TE

test-and-fix

Automatically runs tests and applies fixes to resolve failures.

Install

mkdir -p .claude/skills/test-and-fix && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16837" && unzip -o skill.zip -d .claude/skills/test-and-fix && rm skill.zip

Installs to .claude/skills/test-and-fix

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Run unit tests and automatically fix code failures, regression bugs, or test mismatches. Use when tests are failing, after implementing new features, or to repair "broken" tests.
178 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Identify failing unit tests using `make test`
  • Analyze `pytest` output to pinpoint failing files, line numbers, and errors
  • Apply minimal fixes to source code for bugs or test code for outdated tests
  • Verify fixes by re-running tests
  • Loop through identification, analysis, fixing, and verification until all tests pass
  • Terminate the loop if all tests pass or an iteration limit is reached

How it works

The skill operates in a loop to identify failing unit tests, analyze their output, apply minimal fixes to either source or test code, and then re-verify until all tests pass or a limit is met.

Inputs & outputs

You give it
Failing unit tests
You get back
Passing unit tests or a report indicating persistent errors

When to use test-and-fix

  • Fixing failing unit tests
  • Automating regression bug repairs
  • Maintaining test suite health

About this skill

Test and Fix Loop

Purpose

An autonomous loop for the agent to identify, analyze, and fix failing unit tests using pytest.

Loop Logic

  1. Identify: Run make test to identify failing tests.
  2. Analyze: Examine the pytest output to determine:
    • The failing test file and line number.
    • The expected vs actual values (assertion errors).
    • Tracebacks for runtime errors.
  3. Fix: Apply the minimum necessary change to either the source code (if it's a bug) or the test code (if the test is outdated).
  4. Verify: Re-run make test (or uv run pytest path/to/failing_test.py for speed).
    • If passed: Move to the next failing test or finish if all are resolved.
    • If failed: Analyze the new failure and repeat the loop.

Termination Criteria

  • All tests pass (as reported by make test).
  • Reached max iteration limit (default: 5).
  • The error persists after multiple distinct fix attempts, indicating a need for human intervention.

Examples

Scenario: Fixing a logic error

  1. make test fails in src/your_package/tests/test_dummy.py due to an assertion or import error.
  2. Agent inspects the failing test and the implementation under src/your_package/.
  3. Agent applies the minimum fix in source or test so behavior matches the intended contract.
  4. make test passes.

Resources

When not to use it

  • When all tests are already passing
  • When human intervention is explicitly required due to persistent errors
  • When the task is to write new tests for new features

Limitations

  • Terminates after a maximum iteration limit (default: 5)
  • Requires `pytest` for test execution and output analysis
  • May require human intervention if errors persist after multiple attempts

How it compares

This skill automates the iterative process of finding, fixing, and verifying unit test failures, providing an autonomous loop for bug resolution, unlike manual debugging.

Compared to similar skills

test-and-fix side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
test-and-fix (this skill)03moNo flagsIntermediate
python-testing-patterns773moReviewIntermediate
python-playground24moReviewBeginner
mflux-manual-testing22moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry