AB release-readiness
Validate release readiness with evidence-based go/no-go decisions. Covers go/no-go checklists, smoke test suite design, staged rollout validation, rollback criteria and procedures, and post-deployment verification. Ensures release confidence comes from data, not feelings. Use when: "release ready," "go/no-go," "smoke test," "release checklist," "rollback plan," "staged rollout," "canary deploy." Not for: safe-release techniques (flags, canary, dark launch) applied during the rollout itself — use testing-in-production; scheduled probes that run continuously after release — use synthetic-monitoring; designing new tests from prod telemetry — use observability-driven-testing. Related: testing-in-production, qa-metrics, ci-cd-integration, ai-system-testing.
Validate release readiness with evidence-based go/no-go decisions.
As a process B 71/100 · Nearly there — weak spots: result and completion
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 ≈ 6439 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 264): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 71/100
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6439 tokens
- 85Steps. 141 steps, 2 vague phrases
- 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 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 762: enough signal without eating the budget
- +4Structure: 48 headings
- +3Step-by-step instructions: 141 items
- +4Has examples (2 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: 88.