Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From agentic-usability
Generates SDK usability benchmark test cases by exploring source code. Use when creating evaluation scenarios or test suites for SDKs.
npx claudepluginhub pspdfkit-labs/agentic-usability --plugin agentic-usabilityHow this skill is triggered — by the user, by Claude, or both
Slash command
/agentic-usability:generate [project-directory][project-directory]This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
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.
Generates runnable Vitest unit tests and Playwright E2E specs from BDD/Gherkin test cases, scaffolds, and OpenAPI contracts. Use after generating test cases or app scaffolds.
Generates EvalView test cases for SKILL.md skills via LLM from file content, manual specs, or live agent interaction proxy capture; validates skills and runs tests.
Generates tests for TypeScript, React, Vue, Python, Go, Rust, PHP via framework detection (Jest/Vitest/Pytest/Go test/Cargo test) and expert agent routing. Auto-creates verification tasks.
Share bugs, ideas, or general feedback.
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