diff --git a/.github/workflows/validate.yml b/.github/workflows/validate.yml
new file mode 100644
index 00000000..68c78a32
--- /dev/null
+++ b/.github/workflows/validate.yml
@@ -0,0 +1,85 @@
+name: Validate
+
+on:
+  pull_request:
+    branches: ["*"]
+
+permissions:
+  contents: write
+
+jobs:
+  format:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ github.head_ref }}
+          token: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install dependencies
+        run: uv sync --extra dev
+
+      - name: Run ruff formatting
+        run: uv run ruff format src/ tests/
+
+      - name: Run ruff linting with auto-fix
+        run: uv run ruff check --fix src/ tests/
+
+      - name: Re-run formatting after auto-fix
+        run: uv run ruff format src/ tests/
+
+      - name: Verify all issues are fixed
+        run: |
+          uv run ruff check src/ tests/
+          uv run ruff format --check src/ tests/
+
+      - name: Check for changes
+        id: check_changes
+        run: |
+          if [[ -n "$(git status --porcelain)" ]]; then
+            echo "has_changes=true" >> $GITHUB_OUTPUT
+          else
+            echo "has_changes=false" >> $GITHUB_OUTPUT
+          fi
+
+      - name: Commit and push formatting changes
+        if: steps.check_changes.outputs.has_changes == 'true'
+        run: |
+          git config --local user.email "github-actions[bot]@users.noreply.github.com"
+          git config --local user.name "github-actions[bot]"
+          git add -A
+          git commit -m "style: auto-format code with ruff"
+          git push
+
+  tests:
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          version: "latest"
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install dependencies
+        run: uv sync --extra dev
+
+      - name: Run tests
+        run: uv run pytest tests/ -v
diff --git a/src/deepwork/__init__.py b/src/deepwork/__init__.py
index 9e3fc9c1..38f6acdf 100644
--- a/src/deepwork/__init__.py
+++ b/src/deepwork/__init__.py
@@ -8,6 +8,7 @@
     "__author__",
 ]
 
+
 # Lazy imports to avoid circular dependencies and missing modules during development
 def __getattr__(name: str) -> object:
     """Lazy import for core modules."""
@@ -19,5 +20,6 @@ def __getattr__(name: str) -> object:
             StepInput,
             parse_job_definition,
         )
+
         return locals()[name]
     raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
diff --git a/src/deepwork/cli/install.py b/src/deepwork/cli/install.py
index d710bf8a..030f5668 100644
--- a/src/deepwork/cli/install.py
+++ b/src/deepwork/cli/install.py
@@ -20,9 +20,7 @@ class InstallError(Exception):
     pass
 
 
-def _inject_standard_job(
-    job_name: str, jobs_dir: Path, project_path: Path
-) -> None:
+def _inject_standard_job(job_name: str, jobs_dir: Path, project_path: Path) -> None:
     """
     Inject a standard job definition into the project.
 
@@ -54,8 +52,7 @@ def _inject_standard_job(
 
         shutil.copytree(standard_jobs_dir, target_dir)
         console.print(
-            f"  [green]✓[/green] Installed {job_name} "
-            f"({target_dir.relative_to(project_path)})"
+            f"  [green]✓[/green] Installed {job_name} ({target_dir.relative_to(project_path)})"
         )
     except Exception as e:
         raise InstallError(f"Failed to install {job_name}: {e}") from e
@@ -250,9 +247,7 @@ def _install_deepwork(platform_name: str | None, project_path: Path) -> None:
     # Add platform if not already present
     if platform_to_add not in config_data["platforms"]:
         config_data["platforms"].append(platform_to_add)
-        console.print(
-            f"  [green]✓[/green] Added {platform_config.display_name} to platforms"
-        )
+        console.print(f"  [green]✓[/green] Added {platform_config.display_name} to platforms")
     else:
         console.print(f"  [dim]•[/dim] {platform_config.display_name} already configured")
 
