ai-feature-testing SKILL.md skillA
ai-feature-testing from naodeng/awesome-qa-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add naodeng/awesome-qa-skills/ai-feature-testing@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- naodeng/awesome-qa-skills
- Path
skills/zh/testing-types/ai-feature-testing/SKILL.md- Versions recorded
- 4
- Latest version
- v1.0.0, committed Oct 29, 2026
- First version recorded
- Aug 29, 2026
- Size
- 4,256 bytes
- Repository stars
- 301
- License
- a license file GitHub does not identify
Use this skill when you need to test an AI-enabled product feature for behavior, safety, and user-impact boundaries; triggers include AI 功能测试 and AI feature testing.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# AI 功能测试（中文版） ## 何时使用 - 需要验证嵌入产品的 AI 功能在质量、安全、公平性、降级和用户体验上的表现。 - 需要对现有方案、结果或证据做风险评审，并形成可执行改进项。 - 输入不完整，但仍需先给出带假设和信息缺口的可用初版。 ## 输出格式选项 - 默认输出 Markdown，适合评审、执行和持续补充。 - 用户要求表格、CSV、JSON 或工单格式时，保留同样的风险、证据、优先级和边界字段。 - 若输出会进入自动化流程，先确认字段 schema、枚举值和必填项。 ## 如何使用 1. 先阅读并遵循 `prompts/ai-feature-testing.md` 的输入、执行规则、最低覆盖清单和输出顺序。 2. 补充真正影响判断的范围、环境、版本、限制、证据和成功标准。 3. 先做输入审计，再区分已确认事实、合理假设和待确认问题。 4. 按风险和证据强度排序，产出可直接执行、评审或验证的结果。 5. 信息不足时不要停在提问：先交付受限初版，并说明哪些结论暂不能成立。 ## 参考文件 - 校准领域结果、正确对照或证据缺口时，读取 [references/domain-decision-example.md](references/domain-decision-example.md) 的脱敏输入、逐项预期与复算依据。 - 每次执行必须读取 `prompts/ai-feature-testing.md`；它是本 Skill 的完整执行规范。 - 需要评测或回归本 Skill 时，读取 `evals/eval.yaml` 与匹配的 `evals/cases/` 用例。 - 只有目录实际存在且任务需要时，才读取 `references/`、`examples/`、`scripts/` 或 `output-formats.md`，不要假设不存在的资产。 ## 领域执行要点 1. 固定模型、Prompt、知识/评测数据、产品和环境版本；建立 产品任务×语言×用户群×风险 切片，记录抽样来源及样本量，不以总体平均遮盖小群体。 2. 人工 rubric 为每个维度写可观察锚点、标签者、分歧处理和参考答案来源；先校准样本，再按项目评分与权重汇总，未定规则不自造分数。 3. 分开任务质量、安全/隐私、应拒答与正常可回答、降级/回退门槛；记录每门槛来源、分母和版本，拒答多不自动安全。 4. 切片缺样本或阈值时输出 UNKNOWN/待确认；上线建议保留未决门槛和 Human 决策，不能从静态方案得出已通过。 ## 核心约束 - 不要只测理想输入 - 区分模型限制与产品集成缺陷 - 高风险输出必须设计拒答或人工兜底 - 不编造输入中不存在的系统行为、字段、数据、指标或根因。 …
Read the whole file at its exact version.
How to install
mdr add naodeng/awesome-qa-skills/ai-feature-testing@sha256:c6a3966c3809fcfcThe line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_cr5fksykfxvyky2w)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 29, 2026 and Oct 29, 2026, about one every 20 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-10-29 | 1d0d58f | 4,256 B | A | view · diff |
| git:20261011.7d9502b | 2026-10-11 | 7d9502b | 3,947 B | A | view · diff |
| git:20260829.175e380 | 2026-08-29 | 175e380 | 3,039 B | A | view · diff |
| git:20260829.30ae153 | 2026-08-29 | 30ae153 | 350 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4256 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
naodeng/awesome-qa-skills · 301 stars · license a license file GitHub does not identify · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_cr5fksykfxvyky2w GET https://markdownregistry.com/api/v1/resolve?ref=naodeng/awesome-qa-skills/ai-feature-testing GET https://markdownregistry.com/api/v1/blob/c6a3966c3809fcfc890492e645dad965f9c338a23113dc055adecab138795608
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from naodeng/awesome-qa-skills
Every file in naodeng/awesome-qa-skills