arn-infra-monitor
This skill should be used when the user says "set up monitoring", "arn infra monitor", "infra monitor", "configure monitoring", "set up observability", "add logging", "configure alerting", "set up alerts", "infrastructure monitoring", "add metrics", "set up cloudwatch", "configure grafana", "observability setup", "logging setup", "alerting setup", "health checks", "monitor infrastructure", "arn-infra-monitor", "set up cloud monitoring", "configure notifications", "prometheus", "datadog", "new relic", "sentry", or wants to set up logging, metrics collection, and alerting for their deployed infrastructure.
52
58%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/arn-infra/skills/arn-infra-monitor/SKILL.mdQuality
Discovery
54%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a long list of trigger terms with almost no explanation of what the skill actually does. While the trigger coverage is excellent, the complete absence of concrete capability descriptions (e.g., what monitoring configurations it creates, what platforms it supports, what outputs it produces) makes it difficult for Claude to understand the skill's actual functionality. The description would benefit greatly from leading with specific actions before listing trigger terms.
Suggestions
Add concrete capability descriptions at the beginning, e.g., 'Configures infrastructure monitoring stacks including CloudWatch alarms, Grafana dashboards, Prometheus exporters, and alerting pipelines. Sets up logging aggregation, metrics collection, and notification channels.'
Restructure to separate the 'what it does' from the 'when to use it' — lead with capabilities, then follow with a 'Use when...' clause containing the trigger terms.
Reduce the trigger term list to the most distinctive and common terms rather than exhaustively listing every variation, which adds noise without improving selection accuracy.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lacks concrete actions. It never states what the skill actually does — no specific capabilities like 'configures CloudWatch alarms', 'sets up Grafana dashboards', or 'deploys Prometheus exporters' are mentioned. The only hint of actions is the vague trailing clause 'set up logging, metrics collection, and alerting for their deployed infrastructure.' | 1 / 3 |
Completeness | The 'when' is thoroughly addressed with explicit trigger phrases, but the 'what' is extremely weak — there is no clear explanation of what the skill actually does beyond the vague mention of 'logging, metrics collection, and alerting.' The description is almost entirely a trigger list with no capability description. | 2 / 3 |
Trigger Term Quality | The description includes an extensive list of natural trigger terms users would say, covering tool names (CloudWatch, Grafana, Prometheus, Datadog, New Relic, Sentry), common phrases ('set up monitoring', 'configure alerting', 'add metrics'), and variations. This is strong keyword coverage. | 3 / 3 |
Distinctiveness Conflict Risk | The extensive trigger list helps narrow the domain to infrastructure monitoring/observability, but the breadth of tools mentioned (CloudWatch, Grafana, Prometheus, Datadog, New Relic, Sentry) could overlap with tool-specific skills. The lack of specificity about what it actually configures makes it harder to distinguish from more targeted monitoring skills. | 2 / 3 |
Total | 8 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured monitoring setup skill with a clear 8-step workflow, good error handling, and experience-level-adaptive guidance. Its main weaknesses are verbosity (describing general monitoring concepts Claude already knows) and limited actionability (delegating IaC generation to a specialist agent without showing concrete code examples). The progressive disclosure intent is good but cannot be fully verified without bundle files.
Suggestions
Trim the logging and metrics sections to remove general knowledge (e.g., what CloudTrail is, what structured logging means) and focus on project-specific configuration decisions and concrete IaC patterns.
Add at least one concrete, executable IaC example (e.g., a minimal CloudWatch alarm in Terraform) so Claude has a template even if the specialist agent fails.
Move the detailed alert thresholds table and log retention table into a reference file (e.g., `references/default-alert-config.md`) to reduce the main skill's length while keeping it accessible.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~250 lines) and includes some information Claude could infer (e.g., explaining what structured logging means, listing what CloudTrail/VPC Flow Logs are). The tables and stack recommendations are useful but could be more compact. Some sections like 'Configure Logging' and 'Configure Metrics' describe general best practices rather than project-specific instructions. | 2 / 3 |
Actionability | The skill provides clear workflow steps and specific glob patterns for scanning, but lacks executable code examples. The IaC generation is delegated to a specialist agent via a context block rather than showing concrete Terraform/CloudFormation snippets. The alert thresholds table is concrete and actionable, but the logging and metrics sections are more descriptive than executable. | 2 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with explicit validation points: checking prerequisites before proceeding, presenting configurations for user approval before writing, offering adjustment options, and including a comprehensive error handling section with fallback strategies. The feedback loop in Step 7 (approve/adjust/regenerate) is well-designed. | 3 / 3 |
Progressive Disclosure | The skill references external files like `observability-stack-guide.md`, `alerting-patterns.md`, `experience-derivation.md`, and various manifest files, which suggests good intent for progressive disclosure. However, no bundle files were provided to verify these references exist, and the main SKILL.md itself is quite long with inline content (logging tables, metrics lists, alert tables) that could potentially be in reference files. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- AppsVortex/arness
- Commit
b9084b6
- Reviewed
Table of Contents
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.