but actions are minimal or generic'. It is not entirely vague (anchor 1) because the performance-monitoring domain is explicitly identified.	2 / 5
Completeness	It has a vague 'what' ('agent skill for performance-monitor') and no 'when' clause — 'invoke with $agent-performance-monitor' is invocation syntax, not usage guidance — exactly matching 'Has a vague what and no when'. Not anchor 1 because a what is present; not anchor 3 because the what is boilerplate rather than clear.	2 / 5
Trigger Term Quality	Only 'performance-monitor' and 'invoke' appear; natural phrases users would say (metrics, latency, throughput, SLA, bottleneck, slow agent) are absent, matching 'One or two generic keywords; missing the natural phrases users say'. Not anchor 3 because there is no meaningful keyword coverage beyond the domain name.	2 / 5
Distinctiveness Conflict Risk	The 'performance-monitor' niche is somewhat specific, matching 'Somewhat specific but could still overlap with similar skills' — the templated boilerplate format would be nearly identical to any other performance/monitoring skill. Not anchor 4 because nothing in the wording distinguishes it from sibling skills.	3 / 5
	Total	9 / 20 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/ruflo
Path: .agents/skills/agent-performance-monitor/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.