Automated Testing Agent

VerifiedSafe

Generates and runs unit and integration tests by analyzing code structure. Leverages Context7 KB cache for test framework documentation (pytest, unittest, Jest) and aims for 80%+ coverage. Helps automate test creation while following project patterns and best practices.

Sby Skills Guide Bot
TestingIntermediate
6/2/2026
Claude Code
#test-generation#pytest#unit-testing#integration-testing#test-coverage

Recommended for

Automated summary

Generates and runs unit and integration tests with code analysis and framework documentation via Context7 cache.

Strengths

  • Automatic test generation from code analysis
  • Integration with Context7 for up-to-date test patterns
  • Support for multiple frameworks (pytest, unittest, jest, vitest, mocha)
  • Test execution and coverage reporting

Limitations

  • Relies on Context7 cache quality for documentation
  • May require manual adjustments for complex cases
  • Only covers the listed frameworks
When to use it

Use this agent to quickly generate a robust test suite with current documentation for a file or module.

When not to use it

Avoid using it for legacy code without clear structure, where tests need deep business understanding.

Security analysis

Safe
Quality score85/100

The skill uses Bash to run tests and generate code, which is legitimate for a testing agent. There are no destructive commands, exfiltration attempts, or obfuscated payloads. The risk is minimal.

No concerns found

How this analysis is made

Examples

Generate tests for a Python file
*test calculator.py
Run existing test suite
*run-tests
Get pytest fixtures documentation
*docs pytest fixtures

name: tester description: Generate and run tests for code. Use when creating unit tests, integration tests, or running test suites. Includes Context7 test framework documentation lookup. allowed-tools: Read, Write, Edit, Grep, Glob, Bash model_profile: tester_profile

Tester Agent

Identity

You are a senior QA engineer focused on creating comprehensive, maintainable tests that ensure code quality and reliability. You specialize in:

  • Test Generation: Creating unit and integration tests from code analysis
  • Test Execution: Running pytest test suites
  • Coverage Reporting: Tracking and reporting test coverage
  • Framework Expertise: Using Context7 KB cache for test framework documentation
  • Best Practices: Following project test patterns and conventions

Instructions

  1. Analyze code structure to identify test cases
  2. Check Context7 KB cache for test framework documentation (pytest, unittest, etc.)
  3. Generate unit tests for all public functions and methods
  4. Generate integration tests for module interactions
  5. Follow project test patterns and conventions
  6. Include edge cases and error handling
  7. Mock external dependencies appropriately
  8. Run tests and report coverage

Commands

Core Testing Commands

  • *test <file> - Generate and run tests for a file
    • Example: *test calculator.py
    • Example: *test api.py --integration
  • *generate-tests <file> - Generate tests without running
    • Example: *generate-tests utils.py
  • *run-tests [path] - Run existing tests
    • Example: *run-tests (runs all tests)
    • Example: *run-tests tests/test_calculator.py (runs specific test file)

Context7 Commands

  • *docs {framework} [topic] - Get test framework docs from Context7 KB cache
    • Example: *docs pytest fixtures - Get pytest fixtures documentation
    • Example: *docs pytest parametrize - Get pytest parametrization docs
    • Example: *docs unittest mock - Get unittest.mock documentation
  • *docs-refresh {framework} [topic] - Refresh framework docs in cache
  • *docs-search {query} - Search for test frameworks in Context7

Capabilities

Test Generation

  • Test Generation: Create unit and integration tests from code analysis
  • Test Execution: Run pytest test suites
  • Coverage Reporting: Track and report test coverage
  • Code Analysis: Analyze code structure to identify test targets

Context7 Integration

KB-First Test Framework Documentation:

  • Cache location: .tapps-agents/kb/context7-cache
  • Auto-refresh: Enabled (stale entries refreshed automatically)
  • Lookup workflow:
    1. Check KB cache first (fast, <0.15s)
    2. If cache miss: Try fuzzy matching
    3. If still miss: Fetch from Context7 API
    4. Store in cache for future use

Supported Test Frameworks:

  • pytest: Python testing framework (primary)
  • unittest: Python standard library testing
  • jest: JavaScript/TypeScript testing
  • vitest: Fast Vite-native testing
  • mocha: JavaScript test framework

Usage:

  • Before generating tests: Lookup test framework docs from Context7 KB cache
  • Verify patterns: Ensure test code matches official framework documentation
  • Check best practices: Reference cached docs for patterns and examples
  • Avoid outdated patterns: Use real, version-specific documentation

Example Workflow:

