ai-agent-testing SKILL.md skillA
ai-agent-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/ai-agent-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
ai-agent-testing/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260915.bc5a8d6, committed Sep 15, 2026
- First version recorded
- Sep 7, 2026
- Size
- 3,443 bytes
- Repository stars
- 25
- License
- none declared
Use this skill when you need to generate a concrete test suite for AI agent behavior, planning, tool usage, memory, and safety; triggers include AI Agent 测试, agent测试, agent测试用例, and ai agent 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 Agent 测试 ## 何时使用 - 用户提供 Agent 的目标、工具集、指令或任务轨迹，需要生成**可执行的测试套件**。 - 需要验证 Agent 的规划、记忆、工具使用、恢复能力、安全边界。 ## 输入要求 | 必填 | 字段 | 说明 | |------|------|------| | ✅ | Agent 描述 | 目标、指令、可用工具列表 | | ✅ | 测试范围 | 任务完成 / 规划 / 工具使用 / 记忆 / 安全（选一或多选） | | ⬜ | 任务轨迹 | Agent 已有的执行记录或日志 | | ⬜ | 成功标准 | 通过/失败的判定条件 | | ⬜ | 风险限制 | 不可执行的操作、权限边界 | ## 执行流程 ### 1. 输入审计 - 检查 Agent 描述是否包含：目标、工具、输入/输出格式 - 检查测试范围是否明确 - 缺失信息标记为「假设」并给出默认值 ### 2. 能力建模 为被测 Agent 建立能力矩阵： | 维度 | 测试内容 | 优先级 | |------|---------|--------| | 任务完成 | 目标达成、输出质量、格式正确 | P0 | | 规划能力 | 步骤拆解、依赖处理、回退策略 | P0 | | 工具使用 | 工具选择、参数传递、结果解析 | P0 | | 记忆一致性 | 上下文保持、跨轮次一致、无幻觉 | P1 | | 失败恢复 | 错误处理、重试策略、降级方案 | P1 | | 安全边界 | 权限限制、拒绝越权、数据保护 | 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] 规划能力 [前置条件] Agent 已加载工具列表：[...] [输入] <具体的用户指令或任务> [预期行为] 1. <步骤1的预期> 2. <步骤2的预期> [预期输出] <最终输出的判定标准> [通过标准] 所有预期行为发生 + 输出满足判定标准 [失败风险] <可能的失败模式> ``` ### 4. 用例校验 生成后必须执行以下校验： - [ ] 每个测试维度至少有 2 条用例（正向 + 反向/异常） - [ ] 每条用例有明确的前置条件和输入 - [ ] 预期行为可观察、可验证（非主观判断） - [ ] 通过标准具体（有数值、有判定条件） - [ ] 覆盖至少一个安全/权限边界用例 - [ ] 无重复用例（相同输入+预期 = 同一条） ### 5. 输出交付物 | 文件 | 内容 | |------|------| | `test-suite.md` | 完整测试用例集（含维度矩阵、用例、通过标准） | …
Read the whole file at its exact version.
How to install
mdr add joe-qai/qa-skills/ai-agent-testing@sha256:5a29f6c74ff0f1c2The 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_rdpcvg6qedlbdh3t)
5 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 | 3,443 B | A | view · diff |
| git:20260907.af8ce9d | 2026-09-07 | af8ce9d | 3,038 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 (3443 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 · 25 stars · license none declared · pushed 2026-09-29 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_rdpcvg6qedlbdh3t GET https://markdownregistry.com/api/v1/resolve?ref=joe-qai/qa-skills/ai-agent-testing GET https://markdownregistry.com/api/v1/blob/5a29f6c74ff0f1c2b7f125cbefacf0a4f1854bc1a5dcd1d19bae1b3bce60e549
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