CtrlK
BlogDocsLog inGet started
Tessl Logo

dt-platform-costs

Query and analyze a Dynatrace tenant's ACTUAL billing and usage data with DQL against dt.system.events — DPS consumption breakdown, cost-normalized spend ranking, included volume deduction, chargeback/showback, cost drivers, spending trends, cost investigation, metrics ingest optimization, query cost attribution, workflow total cost, entity-level cost drill-down (RUM, hosts, synthetic, K8s), and AI/LLM cost (AI Units, AI Function Standard Calls, AI-generated query consumption). Directs licensing/entitlement questions to documentation (not via DQL). USE ONLY to query/analyze the tenant's actual consumption. Do NOT use for conceptual 'explain' questions about how DPS billing/pricing works or what units/weights/the rate card mean — see Dynatrace documentation. Do NOT use for making DQL queries faster or cheaper to run (query optimization, reducing scanned data/consumption per run, filter-early best practices) — that belongs to dt-dql-essentials. This skill MEASURES consumption; it does not tune queries.

70

Quality

85%

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

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.

A well-structured, highly actionable skill body that uses progressive disclosure effectively and gives explicit, copy-ready workflows. The main drag is conciseness: the STOP/scope guidance and cost_weight prohibitions are restated several times and could be consolidated.

Suggestions

Consolidate the repeated 'Billing Concepts — STOP' and 'Licensing — STOP' guidance — keep one canonical STOP section and have the intent table link to it instead of restating the full prescription in multiple places.

Reduce repetition of the 'never display cost_weight as a dollar amount' prohibition: state the rule once in Cost Ranking Rules and reference it from the Usage vs Cost section rather than restating.

Trim the top banner so it signals scope in 2-3 lines and delegates the full prescription to the named STOP sections, avoiding near-duplicate wording with the frontmatter description.

DimensionReasoningScore

Conciseness

Mostly efficient and operational, but the 'Billing Concepts — STOP' / 'Licensing — STOP' guidance and the cost_weight prohibitions are repeated across the top banner, dedicated STOP sections, the intent table, and the Cost Ranking Rules — more than minor trimming.

3 / 5

Actionability

Provides a copy-paste Quick Start DQL query, exact pipeline fragments ('| filter isNotNull(cost_weight) | sort cost_weight desc | fields ...'), and a concrete example output table with verbatim disclaimers to copy.

5 / 5

Workflow Clarity

Cost Ranking Rules are a clear 4-step checklist with explicit checkpoints ('Disclaimer BEFORE results') and an 'Empty results?' feedback loop, though the deeper investigation workflows' validation lives in the referenced files.

4 / 5

Progressive Disclosure

SKILL.md is a clean overview with a Knowledge Base Structure table and intent-mapping table routing to 8 verified one-level-deep reference files with section anchors — content is appropriately split and easy to navigate.

5 / 5

Total

17

/

20

Passed

Description

92%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.

A highly specific, well-scoped description that clearly states what the skill does, when to use it, and where its boundaries are. Minor trigger-term naturalness is the only weak spot; everything else is strong.

DimensionReasoningScore

Specificity

Lists many concrete actions — 'consumption breakdown', 'cost-normalized spend ranking', 'included volume deduction', 'chargeback/showback', 'query cost attribution', 'workflow total cost', 'entity-level cost drill-down' — giving comprehensive capability coverage.

5 / 5

Completeness

Explicitly answers both what ('Query and analyze a Dynatrace tenant's ACTUAL billing and usage data') and when ('USE ONLY to query/analyze... Do NOT use for conceptual explain questions...'), with concrete trigger and anti-trigger phrases.

5 / 5

Trigger Term Quality

Strong natural-term coverage with synonyms (billing, usage, consumption, spend, cost) but leans technical (DPS, DQL) and omits a few lay phrasings like 'how much am I spending'.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche (Dynatrace DPS billing via DQL) and explicitly differentiates from dt-dql-essentials (query optimization), dt-biz-cloud-costs (AWS/FOCUS), and conceptual billing docs, minimizing conflict risk.

5 / 5

Total

19

/

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.