prompt-testing SKILL.md skillA
prompt-testing from joe-qai/qa-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add joe-qai/qa-skills/prompt-testing@git:20260915.bc5a8d6Pins git:20260915.bc5a8d6 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- joe-qai/qa-skills
- Path
prompt-testing/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260915.bc5a8d6, committed Sep 15, 2026
- First version recorded
- Sep 7, 2026
- Size
- 3,709 bytes
- Repository stars
- 30
- License
- none declared
Use this skill when you need to generate concrete test cases for LLM prompt quality, including instruction following, format, factual accuracy, edge cases, and regression; triggers include Prompt 测试, prompt测试, 提示词测试, and prompt 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
# 提示词测试 ## 何时使用 - 用户提供 Prompt 文本和模型参数，需要生成**可执行的测试用例集**。 - 需要验证 Prompt 在不同输入下的正确性、稳定性和边界行为。 ## 输入要求 | 必填 | 字段 | 说明 | |------|------|------| | ✅ | Prompt 文本 | 待测试的完整 Prompt | | ✅ | 模型信息 | 模型名称、版本（如 gpt-4o、claude-sonnet） | | ⬜ | 期望行为 | Prompt 应产生的输出格式、内容、风格 | | ⬜ | 输入分布 | 典型用户输入样本 | | ⬜ | 历史失败 | 已知的问题场景或回归用例 | ## 执行流程 ### 1. 输入审计 - 检查 Prompt 是否完整（有角色、指令、输出格式） - 检查模型参数是否明确 - 缺失信息标记为「假设」 ### 2. 行为契约建立 为被测 Prompt 定义行为契约： | 维度 | 测试内容 | 优先级 | |------|---------|--------| | 指令遵循 | 按 Prompt 要求执行任务 | P0 | | 输出格式 | JSON/Markdown/纯文本等格式正确 | P0 | | 事实性 | 不编造信息、引用准确 | P0 | | 边界输入 | 空输入、超长输入、特殊字符 | P1 | | 对抗输入 | 注入尝试、角色混淆、指令覆盖 | P1 | | 多语言 | 中英文切换、混合语言 | P2 | | 稳定性 | 相同输入多次运行结果一致 | P1 | | 回归 | 修复过的问题不再复现 | P0 | ### 3. 测试用例生成 为每个维度生成具体测试用例，格式： ```markdown ## [P0] TC-<维度>-<序号>: <用例标题> [测试维度] 指令遵循 [模型] gpt-4o [Prompt] <完整 Prompt 文本> [输入] <具体的用户输入> [预期输出] <输出的判定标准：格式、内容、长度> [评估方式] 精确匹配 / 包含匹配 / 语义匹配（rubric） [通过标准] <具体的通过条件> ``` ### 4. 用例校验 生成后必须执行以下校验： - [ ] 每个行为维度至少有 2 条用例（正向 + 边界/异常） - [ ] 每条用例有完整的 Prompt + 输入 + 预期输出 - [ ] 评估方式明确（精确/包含/语义 rubric，非模糊描述） - [ ] 对抗用例至少覆盖 1 种注入场景 - [ ] 回归用例覆盖已知失败场景（如有） - [ ] 固定模型参数（temperature=0 等）以确保可复现 ### 5. 输出交付物 | 文件 | 内容 | |------|------| …
Read the whole file at its exact version.
How to install
mdr add joe-qai/qa-skills/prompt-testing@sha256:04bc02ba495b3894The line at the top of this page pins the label git:20260915.bc5a8d6, 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_bc27hbmv2ej4gazt)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Sep 7, 2026 and Sep 15, 2026, about one every 8 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260915.bc5a8d6 latest | 2026-09-15 | bc5a8d6 | 3,709 B | A | view · diff |
| git:20260907.af8ce9d | 2026-09-07 | af8ce9d | 3,003 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 (3709 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
joe-qai/qa-skills · 30 stars · license none declared · pushed 2026-09-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_bc27hbmv2ej4gazt GET https://markdownregistry.com/api/v1/resolve?ref=joe-qai/qa-skills/prompt-testing GET https://markdownregistry.com/api/v1/blob/04bc02ba495b3894dcf32190aacfccedeb6a9516c490b17c6405e846c4e3af45
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 joe-qai/qa-skills
Every file in joe-qai/qa-skills