qa-quality-perspective

QA quality perspective

When to use

Use this at a requirements, strategy, review, test-case, or reporting stage when QA must assess testability, risk-based coverage, defect exposure, and quality risk from available evidence.

Inputs

• stage (required): requirements-analysis, test-strategy, test-strategy-review, code-review, test-case-writing, test-case-review, test-reporting, or test-report-review.
• The declared stage inputs and any available requirement, code, test, defect, environment, or execution evidence.

Workflow

1. Validate stage. If it is missing or unsupported, return Not applicable, list supported stages, and request a valid stage; do not generate filler conclusions.
2. Load and follow only the one Prompt mapped to that stage; never combine stage Prompts.
3. Apply that Prompt's input threshold. When materials are insufficient, state facts, gaps, and needed evidence rather than inventing tests, defects, or quality conclusions.
4. Produce a standalone QA quality report that separates facts, evidence, inference, missing evidence, and recommendations.

stage	Only Prompt to load
requirements-analysis	prompts/requirements-analysis.md
test-strategy	prompts/test-strategy.md
test-strategy-review	prompts/test-strategy-review.md
code-review	prompts/code-review.md
test-case-writing	prompts/test-case-writing.md
test-case-review	prompts/test-case-review.md
test-reporting	prompts/test-reporting.md
test-report-review	prompts/test-report-review.md

QA responsibilities and boundary

• Focus on testability, risk-based coverage, observability, test evidence, defect risk, untested scope, and quality risk.
• Treat only supplied material as fact; label inference and missing evidence. Never invent product intent, acceptance rules, implementation behavior, execution records, defects, or metrics.
• QA does not decide product intent, certify code correctness, or approve release. Without execution evidence, it must never infer that testing ran, passed, or verified quality.

Report contract

Unless returning Not applicable, include: Summary, Facts, Evidence, Inference, Testability, Risk-based coverage, Defects and quality risks, Missing evidence, Recommendations and next steps, Confidence. Tie every quality conclusion to evidence; classify risk as high, medium, or low with impact and uncertainty.

Pre-delivery check

• The stage is valid and exactly one matching Prompt was loaded
• Facts, evidence, inference, missing evidence, and recommendations are distinct
• Testability and risk-based coverage are assessed, or the reason they cannot be assessed is explicit
• No missing product intent, implementation fact, or execution result is reported as fact
• Without execution evidence, the report does not imply or claim executed, passed, or verified testing

On-demand loading and pitfalls

• Read only the mapped prompts/ file after stage is valid. Read evals/ for regression work, but never treat eval cases as project facts.
• Do not replace evidence with a generic risk checklist, or present test recommendations, static reading, or stakeholder opinion as a passing execution result.

Report provenance

Keep the selected stage, a stable source_id, and supplied version in the report header. If a source ID is absent, declare a temporary local locator; if version is absent, write unknown rather than inventing it. Each finding has a stable finding_id, its source/evidence locator and status. Each action links its finding and specifies the evidence that would close it; owner, date and action status stay unknown unless supplied. These are standalone report fields, not a dependency on another Skill.

Qualitative risk anchors

Use impact, observed likelihood signals, and uncertainty together; this is judgment, not arithmetic multiplication or a new score. Unknown likelihood stays unknown.

Risk	Impact and likelihood evidence	Uncertainty/action
High	Critical loss, blocking defect, or critical untested path; credible recurrence or unresolved exposure	Missing critical evidence prevents a confident low-risk claim; prioritize verification/escalation
Medium	Bounded impact or partial evidence with a plausible failure path	State the missing evidence and targeted follow-up
Low	Limited impact with supporting control evidence; no supplied critical exposure	State residual limits; do not equate low risk with release approval