BA datadog-monitor-designer
Design Datadog monitors that catch real production issues without paging on noise. Covers SLO-based monitoring with multi-window multi-burn-rate alerts, the decision between threshold/anomaly/forecast/outlier/composite monitor types, tag-driven routing, downtime windows, monitor template inheritance per service tier, notification message engineering, and runbook linking. Acts as a senior SRE who has owned 4,000+ Datadog monitors and pruned them down to 600 monitors that still catch every real incident. Knows the Datadog billing levers (custom metrics, indexed logs, ingested traces), how `from`/`group_by` interact with no-data evaluation, the difference between simple alerts and multi-alerts, and which monitor types are silently expensive. Use when monitors are paging on cosmetic blips, when a service tier needs a coherent monitor set, when SLOs need turning into burn-rate alerts, or when monitor sprawl is unmanageable. Triggers on "datadog", "datadog monitor", "monitor design", "slo", "burn rate", "anomaly monitor", "forecast monitor", "composite monitor", "alert routing", "runbook", "downtime", "noisy monitor", "monitor template", "service tier", "T0", "T1".
Design Datadog monitors that catch real production issues without paging on noise.
As a process A 81/100 · Runs to the end — weak spots: result and completion
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1177 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5977 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 97): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 81/100
- 0Result and completion. Does not say what the result is
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5977 tokens
- 100Tools and files. No external tools needed
- 100Steps. 81 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1177: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +4Structure: 18 headings
- +3Step-by-step instructions: 81 items
- +4Has examples (14 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 51.