AB observability-driven-testing
Use production telemetry as INPUT to design new tests. Covers OpenTelemetry integration with tests, trace-based assertions, log-informed test creation, production-error analysis for coverage gaps, and telemetry-driven test prioritization. Use when: "trace-based testing," "design tests from logs," "OpenTelemetry assertions," "production errors point to test gaps," "telemetry-driven testing." Not for: safe rollout techniques (flags, canary) during release — use testing-in-production. Not for: scheduled post-deploy probes — use synthetic-monitoring. Not for: triaging CI failures — use ai-bug-triage. Related: testing-in-production, synthetic-monitoring, qa-metrics, ai-bug-triage.
Use production telemetry as INPUT to design new tests.
As a process B 65/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
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 ≈ 5334 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 75, 172): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 9 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 70Execution cost. Instruction body is 5334 tokens
- 100Tools and files. No external tools needed
- 100Steps. 32 steps
- 100Consistency. Name and required fields are in place
- 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
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 684: enough signal without eating the budget
- +4Structure: 33 headings
- +3Step-by-step instructions: 32 items
- +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: 86.