diff --git a/src/deepwork/cli/sync.py b/src/deepwork/cli/sync.py
index 126b9480..c895819e 100644
--- a/src/deepwork/cli/sync.py
+++ b/src/deepwork/cli/sync.py
@@ -137,9 +137,7 @@ def sync_commands(project_path: Path) -> None:
         if job_hooks_list:
             console.print("  [dim]•[/dim] Syncing hooks...")
             try:
-                hooks_count = sync_hooks_to_platform(
-                    project_path, platform_config, job_hooks_list
-                )
+                hooks_count = sync_hooks_to_platform(project_path, platform_config, job_hooks_list)
                 stats["hooks"] += hooks_count
                 if hooks_count > 0:
                     console.print(f"    [green]✓[/green] Synced {hooks_count} hook(s)")
diff --git a/src/deepwork/core/generator.py b/src/deepwork/core/generator.py
index 16a45e27..616dad78 100644
--- a/src/deepwork/core/generator.py
+++ b/src/deepwork/core/generator.py
@@ -100,9 +100,7 @@ def _build_step_context(
         instructions_file = job.job_dir / step.instructions_file
         instructions_content = safe_read(instructions_file)
         if instructions_content is None:
-            raise GeneratorError(
-                f"Step instructions file not found: {instructions_file}"
-            )
+            raise GeneratorError(f"Step instructions file not found: {instructions_file}")
 
         # Separate user inputs and file inputs
         user_inputs = [
@@ -142,9 +140,7 @@ def _build_step_context(
                 prompt_file_path = job.job_dir / hook.prompt_file
                 prompt_content = safe_read(prompt_file_path)
                 if prompt_content is None:
-                    raise GeneratorError(
-                        f"Stop hook prompt file not found: {prompt_file_path}"
-                    )
+                    raise GeneratorError(f"Stop hook prompt file not found: {prompt_file_path}")
                 hook_ctx["content"] = prompt_content
             elif hook.is_script():
                 hook_ctx["type"] = "script"
@@ -203,9 +199,7 @@ def generate_step_command(
 
         # Find step index
         try:
-            step_index = next(
-                i for i, s in enumerate(job.steps) if s.id == step.id
-            )
+            step_index = next(i for i, s in enumerate(job.steps) if s.id == step.id)
         except StopIteration as e:
             raise GeneratorError(f"Step '{step.id}' not found in job '{job.name}'") from e
 
@@ -262,4 +256,3 @@ def generate_all_commands(
             command_paths.append(command_path)
 
         return command_paths
-
diff --git a/src/deepwork/core/hooks_syncer.py b/src/deepwork/core/hooks_syncer.py
index e11bd366..13e01954 100644
--- a/src/deepwork/core/hooks_syncer.py
+++ b/src/deepwork/core/hooks_syncer.py
@@ -8,7 +8,6 @@
 import yaml
 
 from deepwork.core.detector import PlatformConfig
-from deepwork.utils.yaml_utils import load_yaml
 
 
 class HooksSyncError(Exception):
diff --git a/src/deepwork/core/parser.py b/src/deepwork/core/parser.py
index 640ec92b..babf16fc 100644
--- a/src/deepwork/core/parser.py
+++ b/src/deepwork/core/parser.py
@@ -155,9 +155,7 @@ def validate_dependencies(self) -> None:
         for step in self.steps:
             for dep_id in step.dependencies:
                 if dep_id not in step_ids:
-                    raise ParseError(
-                        f"Step '{step.id}' depends on non-existent step '{dep_id}'"
-                    )
+                    raise ParseError(f"Step '{step.id}' depends on non-existent step '{dep_id}'")
 
         # Check for circular dependencies using topological sort
         visited = set()
diff --git a/src/deepwork/hooks/evaluate_policies.py b/src/deepwork/hooks/evaluate_policies.py
index e5af4950..341b6d16 100644
--- a/src/deepwork/hooks/evaluate_policies.py
+++ b/src/deepwork/hooks/evaluate_policies.py
@@ -63,7 +63,7 @@ def format_policy_message(policies: list) -> str:
     lines = ["## DeepWork Policies Triggered", ""]
     lines.append(
         "Comply with the following policies. "
-        "To mark a policy as addressed, include `<promise policy=\"Policy Name\">addressed</promise>` "
+        'To mark a policy as addressed, include `<promise policy="Policy Name">addressed</promise>` '
         "in your response."
     )
     lines.append("")
diff --git a/src/deepwork/utils/fs.py b/src/deepwork/utils/fs.py
index d775f0cc..f650516a 100644
--- a/src/deepwork/utils/fs.py
+++ b/src/deepwork/utils/fs.py
@@ -54,9 +54,7 @@ def safe_read(path: Path | str) -> str | None:
     return path_obj.read_text(encoding="utf-8")
 
