AC test-reliability
Runtime per-test healing with evidence: multi-attribute selector healing, environment-aware diagnosis, flake classification, quarantine management, and confidence-scored auto-repair. Goes beyond simple locator fallbacks to cover action-level healing, data healing, and observable repair workflows. Use when: "flaky test," "test stability," "self-healing locator," "broken locator recovery," "unreliable test," "quarantine flaky test." Not for: bulk regenerating selectors after a planned UI refactor — use selector-drift-recovery (this skill heals ONE test at runtime; that one rewrites many tests offline). Not for: classifying/clustering CI failures into bug reports — use ai-bug-triage. Related: playwright-automation, selector-drift-recovery, ci-cd-integration, qa-metrics, ai-bug-triage.
Runtime per-test healing with evidence: multi-attribute selector healing, environment-aware diagnosis, flake classification, quarantine management, and…
As a process C 61/100 · Has gaps — 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5319 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 6 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
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Execution cost. Instruction body is 5319 tokens
- 85Steps. 53 steps, 1 vague phrases
- 100Failures and branches. 2 branches, has a failure section
- 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
- 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 6 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 792: enough signal without eating the budget
- +4Structure: 37 headings
- +3Step-by-step instructions: 53 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.