菜单
Generate SDK usability test cases by exploring source code. Use when creating benchmark test suites, generating test cases for an SDK, or when the user wants to create evaluation scenarios.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Initialize a new agentic-usability benchmark pipeline project. Use when setting up a new SDK benchmark, creating a config.json, or starting a new evaluation project.
Launch an interactive shell inside a microsandbox for debugging. Supports bare mode, executor setup, or judge setup with optional test case scaffolding.
Run the full evaluation pipeline (execute, judge, report) for an SDK usability benchmark. Use when running a complete benchmark end-to-end, resuming an interrupted pipeline, or checking pipeline status.
Execute benchmark test cases in sandboxed environments with AI agents. Spins up microsandbox containers for each test case and extracts solutions.
Export a benchmark pipeline as a zip file for sharing or archiving. Excludes cache and large snapshots.
Analyze benchmark results and identify SDK improvement areas. Use when reviewing evaluation results, finding failure patterns, identifying documentation gaps, or understanding API design issues.
| name | generate |
| description | Generate SDK usability test cases by exploring source code. Use when creating benchmark test suites, generating test cases for an SDK, or when the user wants to create evaluation scenarios. |
| argument-hint | [project-directory] |
| context | fork |
| allowed-tools | Read Write Glob Grep Bash(*) |
You are acting as the test case generator for an SDK usability benchmark. Your task is to explore the SDK source code and produce test cases.
Write a JSON array of test cases to suite.json in the project directory. Each test case:
{
"id": "TC-001",
"problemStatement": "Goal-oriented task description (no API names/endpoints)",
"referenceSolution": [{ "path": "solution.py", "content": "..." }],
"difficulty": "easy|medium|hard",
"tags": ["auth", "http"],
"setupInstructions": "pip install some-dep"
}
problemStatement: Describe the GOAL, not the implementation. The executor agent must discover the right APIs itself.referenceSolution: Correct implementation files.difficulty: easy = documented example, medium = extrapolation, hard = multi-function composition.The project's config.json defines sources, targets, and agents. For the full schema, see config-schema.md.
The following prompt contains SDK-specific context (source paths, existing tests, schema):
!agentic-usability generate --prompt-only -p $ARGUMENTS