AB synthetic-monitoring
Scheduled probes that run CONTINUOUSLY after release. Covers probe design for critical user journeys, alerting integration, SLA validation, multi-region monitoring, and the boundary between QA and SRE. Use when: "synthetic monitoring," "uptime testing," "scheduled probes," "SLA validation," "availability monitoring," "post-deploy checks." Not for: safe-release techniques during rollout — use testing-in-production. Not for: designing tests from prod telemetry — use observability-driven-testing. Not for: a one-shot post-deploy smoke gate tied to a release — use release-readiness. Related: testing-in-production, release-readiness, performance-testing, qa-metrics.
Scheduled probes that run CONTINUOUSLY after release.
As a process B 74/100 · Nearly there — weak spots: inputs and preconditions
How to improve
- 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
- warning
body-longSKILL.md body ≈ 5557 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 129): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 74/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, python, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5557 tokens
- 100Steps. 34 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 1 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
- low 14 top-level sections: this looks like several domains in one skill
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
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 668: enough signal without eating the budget
- +4Structure: 31 headings
- +3Step-by-step instructions: 34 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.