CtrlK
BlogDocsLog inGet started
Tessl Logo

dt-obs-network-devices

Analyze SNMP-monitored network devices (switches, routers, firewalls, load balancers) in Dynatrace. Three data layers: Smartscape topology (`EXT_NETWORK_DEVICE` / `EXT_NETWORK_INTERFACE` nodes, `belongs_to` and `calls` edges); `com.dynatrace.extension.network_device.*` metrics (CPU, memory, uptime, throughput, saturation, errors); and logs (SNMP traps, syslog, auto-discovery). Use to inventory devices, find down or saturated interfaces, check device CPU/memory/uptime, map topology and neighbors, detect interface errors, and investigate traps and syslog events. Trigger: "network device", "switch", "router", "firewall", "SNMP", "interface status", "interface down", "interface utilization", "link saturation", "device CPU", "device memory", "device uptime", "device neighbors", "LLDP", "CDP", "SNMP trap", "syslog". Do NOT use for network flow/traffic or top talkers (use dt-obs-network-flows), host NIC throughput (use dt-obs-hosts), or service request/latency (use dt-obs-services).

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 well-structured routing skill: it frames the three Dynatrace data layers, mandates a monitoring-mode check, routes each question type to a validated reference file, and disambiguates from sibling skills. Minor conciseness trimming would push it to the top band.

Suggestions

Trim the illustrative 'answers questions such as' line and the 'vs network flows' callout, or fold them into the routing/Related Skills tables, to lift conciseness toward 5.

Add one short inline end-to-end DQL snippet (e.g. a joined device+interface query) so the body is copy-paste-ready for the most common case, improving actionability.

Optionally make the monitoring-mode check an explicit numbered step 0 in the Routing section so the workflow checkpoint is unmissable.

DimensionReasoningScore

Conciseness

Dense and mostly lean — every section serves routing or the Dynatrace data model rather than restating SNMP basics — but a few passages (the illustrative questions list, the 'vs network flows' callout) could be trimmed; not 5 because of these minor over-explanatory instances, not 3 because the body largely assumes Claude's competence.

4 / 5

Actionability

Provides concrete DQL fragments, namespaces, node types, and field tables that route each question, with executable queries deliberately deferred to the validated reference files; not 5 because the body itself is not copy-paste-ready full queries, not 3 because the guidance is concrete and mostly executable.

4 / 5

Workflow Clarity

Clear routing workflow with an explicit 'first thing to check' checkpoint (monitoring_mode before assuming a data gap) and numbered routing rules; not 5 because it lacks formal validate→fix→retry feedback loops, not 3 because the sequence and key checkpoint are present (and the skill is non-destructive, so no validation cap applies).

4 / 5

Progressive Disclosure

A clear overview that points to three well-signaled one-level-deep reference files (topology-model.md, metrics.md, logs.md), all of which exist under references/, with a dedicated Reference Files section; not 4 because navigation and content split are clean and complete.

5 / 5

Total

17

/

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.

The description is exemplary: concrete capabilities, a comprehensive trigger list, explicit what/when guidance, and active conflict disambiguation via a do-not-use clause. Every dimension lands at the top anchor.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'inventory devices, find down or saturated interfaces, check device CPU/memory/uptime, map topology and neighbors, detect interface errors, and investigate traps and syslog events' — with comprehensive coverage matching the score-5 anchor; not 4 because there are no real coverage gaps.

5 / 5

Completeness

Explicitly answers what ('Analyze SNMP-monitored network devices … Three data layers …') and when (a dedicated 'Trigger:' list), plus a 'Do NOT use for' boundary, hitting the score-5 anchor; not 4 because both what and when are concrete and explicit.

5 / 5

Trigger Term Quality

An extensive Trigger list covers natural phrases and synonyms ('interface status', 'interface down', 'interface utilization', 'link saturation') plus acronyms (LLDP, CDP, SNMP), matching the comprehensive-coverage anchor; not 4 because common variations are thoroughly covered.

5 / 5

Distinctiveness Conflict Risk

Clear SNMP-device niche with distinct triggers and explicit routing away from sibling skills (dt-obs-network-flows, dt-obs-hosts, dt-obs-services), minimizing conflict risk; not 4 because overlap risk is actively disambiguated.

5 / 5

Total

20

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 5 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
Dynatrace/dynatrace-for-ai
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.