Testing LLM

What it does

When your agent uses it

• Testing AI features
• Validating LLM outputs
• Building evaluation pipelines

Example prompts

• “/testing-llm”

Requirements

• Python 3
• Node.js
• Compatibility (from SKILL.md): Claude Code 2.1.277+.
• Pre-approved tools (allowed-tools): Read, Glob, Grep, WebFetch, WebSearch

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Planner: Explores your app and produces Markdown test plans. Owned by the
2. 2Generator: Converts Markdown specs into Playwright tests, validating selectors
3. 3Healer (references/healer-agent.md): Automatically fixes failing tests by replaying failures, inspecting the DOM, and patching…

What it can do on your machine

Read from SKILL.md and the folder at commit 0ef71d2. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Glob
  • Grep
  • WebFetch
  • WebSearch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npx

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • deepeval.com
  • playwright.dev
  • docs.ragas.io
  • vcrpy.readthedocs.io
  • docs.scipy.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Claude Code 2.1.277+.

  From compatibility in the SKILL.md frontmatter.

Context cost

Testing LLM loads about 2.6k tokens when it runs, and up to ~5.6k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 809 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~66

When it runs · the whole SKILL.md, loaded when a task matches

~2.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~5.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from yonatangross/orchestkit at commit 0ef71d2, republished under its MIT licence (© yonatangross). 809 words, ~2,572 tokens.

name

testing-llm

description

LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.

allowed-tools

Read, Glob, Grep, WebFetch, WebSearch

compatibility

Claude Code 2.1.277+.

license

MIT

user-invocable

false

disable-model-invocation

false

metadata.owner-agent

test-generator

metadata.category

document-asset-creation

metadata.version

2.1.0

metadata.author

OrchestKit

metadata.complexity

medium

metadata.tags

testing, llm, ai, deepeval, ragas, evaluation, mocking

from unittest.mock import AsyncMock, patch
import pytest

@pytest.fixture
def mock_llm():
    mock = AsyncMock()
    mock.return_value = {"content": "Mocked response", "confidence": 0.85}
    return mock

@pytest.mark.asyncio
async def test_with_mocked_llm(mock_llm):
    with patch("app.core.model_factory.get_model", return_value=mock_llm):
        result = await synthesize_findings(sample_findings)
    assert result["summary"] is not None

from deepeval import assert_test
from deepeval.test_case import LLMTestCase
from deepeval.metrics import AnswerRelevancyMetric, FaithfulnessMetric

test_case = LLMTestCase(
    input="What is the capital of France?",
    actual_output="The capital of France is Paris.",
    retrieval_context=["Paris is the capital of France."],
)

assert_test(test_case, [
    AnswerRelevancyMetric(threshold=0.7),
    FaithfulnessMetric(threshold=0.8),
])

metric = AnswerRelevancyMetric(threshold=0.7, include_reason=True)
metric.measure(test_case)
print(metric.score, metric.reason)
# 0.62  "Response addresses the topic but omits the date asked for."

from ragas import evaluate
from ragas.metrics import Faithfulness, LLMContextRecall

result = evaluate(
    dataset,
    metrics=[Faithfulness(), LLMContextRecall()],
)

from pydantic import BaseModel, Field

class LLMResponse(BaseModel):
    answer: str = Field(min_length=1)
    confidence: float = Field(ge=0.0, le=1.0)
    sources: list[str] = Field(default_factory=list)

async def test_structured_output():
    result = await get_llm_response("test query")
    parsed = LLMResponse.model_validate(result)
    assert 0 <= parsed.confidence <= 1.0

@pytest.fixture(scope="module")
def vcr_config():
    import os
    return {
        "record_mode": "none" if os.environ.get("CI") else "new_episodes",
        "filter_headers": ["authorization", "x-api-key"],
    }

@pytest.mark.vcr()
async def test_llm_integration():
    response = await llm_client.complete("Say hello")
    assert "hello" in response.content.lower()

Planner -> specs/*.md -> Generator -> tests/*.spec.ts -> Healer (auto-fix)

© yonatangross, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (references) in src/skills/testing-llm of yonatangross/orchestkit.

• SKILL.md
• checklists/llm-test-checklist.md
• references/healer-agent.md
• references/langfuse-v4.md
• references/ork-delta.md
• rules/_sections.md
• rules/llm-evaluation.md
• rules/llm-mocking.md
• test-cases.json

Open the folder on GitHubat commit 0ef71d2