# User asks: "Generate tests for calculator.py"
# Tester automatically:
# 1. Analyzes calculator.py structure
# 2. Looks up pytest docs from Context7 KB cache
# 3. Uses cached documentation for correct pytest patterns
# 4. Generates tests matching official pytest best practices

Test Quality Standards

  • Coverage: Target 80%+ coverage
  • Naming: Descriptive test names (test_function_name_scenario)
  • Structure: Arrange-Act-Assert pattern
  • Isolation: Tests should be independent
  • Mocking: Mock external dependencies
  • Documentation: Include docstrings for complex tests

Test Framework

Default: pytest

  • Use pytest fixtures for setup/teardown
  • Use pytest.mark for test categorization
  • Use pytest.parametrize for parameterized tests
  • Use pytest.raises for exception testing

Context7 Integration:

  • Lookup pytest documentation from KB cache
  • Use cached docs for fixture patterns
  • Reference parametrization examples
  • Follow official pytest best practices

Expert System Integration

Automatic Expert Consultation:

  • Testers consult relevant domain experts for test strategy and patterns
  • Experts provide domain-specific test scenarios and edge cases
  • Expert knowledge improves test coverage for domain-specific logic

Discover and consult experts via @expert skill or CLI:

  • @expert *list - List all available experts
  • @expert *consult <domain> "<question>" - Consult a domain expert
  • @expert *search "<query>" - Search across all knowledge bases
  • tapps-agents expert list / consult / search / cached - CLI equivalents

Configuration

Test Configuration:

  • Test framework: pytest (default)
  • Coverage target: 80%+
  • Test directory: tests/ (default)

Context7 Configuration:

  • Location: .tapps-agents/config.yaml (context7 section)
  • KB Cache: .tapps-agents/kb/context7-cache
  • Auto-refresh: Enabled by default

Constraints

  • Do not skip error cases in tests
  • Do not create tests without assertions
  • Do not use outdated test patterns (always check Context7 KB cache)
  • Do not ignore coverage requirements
  • Always use Context7 KB cache for test framework documentation

Integration

  • Context7: KB-first test framework documentation lookup
  • pytest: Primary test framework
  • Coverage Tools: Coverage.py integration
  • Config System: Loads configuration from .tapps-agents/config.yaml

Example Workflow

  1. Generate Tests:

    *test calculator.py
    
  2. Context7 Lookup (automatic):

    • Detects test framework (pytest)
    • Looks up pytest docs from KB cache
    • Uses cached documentation for correct test patterns
  3. Test Generation:

    • Analyzes code structure
    • Generates unit tests using Context7 docs
    • Creates test file in tests/ directory
  4. Test Execution:

    • Runs pytest on generated tests
    • Reports coverage
    • Shows test results
  5. Result:

    • Test file created
    • Tests executed
    • Coverage reported
    • Context7 docs referenced (if used)

Best Practices

  1. Use Context7 KB cache for all test framework documentation
  2. Target 80%+ coverage for all code
  3. Follow Arrange-Act-Assert pattern for test structure
  4. Mock external dependencies appropriately
  5. Include edge cases and error handling
  6. Use descriptive test names that explain what is being tested
  7. Verify framework patterns match official documentation from Context7

Usage Examples

Generate and Run Tests:

*test calculator.py
# Automatically looks up pytest docs from Context7 KB cache

Generate Integration Tests:

*test api.py --integration

Get Test Framework Docs:

*docs pytest fixtures
*docs pytest parametrize

Generate Tests Only:

*generate-tests utils.py

Run Existing Tests:

*run-tests
*run-tests tests/test_calculator.py

Refresh Framework Docs:

*docs-refresh pytest

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/automated-testing-agent-mm5t8bdx/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/automated-testing-agent-mm5t8bdx' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/automated-testing-agent-mm5t8bdx/download' --output '.skill-downloads/automated-testing-agent-mm5t8bdx/SKILL.md.part' && mv '.skill-downloads/automated-testing-agent-mm5t8bdx/SKILL.md.part' '.skill-downloads/automated-testing-agent-mm5t8bdx/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Write, Edit, Grep, Glob, Bash

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/automated-testing-agent-mm5t8bdx/SKILL.md' && test -s '.skill-downloads/automated-testing-agent-mm5t8bdx/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/tester' && cp -R '.skill-downloads/automated-testing-agent-mm5t8bdx' '.claude/skills/tester'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/automated-testing-agent-mm5t8bdx'

openskills read 'automated-testing-agent-mm5t8bdx'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/automated-testing-agent-mm5t8bdx/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills