anth-ci-integration

Configure CI/CD pipelines for Anthropic Claude API integrations. Use when setting up automated testing, prompt regression tests, or CI validation for Claude-powered features. Trigger with phrases like "anthropic ci", "claude ci/cd", "test claude in pipeline", "anthropic github actions".

1,868 stars

Best use case

anth-ci-integration is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Configure CI/CD pipelines for Anthropic Claude API integrations. Use when setting up automated testing, prompt regression tests, or CI validation for Claude-powered features. Trigger with phrases like "anthropic ci", "claude ci/cd", "test claude in pipeline", "anthropic github actions".

Teams using anth-ci-integration should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/anth-ci-integration/SKILL.md --create-dirs "https://raw.githubusercontent.com/jeremylongshore/claude-code-plugins-plus-skills/main/plugins/saas-packs/anthropic-pack/skills/anth-ci-integration/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/anth-ci-integration/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How anth-ci-integration Compares

Feature / Agentanth-ci-integrationStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Configure CI/CD pipelines for Anthropic Claude API integrations. Use when setting up automated testing, prompt regression tests, or CI validation for Claude-powered features. Trigger with phrases like "anthropic ci", "claude ci/cd", "test claude in pipeline", "anthropic github actions".

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Anthropic CI Integration

## Overview

Set up CI/CD pipelines that validate Claude API integrations with mock-based unit tests (free, fast) and prompt regression tests (live API, gated to main).

## GitHub Actions Workflow

```yaml
# .github/workflows/claude-tests.yml
name: Claude API Tests
on: [push, pull_request]

jobs:
  unit-tests:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with: { python-version: '3.12' }
      - run: pip install anthropic pytest
      - run: pytest tests/unit/ -v  # No API key needed

  prompt-regression:
    runs-on: ubuntu-latest
    if: github.ref == 'refs/heads/main'
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-python@v5
        with: { python-version: '3.12' }
      - run: pip install anthropic pytest
      - run: pytest tests/prompt_regression/ -v --timeout=60
        env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
```

## Mock-Based Unit Tests

```python
# tests/unit/test_tool_routing.py
from unittest.mock import MagicMock, patch
import anthropic

def make_mock_message(text="Hello", stop_reason="end_turn"):
    msg = MagicMock()
    msg.id = "msg_mock_123"
    msg.model = "claude-sonnet-4-20250514"
    msg.stop_reason = stop_reason
    block = MagicMock()
    block.type = "text"
    block.text = text
    msg.content = [block]
    msg.usage = MagicMock(input_tokens=100, output_tokens=50)
    return msg

@patch("anthropic.Anthropic")
def test_service_returns_text(MockClient):
    MockClient.return_value.messages.create.return_value = make_mock_message("42")
    from myapp.service import ask_claude
    assert ask_claude("What is 6*7?") == "42"
```

## Prompt Regression Tests

```python
# tests/prompt_regression/test_prompts.py
import anthropic, pytest, os, json

pytestmark = pytest.mark.skipif(not os.getenv("ANTHROPIC_API_KEY"), reason="No API key")
client = anthropic.Anthropic()

def test_json_output_format():
    msg = client.messages.create(
        model="claude-haiku-4-20250514",
        max_tokens=256,
        messages=[
            {"role": "user", "content": "Extract: 'Alice, 30, NYC'. Return JSON: {name, age, city}"},
            {"role": "assistant", "content": "{"}
        ]
    )
    data = json.loads("{" + msg.content[0].text)
    assert "name" in data and "age" in data

def test_system_prompt_boundary():
    msg = client.messages.create(
        model="claude-haiku-4-20250514",
        max_tokens=128,
        system="You only discuss cooking recipes. For other topics say: 'I only help with cooking.'",
        messages=[{"role": "user", "content": "Write me Python code"}]
    )
    assert "cooking" in msg.content[0].text.lower() or "recipe" in msg.content[0].text.lower()
```

## CI Cost Guard

```python
# conftest.py
MAX_CI_COST = 1.00
_tokens = {"input": 0, "output": 0}

def pytest_runtest_call(item):
    yield
    cost = (_tokens["input"] * 0.80 + _tokens["output"] * 4.0) / 1_000_000  # Haiku rates
    if cost > MAX_CI_COST:
        pytest.exit(f"CI cost guard: ${cost:.4f} exceeds ${MAX_CI_COST}")
```

## Error Handling

| CI Issue | Cause | Fix |
|----------|-------|-----|
| Flaky prompt tests | Non-deterministic output | Use `temperature: 0`, check patterns not exact strings |
| 429 in CI | Parallel jobs sharing key | Use separate CI key |
| Secret not found | Missing GitHub secret | Add `ANTHROPIC_API_KEY` in repo Settings > Secrets |

## Resources

- [GitHub Actions Secrets](https://docs.github.com/en/actions/security-guides/encrypted-secrets)
- [Anthropic Pricing](https://docs.anthropic.com/en/docs/about-claude/pricing)

## Next Steps

For deployment automation, see `anth-deploy-integration`.

