git:20260903.6713296 to git:20261011.7d9502b

8 added, 0 removed. Audit A to A.

---

name: ai-assisted-testing

description: Use this skill when you need AI-assisted testing workflows such as test data generation, root-cause analysis, and prioritization; triggers include AI-assisted testing and AI for QA.

---

# AI-Assisted Testing

**Chinese version：** See the corresponding Chinese skill.

## When to Use

- Need help with ai assisted testing in a real project context.

- Need an output that can be used directly for execution, review, or follow-up.

## Workflow

1. Read and follow the main prompt listed under Progressive disclosure (coverage, structure, quality bar).

2. Add only project context that changes the result: scope, environment, constraints, risks, dependencies, expected deliverable.

3. If input is incomplete, return a usable first draft and explicitly mark assumptions and gaps.

4. Default to Markdown; switch formats only when the user asks.

+ ## Domain Execution Essentials

+ 1. Record input classification, sanitization, and allowed use. Replace identities, tokens, and personal data with non-reversible placeholders while retaining schema/business constraints.

+ 2. Trace input snapshot→model/prompt version→AI draft ID→Human review→adopted version ID→acceptance evidence. Drafts do not automatically become execution assets.

+ 3. Name the reviewers of business oracles, assertions, privacy, and high-risk tradeoffs. Unreviewed work remains draft, unexecuted work NOT_RUN; AI does not accept on behalf of Human.

+ 4. Compare equal tasks/complexity/windows: manual baseline versus AI generation+review+rework+acceptance time. Track defects/rework separately; generation time alone cannot prove productivity gains.

## Core Constraints

- Prioritize by risk / business impact — do not treat everything equally.

- Separate confirmed facts from current assumptions.

- Do not invent endpoints, fields, environments, or root causes the user did not provide.

- Keep output executable: concrete scenarios, clear priority, clear next steps.

## Progressive Disclosure

+ - When calibrating domain outcomes, valid controls, or evidence gaps, read [references/domain-decision-example.md](references/domain-decision-example.md) for sanitized input, per-item oracles, and reproducible calculations.

- Before producing output, read and follow `prompts/ai-assisted-testing.md` (minimum coverage, output structure, quality bar).

- When Excel/CSV/JSON/Word is requested: read `output-formats.md` and honor the format.

- When a ready-made template fits: use matching files under `output-templates/`.

- For format conversion or helper checks: prefer existing `scripts/` over reinventing.

- For evaluating/regressing this skill: use `evals/` with skill-up.

## Pre-delivery Checklist

- [ ] Followed the main prompt's output structure

- [ ] Minimum coverage focus: task scope, best AI-assisted opportunities, human verification points, high-risk areas that need manual judgment, draft artifacts to generate, review and approval steps, quality gates, time-saving opportunities, ... (details in main prompt)

- [ ] Covered the minimum checklist, or explained omissions

- [ ] High-risk items have explicit priority

- [ ] Did not invent details the user did not provide

- [ ] Assumptions and gaps are marked

## Common Pitfalls

- Do not pretend completeness when scope/context is missing.

- Do not treat every item as equally important.

- Do not skip assumptions and information gaps.

- Do not dump generic theory unrelated to the current toolchain.