dt-obs-hosts

Host and process metrics including CPU, memory, disk, network, containers, and process-level telemetry. Use when analyzing infrastructure health, resource utilization, process consumption, or host discovery. Also use when building timeseries queries for host metrics that feed into analytical workflows like anomaly detection, forecasting, or seasonality analysis. Trigger: "show hosts", "CPU usage", "memory utilization", "disk space", "high CPU", "host with most free disk", "top hosts by CPU", "top processes by memory", "Linux hosts in AWS", "what databases are running", "infrastructure costs by cost center", "hosts running EOL Java", "container monitoring", "listening ports", "process resource consumption", "CPU forecast", "memory anomaly", "host seasonality". Do NOT use for explaining existing queries, product documentation questions, Kubernetes pod/workload queries (use dt-obs-kubernetes), AWS cloud resource inventory (use dt-obs-aws), or service-level metrics (use dt-obs-services).

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%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.

A well-structured, highly actionable skill body with strong progressive disclosure and executable DQL throughout. The only slack is mild prose redundancy in the analytical and 'When to Use' sections relative to the frontmatter description.

Suggestions

Tighten the Analytical Workflows prose (e.g., the novelty-type selection rule and detector-choice paragraphs) into bullet directives to reduce overlap with the description and cut tokens.

The 'When to Use This Skill' example list largely duplicates the description's Trigger block — consolidate to avoid repeating the same trigger phrases twice.

Make the implicit verification checkpoints explicit in the numbered analytical workflows (e.g., a 'Verify the timeseries returned data before passing to the analysis tool' step).

Dimension	Reasoning	Score
Conciseness	Dense and mostly token-efficient — every workflow carries concrete DQL, real metric names, and thresholds — but the Analytical Workflows prose and the 'When to Use' list echo content already in the description and could be trimmed slightly.	4 / 5
Actionability	Each of 8 workflows ships copy-paste-ready executable DQL with specific metric identifiers, functions (getNodeName), and real thresholds; the Common Query Patterns section provides reusable templates, covering the common cases fully.	5 / 5
Workflow Clarity	Workflows are numbered 1–8 and analytical steps are explicitly sequenced, with a Troubleshooting table serving as error recovery; being read-only query work there is no destructive-validation requirement, but a few checkpoints are implicit rather than explicit.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with a dedicated 'When to Load References' section, well-signaled one-level-deep references (host-metrics.md, process-monitoring.md, container-monitoring.md, inventory-discovery.md — all verified present), and consistent '→' navigation pointers.	5 / 5
	Total	18 / 20 Passed

Description

100%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.

An exemplary description: concrete capabilities, comprehensive natural trigger phrases, explicit what/when guidance, and clear negative boundaries against sibling skills. No meaningful gaps.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete capabilities — 'CPU, memory, disk, network, containers, and process-level telemetry' plus 'building timeseries queries' and analytical workflows (anomaly detection, forecasting, seasonality) — matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (host and process metrics...) and 'when' ('Use when analyzing...', 'Also use when building timeseries queries...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Extensive natural trigger phrases a user would actually say — 'show hosts', 'CPU usage', 'high CPU', 'host with most free disk', 'top hosts by CPU', 'memory anomaly', 'host seasonality' — covering synonyms and variations as the top anchor requires.	5 / 5
Distinctiveness Conflict Risk	Clear niche with explicit negative boundary guidance — 'Do NOT use for ... Kubernetes pod/workload queries (use dt-obs-kubernetes), AWS cloud resource inventory (use dt-obs-aws), or service-level metrics (use dt-obs-services)' — minimizing conflict risk.	5 / 5
	Total	20 / 20 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: Dynatrace/dynatrace-for-ai
Path: skills/dt-obs-hosts/SKILL.md
Commit: 3287f9d

Reviewed: 5 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.