 
-def copy_dir(
-    src: Path | str, dst: Path | str, ignore_patterns: list[str] | None = None
-) -> None:
+def copy_dir(src: Path | str, dst: Path | str, ignore_patterns: list[str] | None = None) -> None:
     """
     Recursively copy directory, optionally ignoring patterns.
 
diff --git a/tests/integration/test_full_workflow.py b/tests/integration/test_full_workflow.py
index 17c830ff..7f2a5708 100644
--- a/tests/integration/test_full_workflow.py
+++ b/tests/integration/test_full_workflow.py
@@ -10,9 +10,7 @@
 class TestJobWorkflow:
     """Integration tests for complete job workflow."""
 
-    def test_parse_and_generate_workflow(
-        self, fixtures_dir: Path, temp_dir: Path
-    ) -> None:
+    def test_parse_and_generate_workflow(self, fixtures_dir: Path, temp_dir: Path) -> None:
         """Test complete workflow: parse job → generate commands."""
         # Step 1: Parse job definition
         job_dir = fixtures_dir / "jobs" / "complex_job"
@@ -40,7 +38,7 @@ def test_parse_and_generate_workflow(
             assert f"# {job.name}.{job.steps[i].id}" in content
 
             # Check step numbers
-            assert f"Step {i+1} of 4" in content
+            assert f"Step {i + 1} of 4" in content
 
     def test_simple_job_workflow(self, fixtures_dir: Path, temp_dir: Path) -> None:
         """Test workflow with simple single-step job."""
@@ -68,9 +66,7 @@ def test_simple_job_workflow(self, fixtures_dir: Path, temp_dir: Path) -> None:
         assert "input_param" in content
         assert "Command Complete" in content  # Standalone completion message
 
-    def test_command_generation_with_dependencies(
-        self, fixtures_dir: Path, temp_dir: Path
-    ) -> None:
+    def test_command_generation_with_dependencies(self, fixtures_dir: Path, temp_dir: Path) -> None:
         """Test that generated commands properly handle dependencies."""
         job_dir = fixtures_dir / "jobs" / "complex_job"
         job = parse_job_definition(job_dir)
@@ -99,9 +95,7 @@ def test_command_generation_with_dependencies(
         assert "## Workflow Complete" in step4_content
         assert "## Next Step" not in step4_content
 
-    def test_command_generation_with_file_inputs(
-        self, fixtures_dir: Path, temp_dir: Path
-    ) -> None:
+    def test_command_generation_with_file_inputs(self, fixtures_dir: Path, temp_dir: Path) -> None:
         """Test that generated commands properly handle file inputs."""
         job_dir = fixtures_dir / "jobs" / "complex_job"
         job = parse_job_definition(job_dir)
@@ -125,9 +119,7 @@ def test_command_generation_with_file_inputs(
         assert "primary_research.md" in step4_content
         assert "secondary_research.md" in step4_content
 
-    def test_command_generation_with_user_inputs(
-        self, fixtures_dir: Path, temp_dir: Path
-    ) -> None:
+    def test_command_generation_with_user_inputs(self, fixtures_dir: Path, temp_dir: Path) -> None:
         """Test that generated commands properly handle user parameter inputs."""
         job_dir = fixtures_dir / "jobs" / "complex_job"
         job = parse_job_definition(job_dir)
diff --git a/tests/integration/test_install_flow.py b/tests/integration/test_install_flow.py
index 12096d24..ac992f7b 100644
--- a/tests/integration/test_install_flow.py
+++ b/tests/integration/test_install_flow.py
@@ -16,8 +16,9 @@ def test_install_with_claude(self, mock_claude_project: Path) -> None:
         runner = CliRunner()
 
         result = runner.invoke(
-            cli, ["install", "--platform", "claude", "--path", str(mock_claude_project)],
-            catch_exceptions=False
+            cli,
+            ["install", "--platform", "claude", "--path", str(mock_claude_project)],
+            catch_exceptions=False,
         )
 
         assert result.exit_code == 0
@@ -54,8 +55,7 @@ def test_install_with_auto_detect(self, mock_claude_project: Path) -> None:
         runner = CliRunner()
 
         result = runner.invoke(
-            cli, ["install", "--path", str(mock_claude_project)],
-            catch_exceptions=False
+            cli, ["install", "--path", str(mock_claude_project)], catch_exceptions=False
         )
 
         assert result.exit_code == 0
@@ -101,9 +101,7 @@ def test_install_fails_with_multiple_platforms(self, temp_dir: Path) -> None:
         assert result.exit_code != 0
         assert "Multiple AI platforms detected" in result.output
 
