Skill

generate-tests

Generates EvalView test cases for SKILL.md files via LLM from skill definitions, manual specs, or proxy capture of agent interactions. Validates and runs tests.

testing

npx claudepluginhub hidai25/eval-view

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Use this skill when the user wants to create test cases for their AI agent or skill without writing YAML by hand.

SKILL.md

Similar Skills

testing-skills-with-subagents

Tests Claude Code skills using TDD RED-GREEN-REFACTOR: baseline failures without skill, write fixes, iterate loopholes with pressure scenarios before deployment.

1 file

nickcrew-claude-ctx-plugin

skill-tester

Tests and benchmarks Claude Code skills empirically via evaluation-driven development. Compares skill vs baseline performance using pass rates, timing, token metrics in quick workflow or 7-phase full pipeline.

3 files8 tools

skills-toolkit

ring:testing-skills-with-subagents

169

Tests Claude skills using TDD cycle: run pressure scenarios without skill to observe failures (RED), implement skill (GREEN), close rationalization loopholes (REFACTOR). For discipline-enforcing skills.

ring-default

Stats

Stars97

Forks21

Last CommitApr 6, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Generate Tests

Use this skill when the user wants to create test cases for their AI agent or skill without writing YAML by hand.

Four approaches

1. Generate tests from a SKILL.md file

Use the generate_skill_tests MCP tool to auto-generate a test suite from a skill definition. This reads the SKILL.md and produces YAML test cases covering explicit triggers, implicit triggers, contextual triggers, and negative cases.

Steps:

Ask the user which SKILL.md to generate tests for (or detect it from context).
Call generate_skill_tests with:
- skill_path: path to the SKILL.md file
- output_path (optional): where to save the generated YAML
- count (optional): number of test cases (default: 10)
After generation, offer to run the tests with run_skill_test.

CLI equivalent:

evalview skill generate-tests .claude/skills/my-skill/SKILL.md --auto
evalview skill generate-tests .claude/skills/my-skill/SKILL.md -c 20 -o tests/my-skill-tests.yaml

2. Create individual test cases manually

Use the create_test MCP tool to create a single test YAML file from a description.

Steps:

Gather from the user: test name, query, expected tools, forbidden tools, expected output keywords, and minimum score.
Call create_test with the parameters.
After creating the test, call run_snapshot to establish the golden baseline.

3. Capture real interactions

Use the CLI evalview capture command to proxy real agent traffic and save interactions as test YAMLs automatically. This records the query, output, and tool calls from live usage.

CLI equivalent:

evalview capture --agent http://localhost:8080/execute --output-dir tests/test-cases
evalview capture --multi-turn  # saves all turns as one multi-turn conversation test

4. Validate a skill before testing

Use validate_skill to check a SKILL.md for correct structure and completeness before generating tests from it.

Running generated tests

After generating tests, execute them with run_skill_test:

test_file: path to the generated YAML
no_rubric: true for fast deterministic-only checks (no LLM cost)
verbose: true for detailed output on all tests

CLI equivalent:

evalview skill test tests/my-skill-tests.yaml
evalview skill test tests/my-skill-tests.yaml --no-rubric  # fast, $0
evalview skill test tests/my-skill-tests.yaml --verbose --model claude-sonnet-4-20250514