Agent skill

Assertion Synthesizer

by ArabelaTso in ArabelaTso/Skills-4-SE

Generate test assertions from existing code implementation. An agent skill from ArabelaTso/Skills-4-SE.

Apache-2.0Auto-check passedTesting & QA

Install Assertion Synthesizer

skills CLI
$ npx skills add ArabelaTso/Skills-4-SE --skill assertion-synthesizer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ArabelaTso/Skills-4-SE assertion-synthesizer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ArabelaTso/Skills-4-SE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/assertion-synthesizer .claude/skills/assertion-synthesizer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
assertion-synthesizer
GitHub stars
253
Token cost
~2.9k tokens
SKILL.md length
459 words
Files
1
Skills in repo
170
Repo updated
First seen
Licence
Apache-2.0

At a glance

Generate test assertions from existing code implementation. An agent skill from ArabelaTso/Skills-4-SE.

  • Works in 5 steps: Analyze Code → Identify Test Scenarios → Generate Assertions → …
  • The user has implementation code without tests
  • SKILL.md covers Workflow, Language-Specific Patterns, Assertion Synthesis Strategies and Best Practices, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Assertion Synthesizer is an agent skill from ArabelaTso/Skills-4-SE. Generate test assertions from existing code implementation. Use when the user has implementation code without tests or incomplete test coverage, and needs assertions synthesized by analyzing the code's behavior, inputs, outputs, and state changes. Supports Python (pytest/unittest), Java (JUnit/AssertJ), and JavaScript/TypeScript (Jest/Chai). Handles equality checks, collections, exceptions, and state verification.

Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Unit testing. It works with pytest, Python, Jest and JUnit. The repository describes itself as: A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows. The licence is Apache-2.0.

When your agent uses it

  • The user has implementation code without tests
  • Incomplete test coverage
  • Needs assertions synthesized by analyzing the codes behavior

Example prompts

  • “/assertion-synthesizer”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Analyze Code
  2. Identify Test Scenarios
  3. Generate Assertions
  4. Structure Tests
  5. Verify Coverage

What it can do on your machine

Read from SKILL.md and the folder at commit 4f38503. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python, java and javascript).

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

  • Network

    No URLs in SKILL.md.

    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.

Context cost

Assertion Synthesizer loads about 2.9k tokens when it runs. Until then it costs about 110 tokens; SKILL.md has 459 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~110
When it runs · the whole SKILL.md, loaded when a task matches
~2.9k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 ArabelaTso/Skills-4-SE at commit 4f38503, republished under its Apache-2.0 licence (© ArabelaTso). 459 words, ~2,875 tokens.

Download SKILL.mdSave it as .claude/skills/assertion-synthesizer/SKILL.md (or your agent's skills folder).
name
assertion-synthesizer
description
Generate test assertions from existing code implementation. Use when the user has implementation code without tests or incomplete test coverage, and needs assertions synthesized by analyzing the code's behavior, inputs, outputs, and state changes. Supports Python (pytest/unittest), Java (JUnit/AssertJ), and JavaScript/TypeScript (Jest/Chai). Handles equality checks, collections, exceptions, and state verification.

Assertion Synthesizer

Generate comprehensive test assertions by analyzing code implementation, behavior, and expected outputs.

Workflow

1. Analyze Code

Read and understand the implementation to identify testable behavior:

  • Function signatures: Parameters, return types, side effects
  • Logic paths: Conditionals, loops, branching behavior
  • Edge cases: Boundary conditions, null/empty inputs, error conditions
  • State changes: Object mutations, attribute modifications
  • Dependencies: External calls, database operations, I/O
2. Identify Test Scenarios

Extract scenarios that need assertions:

  • Happy path: Normal inputs producing expected outputs
  • Edge cases: Empty lists, zero values, boundary conditions
  • Error cases: Invalid inputs, exceptions, error handling
  • State verification: Object state before/after operations
  • Collection assertions: List contents, ordering, membership
3. Generate Assertions

