CtrlK
BlogDocsLog inGet started
Tessl Logo

dt-setup-oneagent

Reference knowledge for installing, uninstalling, or creating-and-installing Dynatrace OneAgent across VM/server, Kubernetes (Operator + DynaKube), AWS Lambda (layer + env vars, plus optional fresh function provisioning), Windows hosts, remote Linux hosts / EC2 instances over SSH, and Azure VMs / VM Scale Sets. Returns documented endpoints, env vars, token scopes, and copy-paste-ready commands. Returns the exact commands to run rather than executing them. Use when the user asks to install or uninstall OneAgent, or asks "how do I…", "what URL/scope/var do I need for…", or "explain the OneAgent deployment for X".

77

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 dense, well-structured operational reference: executable commands with correct auth handling, explicit validation and rollback checkpoints for the risky operations, and clean one-level-deep navigation to five real reference files. Its only weakness is mild prose redundancy in the Hard-rules section, which could be tightened without losing any rule.

DimensionReasoningScore

Conciseness

Nearly every token is Dynatrace-specific knowledge Claude cannot know (URL normalization, token-prefix-to-header mapping, dtctl quirks), but the Hard-rules prose has minor restatement that could be trimmed (e.g. "not to 'demonstrate', not 'while we're at it', not preemptively"; "The input is authoritative; the rule above is about…"). Not 3 — there is no generic explanation of concepts Claude already knows.

4 / 5

Actionability

"wget -O Dynatrace-OneAgent-Linux.sh --header=\"Authorization: ${DT_AUTH}\"…", the full install/uninstall commands with flags, and the executable dtctl fallback snippet are copy-paste ready, with the remaining targets fully specified in the references. Not 4 — the inline commands are complete and correct for the base case, with per-target coverage delegated rather than missing.

5 / 5

Workflow Clarity

An explicit reading order ("They share the rules, URL normalization and token guidance above — read those first, then the one you need") plus explicit validation checkpoints and recovery loops: "Check the output really is JSON first, and fall back to scraping", "State the tenant you are about to use and let the user correct you", "Take a rollback snapshot before the first write", read-merge-write for collection-replacing writes.

5 / 5

Progressive Disclosure

The body is a genuine overview — shared rules, URL normalization, token guidance, the base VM case — and each target points to an existing, one-level-deep reference (aws-lambda.md, azure-vm.md, kubernetes.md, remote-vm-ec2.md, windows.md all present on disk), signalled in both a by-target and a by-platform navigation table with rationale for the one seeming overlap (managed Kubernetes inside kubernetes.md).

5 / 5

Total

19

/

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 specific, comprehensive, and trigger-rich: it states concrete capabilities and deliverables in third person and pairs them with explicit, naturally-worded 'Use when…' triggers that quote how a user would actually ask. It is long, but every clause carries information about a distinct target or deliverable rather than padding.

DimensionReasoningScore

Specificity

"installing, uninstalling, or creating-and-installing Dynatrace OneAgent" plus "Returns documented endpoints, env vars, token scopes, and copy-paste-ready commands" lists multiple concrete actions and deliverables across six enumerated target types — comprehensive, not just several actions with gaps.

5 / 5

Completeness

The what ("Reference knowledge for… Returns documented endpoints, env vars, token scopes, and copy-paste-ready commands") and the when ("Use when the user asks to install or uninstall OneAgent, or asks 'how do I…'") are both explicit and concrete; third-person voice is used consistently.

5 / 5

Trigger Term Quality

"install or uninstall OneAgent", "how do I…", "what URL/scope/var do I need for…", "explain the OneAgent deployment for X" are verbatim natural user phrasings, covering synonyms of how the request would actually be worded.

5 / 5

Distinctiveness Conflict Risk

"Dynatrace OneAgent", "Operator + DynaKube", "AWS Lambda (layer + env vars)" name a clear niche with distinct triggers; virtually no overlap risk with generic install or cloud skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

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
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.