render-monitor

Monitor Render services in real-time. Check health, performance metrics, logs, and resource usage. Use when users want to check service status, view metrics, monitor performance, or verify deployments are healthy.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

72%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 body is highly actionable with executable MCP calls and CLI fallbacks plus useful threshold tables, and it practices good progressive disclosure with one real reference. Its main weaknesses are some repetitive code blocks and the absence of explicit validation checkpoints in the health-check workflow.

Suggestions

De-duplicate the shared list_services()/list_logs()/get_metrics() examples between the Quick Health Check and Quick Reference sections to reduce token redundancy.

Add an explicit post-check checkpoint to the health-check workflow (e.g. 'If any check fails, drill into the failing service via get_service and recent error logs').

Consolidate the per-metric resourceId boilerplate by defining the service-id placeholder once and referencing it, rather than repeating full get_metrics blocks for each metric type.

Dimension	Reasoning	Score
Conciseness	The body avoids explaining concepts Claude already knows and uses compact threshold tables, but the Quick Health Check and Quick Reference sections repeat the same list_services()/list_logs()/get_metrics() calls, and metric subsections repeat the resourceId boilerplate, so it could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready tool calls (e.g. get_metrics with explicit metricTypes, query_render_postgres with real SQL) and concrete CLI commands, matching the score-3 anchor.	3 / 3
Workflow Clarity	The 5-step Quick Health Check is clearly sequenced and threshold tables supply decision criteria, but there are no explicit validation checkpoints or error-recovery feedback loops (e.g. 'if errors found, investigate X'), leaving checkpoints implicit.	2 / 3
Progressive Disclosure	The SKILL.md is an overview with a single one-level-deep, clearly signaled reference to references/metrics-guide.md (verified to exist), giving easy navigation without nested references.	3 / 3
	Total	10 / 12 Passed

Description

100%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 is concise, concrete, and explicitly scoped to the Render platform with a clear 'Use when...' trigger clause. It answers both what the skill does and when to invoke it without fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Check health, performance metrics, logs, and resource usage' — matching the score-3 anchor for listing multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Monitor Render services... Check health, performance metrics, logs, and resource usage') and when ('Use when users want to check service status, view metrics...').	3 / 3
Trigger Term Quality	Includes natural user phrasing — 'check service status, view metrics, monitor performance, or verify deployments are healthy' — with good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Scoped to 'Render services' with Render-specific triggers, giving it a clear niche unlikely to conflict with non-Render skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/render/skills/render-monitor/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.