Create appropriate assertions for each scenario:

Assertion Types:

  • Equality: assert result == expected, assertEquals(expected, actual)
  • Truthiness: assert is_valid, assertTrue(condition)
  • Collections: assert item in list, assertContains(list, item)
  • Exceptions: pytest.raises(Exception), assertThrows(Exception)
  • State: assert obj.status == "active", assertEquals("active", obj.getStatus())
4. Structure Tests

Organize assertions into well-structured test functions:

  • Use descriptive test names
  • Follow Arrange-Act-Assert pattern
  • Group related assertions
  • Add explanatory comments
5. Verify Coverage

Ensure all important behaviors have assertions:

  • Check all return values are tested
  • Verify edge cases are covered
  • Confirm error conditions are tested
  • Validate state changes are asserted

Language-Specific Patterns

Python (pytest)
python
def test_basic_equality():
    # Arrange
    calculator = Calculator()

    # Act
    result = calculator.add(2, 3)

    # Assert
    assert result == 5

def test_collection_membership():
    items = get_active_items()
    assert "item1" in items
    assert len(items) == 3

def test_exception_handling():
    with pytest.raises(ValueError, match="Invalid input"):
        process_data(None)

def test_state_change():
    user = User("Alice")
    user.activate()
    assert user.is_active == True
    assert user.status == "active"
Python (unittest)
python
def test_basic_equality(self):
    calculator = Calculator()
    result = calculator.add(2, 3)
    self.assertEqual(result, 5)

def test_collection_membership(self):
    items = get_active_items()
    self.assertIn("item1", items)
    self.assertEqual(len(items), 3)

def test_exception_handling(self):
    with self.assertRaises(ValueError):
        process_data(None)

def test_state_change(self):
    user = User("Alice")
    user.activate()
    self.assertTrue(user.is_active)
    self.assertEqual(user.status, "active")
Java (JUnit + AssertJ)
java
@Test
void testBasicEquality() {
    Calculator calculator = new Calculator();
    int result = calculator.add(2, 3);
    assertThat(result).isEqualTo(5);
}

@Test
void testCollectionMembership() {
    List<String> items = getActiveItems();
    assertThat(items).contains("item1");
    assertThat(items).hasSize(3);
}

@Test
void testExceptionHandling() {
    assertThatThrownBy(() -> processData(null))
        .isInstanceOf(IllegalArgumentException.class)
        .hasMessage("Invalid input");
}

@Test
void testStateChange() {
    User user = new User("Alice");
    user.activate();
    assertThat(user.isActive()).isTrue();
    assertThat(user.getStatus()).isEqualTo("active");
}
JavaScript/TypeScript (Jest)
javascript
test('basic equality', () => {
    const calculator = new Calculator();
    const result = calculator.add(2, 3);
    expect(result).toBe(5);
});

test('collection membership', () => {
    const items = getActiveItems();
    expect(items).toContain('item1');
    expect(items).toHaveLength(3);
});

test('exception handling', () => {
    expect(() => processData(null))
        .toThrow('Invalid input');
});

test('state change', () => {
    const user = new User('Alice');
    user.activate();
    expect(user.isActive).toBe(true);
    expect(user.status).toBe('active');
});

Assertion Synthesis Strategies

From Return Values

Analyze what the function returns and assert on it:

python
# Code:
def get_full_name(first, last):
    return f"{first} {last}"

# Synthesized assertion:
def test_get_full_name():
    result = get_full_name("John", "Doe")
    assert result == "John Doe"
    assert isinstance(result, str)
From Side Effects

Identify state changes and mutations:

python
# Code:
def withdraw(account, amount):
    if account.balance >= amount:
        account.balance -= amount
        return True
    return False

# Synthesized assertions:
def test_withdraw_success():
    account = Account(balance=100)
    result = withdraw(account, 50)
    assert result == True
    assert account.balance == 50

def test_withdraw_insufficient_funds():
    account = Account(balance=30)
    result = withdraw(account, 50)
    assert result == False
    assert account.balance == 30  # Balance unchanged
From Conditional Logic