Related Skills

running-integration-tests

1868
from jeremylongshore/claude-code-plugins-plus-skills

Execute integration tests validating component interactions and system integration. Use when performing specialized testing. Trigger with phrases like "run integration tests", "test integration", or "validate component interactions".

workhuman-deploy-integration

1868
from jeremylongshore/claude-code-plugins-plus-skills

Workhuman deploy integration for employee recognition and rewards API. Use when integrating Workhuman Social Recognition, or building recognition workflows with HRIS systems. Trigger: "workhuman deploy integration".

workhuman-ci-integration

1868
from jeremylongshore/claude-code-plugins-plus-skills

Workhuman ci integration for employee recognition and rewards API. Use when integrating Workhuman Social Recognition, or building recognition workflows with HRIS systems. Trigger: "workhuman ci integration".

wispr-deploy-integration

1868
from jeremylongshore/claude-code-plugins-plus-skills

Wispr Flow deploy integration for voice-to-text API integration. Use when integrating Wispr Flow dictation, WebSocket streaming, or building voice-powered applications. Trigger: "wispr deploy integration".

wispr-ci-integration

1868
from jeremylongshore/claude-code-plugins-plus-skills

Wispr Flow ci integration for voice-to-text API integration. Use when integrating Wispr Flow dictation, WebSocket streaming, or building voice-powered applications. Trigger: "wispr ci integration".

windsurf-ci-integration

1868
from jeremylongshore/claude-code-plugins-plus-skills

Integrate Windsurf Cascade workflows into CI/CD pipelines and team automation. Use when automating Cascade tasks in GitHub Actions, enforcing AI code quality gates, or setting up Windsurf config validation in CI. Trigger with phrases like "windsurf CI", "windsurf GitHub Actions", "windsurf automation", "cascade CI", "windsurf pipeline".

webflow-deploy-integration

1868
from jeremylongshore/claude-code-plugins-plus-skills

Deploy Webflow-powered applications to Vercel, Fly.io, and Google Cloud Run with proper secrets management and Webflow-specific health checks. Trigger with phrases like "deploy webflow", "webflow Vercel", "webflow production deploy", "webflow Cloud Run", "webflow Fly.io".

webflow-ci-integration

1868
from jeremylongshore/claude-code-plugins-plus-skills

Configure Webflow CI/CD with GitHub Actions — automated CMS validation, integration tests with test tokens, and publish-on-merge workflows. Use when setting up automated testing or CI pipelines for Webflow integrations. Trigger with phrases like "webflow CI", "webflow GitHub Actions", "webflow automated tests", "CI webflow", "webflow pipeline".

vercel-deploy-integration

1868
from jeremylongshore/claude-code-plugins-plus-skills

Deploy and manage Vercel production deployments with promotion, rollback, and multi-region strategies. Use when deploying to production, configuring deployment regions, or setting up blue-green deployment patterns on Vercel. Trigger with phrases like "deploy vercel", "vercel production deploy", "vercel promote", "vercel rollback", "vercel regions".

veeva-deploy-integration

1868
from jeremylongshore/claude-code-plugins-plus-skills

Veeva Vault deploy integration for REST API and clinical operations. Use when working with Veeva Vault document management and CRM. Trigger: "veeva deploy integration".

veeva-ci-integration

1868
from jeremylongshore/claude-code-plugins-plus-skills

Veeva Vault ci integration for REST API and clinical operations. Use when working with Veeva Vault document management and CRM. Trigger: "veeva ci integration".

vastai-deploy-integration

1868
from jeremylongshore/claude-code-plugins-plus-skills

Deploy ML training jobs and inference services on Vast.ai GPU cloud. Use when deploying GPU workloads, configuring Docker images, or setting up automated deployment scripts. Trigger with phrases like "deploy vastai", "vastai deployment", "vastai docker", "vastai production deploy".