AC test-case-management
Author and maintain MANUAL and hybrid test cases and suites in TestRail, Xray (Jira), Zephyr Scale, and Qase. Covers test-case anatomy (title, preconditions, steps, expected results, test data), suite/section organization, bulk authoring from user stories and acceptance criteria, ambiguous-step linting, CSV/API import-export payloads per tool, requirement traceability and coverage gaps, review hygiene, and when a manual case should graduate to automation. Use when: "write a test case," "manual test case," "TestRail case," "Xray test," "Zephyr Scale case," "Qase case," "import CSV into TestRail," "lint these steps," "traceability report," "should this be automated." Not for: Generating automated TEST CODE — that is ai-test-generation. Sprint-level WHAT-to-test selection — that is test-planning. Related: ai-test-generation, test-planning, exploratory-testing, qa-project-context.
Author and maintain MANUAL and hybrid test cases and suites in TestRail, Xray (Jira), Zephyr Scale, and Qase.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 178): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 51/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 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
- 70Execution cost. Instruction body is 4769 tokens
- 85Steps. 47 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- low 16 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (5 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
- +3Description length 889: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 24 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.