Test each branch:

python
# Code:
def classify_age(age):
    if age < 0:
        raise ValueError("Invalid age")
    elif age < 18:
        return "minor"
    elif age < 65:
        return "adult"
    else:
        return "senior"

# Synthesized assertions:
def test_classify_age_invalid():
    with pytest.raises(ValueError):
        classify_age(-1)

def test_classify_age_minor():
    assert classify_age(10) == "minor"
    assert classify_age(17) == "minor"

def test_classify_age_adult():
    assert classify_age(18) == "adult"
    assert classify_age(64) == "adult"

def test_classify_age_senior():
    assert classify_age(65) == "senior"
    assert classify_age(100) == "senior"
From Collections

Assert on collection properties:

python
# Code:
def filter_active_users(users):
    return [u for u in users if u.is_active]

# Synthesized assertions:
def test_filter_active_users():
    users = [
        User("Alice", is_active=True),
        User("Bob", is_active=False),
        User("Charlie", is_active=True)
    ]
    result = filter_active_users(users)

    assert len(result) == 2
    assert all(u.is_active for u in result)
    assert result[0].name == "Alice"
    assert result[1].name == "Charlie"
From Object State

Verify object properties:

python
# Code:
class ShoppingCart:
    def __init__(self):
        self.items = []
        self.total = 0

    def add_item(self, item, price):
        self.items.append(item)
        self.total += price

# Synthesized assertions:
def test_shopping_cart_add_item():
    cart = ShoppingCart()

    # Initial state
    assert cart.items == []
    assert cart.total == 0

    # After first item
    cart.add_item("book", 20)
    assert len(cart.items) == 1
    assert "book" in cart.items
    assert cart.total == 20

    # After second item
    cart.add_item("pen", 5)
    assert len(cart.items) == 2
    assert cart.total == 25

Best Practices

Assertion Quality
  • Be specific: Prefer assert result == 5 over assert result > 0
  • Test one thing: Each test should verify one specific behavior
  • Use meaningful values: Avoid magic numbers, use named constants
  • Check types: Verify return types when relevant
Show full SKILL.md (175 more words)Show less
Coverage Completeness
  • All branches: Test every if/else path
  • Boundary values: Test min, max, zero, empty, null
  • Error cases: Assert on exceptions and error messages
  • State transitions: Verify before/after states
Test Organization
  • Descriptive names: test_withdraw_insufficient_funds not test_case_2
  • Arrange-Act-Assert: Clear separation of setup, execution, verification
  • Group related tests: Use test classes or describe blocks
  • Comment complex assertions: Explain what's being verified
Common Patterns

Multiple assertions for comprehensive verification:

python
def test_user_registration():
    user = register_user("alice@example.com", "password123")

    # Verify all important properties
    assert user.email == "alice@example.com"
    assert user.is_active == False  # Not activated yet
    assert user.created_at is not None
    assert user.id is not None
    assert len(user.roles) == 1
    assert "user" in user.roles

Parametrized tests for multiple inputs:

python
@pytest.mark.parametrize("input,expected", [
    (0, "zero"),
    (1, "one"),
    (5, "many"),
    (100, "many"),
])
def test_number_to_word(input, expected):
    assert number_to_word(input) == expected

Example Sessions

Example 1: Untested Function

User provides code:

python
def calculate_discount(price, discount_percent):
    if discount_percent < 0 or discount_percent > 100:
        raise ValueError("Discount must be between 0 and 100")
    return price * (1 - discount_percent / 100)

Synthesized assertions:

python
def test_calculate_discount_normal():
    assert calculate_discount(100, 10) == 90.0
    assert calculate_discount(50, 20) == 40.0

def test_calculate_discount_zero():
    assert calculate_discount(100, 0) == 100.0

def test_calculate_discount_full():
    assert calculate_discount(100, 100) == 0.0

def test_calculate_discount_invalid_negative():
    with pytest.raises(ValueError, match="between 0 and 100"):
        calculate_discount(100, -10)

def test_calculate_discount_invalid_over_100():
    with pytest.raises(ValueError, match="between 0 and 100"):
        calculate_discount(100, 150)
Example 2: Enhancing Existing Tests

User provides weak test:

python
def test_sort_list():
    result = sort_list([3, 1, 2])
    assert result  # Only checks if result exists

Enhanced assertions:

python
def test_sort_list():
    result = sort_list([3, 1, 2])

    # Verify actual sorting behavior
    assert result == [1, 2, 3]
    assert len(result) == 3
    assert isinstance(result, list)

def test_sort_list_empty():
    assert sort_list([]) == []

def test_sort_list_already_sorted():
    assert sort_list([1, 2, 3]) == [1, 2, 3]

def test_sort_list_duplicates():
    assert sort_list([3, 1, 2, 1]) == [1, 1, 2, 3]

Tips

Analyzing Complex Code
  • Break down complex functions into testable units
  • Identify all execution paths through code
  • Look for implicit assumptions to test
  • Consider edge cases the code may not handle
Capturing Behavior
  • Run code mentally or actually execute it
  • Note all observable outputs and state changes
  • Document expected behavior in assertions
  • Test both success and failure scenarios
Balancing Coverage
  • Prioritize critical paths over trivial code
  • Don't over-assert on implementation details
  • Focus on public API behavior
  • Test the contract, not the implementation

© ArabelaTso, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/assertion-synthesizer of ArabelaTso/Skills-4-SE.

Open the folder on GitHubat commit 4f38503

Compare with similar skills

Assertion Synthesizer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Assertion Synthesizer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Assertion Synthesizer this skillArabelaTso/Skills-4-SE253—~2.9kAutomated safety check: PassApache-2.0
TDD GuideLeoYeAI/openclaw-master-skills2.2k—~1.4kAutomated safety check: PassMIT
Python Testing Patternsjh941213/my-cc-harness12617 repos~5.4kAutomated safety check: PassNone
Test Analysis Extensionsmicrosoft/testfx1k2 repos~1.1kAutomated safety check: PassMIT
TDD Guidealirezarezvani/claude-skills28k—~3.4kAutomated safety check: PassMIT
Assertion Qualitymicrosoft/testfx1k—~4.1kAutomated safety check: PassMIT

Similar skills

  • TDD Guide

    LeoYeAI/openclaw-master-skills

    Test-driven development skill for writing unit tests, generating test fixtures and mocks, analyzing coverage gaps, and guiding red-green-refactor workflows across Jest, Pytest, JUnit, Vitest, and…

    2.2k GitHub stars~1.4k tokensUpdated 2 mo ago
    Testing & QAAuto-check passed
  • Python Testing Patterns

    jh941213/my-cc-harness

    Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development.

    126 GitHub starsUsed in 17 repos~5.4k tokens
    Testing & QAAuto-check passed
  • Test Analysis Extensions

    microsoft/testfx

    Official

    Provides file paths to language-specific reference files for the test ANALYSIS skills (assertion-quality, test-anti-patterns, test-gap-analysis, test-smell-detection, test-tagging).

    1k GitHub starsUsed in 2 repos~1.1k tokens
    Testing & QAAuto-check passed
  • TDD Guide

    alirezarezvani/claude-skills

    Test-driven development skill for writing unit tests, generating test fixtures and mocks, analyzing coverage gaps, and guiding red-green-refactor workflows across Jest, Pytest, JUnit, Vitest, and…

    28k GitHub stars~3.4k tokensUpdated 1 mo ago
    Testing & QAAuto-check passed
  • Assertion Quality

    microsoft/testfx

    Official

    Analyzes the variety and depth of assertions across test suites in any language.

    1k GitHub stars~4.1k tokensUpdated today
    Testing & QAAuto-check passed
  • Test Gap Analysis

    microsoft/testfx

    Official

    Performs pseudo-mutation analysis on production code in any language to find gaps in existing test suites.

    1k GitHub stars~4k tokensUpdated today
    Testing & QAAuto-check passed

More from ArabelaTso/Skills-4-SE

All 170 skills in this repo
  • Framework Migration Assistant

    ArabelaTso/Skills-4-SE

    Automatically migrate Python web applications between frameworks (Flask → FastAPI, Django → FastAPI).

    253 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Metamorphic Test Generator

    ArabelaTso/Skills-4-SE

    Generate test cases using metamorphic testing by applying transformations based on metamorphic properties.

    253 GitHub stars~798 tokensUpdated 1 mo ago
    Auto-check passed
  • Reproduction Trace Instrumenter

    ArabelaTso/Skills-4-SE

    Instruments programs to capture execution traces specifically for reproducing reported bugs, enabling consistent replay and diagnosis of failures.

    253 GitHub stars~2.4k tokensUpdated 1 mo ago
    Auto-check passed
  • Spring Mvc To Boot Migrator

    ArabelaTso/Skills-4-SE

    Automatically migrate Spring MVC applications to Spring Boot.

    253 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed
  • State Snapshot Instrumenter

    ArabelaTso/Skills-4-SE

    Instrument programs (Python, C/C++, Java) to capture snapshots of key program states at runtime, including variables, memory, and call stacks.

    253 GitHub stars~2.2k tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Assertion Synthesizer

What does Assertion Synthesizer do?

Generate test assertions from existing code implementation. An agent skill from ArabelaTso/Skills-4-SE. Assertion Synthesizer is an agent skill from ArabelaTso/Skills-4-SE. Generate test assertions from existing code implementation.

When should I use Assertion Synthesizer?

Assertion Synthesizer fits situations like: the user has implementation code without tests; incomplete test coverage; needs assertions synthesized by analyzing the codes behavior.

How do I install Assertion Synthesizer in Claude Code?

Run `npx skills add ArabelaTso/Skills-4-SE --skill assertion-synthesizer -a claude-code`. Or copy the skill folder (skills/assertion-synthesizer in ArabelaTso/Skills-4-SE) into .claude/skills/assertion-synthesizer in your project. Claude Code loads it when a task matches its description.

How do I install Assertion Synthesizer in Codex?

Run `npx skills add ArabelaTso/Skills-4-SE --skill assertion-synthesizer -a codex`. Or copy the skill folder (skills/assertion-synthesizer in ArabelaTso/Skills-4-SE) into .agents/skills/assertion-synthesizer in your project. Codex loads it when a task matches its description.

Can I use Assertion Synthesizer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ArabelaTso/Skills-4-SE --skill assertion-synthesizer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/assertion-synthesizer, .gemini/skills/assertion-synthesizer, .github/skills/assertion-synthesizer and .opencode/skills/assertion-synthesizer in your project.

What does Assertion Synthesizer need to run?

SKILL.md names no scripts, command-line tools or credentials: Assertion Synthesizer is instructions for the agent only. Our summary lists: Python 3.

Does Assertion Synthesizer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Assertion Synthesizer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Assertion Synthesizer use?

Assertion Synthesizer is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Assertion Synthesizer use?

About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Assertion Synthesizer?

Skills that share tags, products or a category with Assertion Synthesizer: TDD Guide (LeoYeAI/openclaw-master-skills, 2.2k stars), Python Testing Patterns (jh941213/my-cc-harness, 126 stars), Test Analysis Extensions (microsoft/testfx, 1k stars) and TDD Guide (alirezarezvani/claude-skills, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Assertion Synthesizer?

ArabelaTso (a GitHub user) maintains it in ArabelaTso/Skills-4-SE, which has 253 GitHub stars. The repository holds 170 skills in this directory. The repository was last updated on August 21, 2026.

Source: ArabelaTso/Skills-4-SE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.