-    def test_install_with_specified_platform_when_missing(
-        self, mock_git_repo: Path
-    ) -> None:
+    def test_install_with_specified_platform_when_missing(self, mock_git_repo: Path) -> None:
         """Test that install fails when specified platform is not present."""
         runner = CliRunner()
 
@@ -121,15 +119,17 @@ def test_install_is_idempotent(self, mock_claude_project: Path) -> None:
 
         # First install
         result1 = runner.invoke(
-            cli, ["install", "--platform", "claude", "--path", str(mock_claude_project)],
-            catch_exceptions=False
+            cli,
+            ["install", "--platform", "claude", "--path", str(mock_claude_project)],
+            catch_exceptions=False,
         )
         assert result1.exit_code == 0
 
         # Second install
         result2 = runner.invoke(
-            cli, ["install", "--platform", "claude", "--path", str(mock_claude_project)],
-            catch_exceptions=False
+            cli,
+            ["install", "--platform", "claude", "--path", str(mock_claude_project)],
+            catch_exceptions=False,
         )
         assert result2.exit_code == 0
 
diff --git a/tests/unit/test_evaluate_policies.py b/tests/unit/test_evaluate_policies.py
index dfda87fd..99b88b23 100644
--- a/tests/unit/test_evaluate_policies.py
+++ b/tests/unit/test_evaluate_policies.py
@@ -1,9 +1,7 @@
 """Tests for the hooks evaluate_policies module."""
 
-import pytest
-
-from deepwork.hooks.evaluate_policies import extract_promise_tags, format_policy_message
 from deepwork.core.policy_parser import Policy
+from deepwork.hooks.evaluate_policies import extract_promise_tags, format_policy_message
 
 
 class TestExtractPromiseTags:
@@ -45,11 +43,11 @@ def test_returns_empty_set_for_no_promises(self) -> None:
 
     def test_multiline_promise_content(self) -> None:
         """Test promise tag with multiline content."""
-        text = '''<promise policy="Complex Policy">
+        text = """<promise policy="Complex Policy">
         I have addressed this by:
         1. Updating the docs
         2. Running tests
-        </promise>'''
+        </promise>"""
         result = extract_promise_tags(text)
         assert result == {"Complex Policy"}
 
diff --git a/tests/unit/test_generator.py b/tests/unit/test_generator.py
index 5774f10d..92f98a90 100644
--- a/tests/unit/test_generator.py
+++ b/tests/unit/test_generator.py
@@ -5,7 +5,7 @@
 import pytest
 
 from deepwork.core.detector import PLATFORMS
-from deepwork.core.generator import GeneratorError, CommandGenerator
+from deepwork.core.generator import CommandGenerator, GeneratorError
 from deepwork.core.parser import parse_job_definition
 
 
@@ -35,9 +35,7 @@ def test_init_raises_for_missing_templates_dir(self, temp_dir: Path) -> None:
         with pytest.raises(GeneratorError, match="Templates directory not found"):
             CommandGenerator(nonexistent)
 
-    def test_generate_step_command_simple_job(
-        self, fixtures_dir: Path, temp_dir: Path
-    ) -> None:
+    def test_generate_step_command_simple_job(self, fixtures_dir: Path, temp_dir: Path) -> None:
         """Test generating command for simple job step."""
         job_dir = fixtures_dir / "jobs" / "simple_job"
         job = parse_job_definition(job_dir)
@@ -45,9 +43,7 @@ def test_generate_step_command_simple_job(
         generator = CommandGenerator()
         platform = PLATFORMS["claude"]
 
-        command_path = generator.generate_step_command(
-            job, job.steps[0], platform, temp_dir
-        )
+        command_path = generator.generate_step_command(job, job.steps[0], platform, temp_dir)
 
         assert command_path.exists()
         assert command_path.name == "simple_job.single_step.md"
@@ -69,9 +65,7 @@ def test_generate_step_command_complex_job_first_step(
         generator = CommandGenerator()
         platform = PLATFORMS["claude"]
 
-        command_path = generator.generate_step_command(
-            job, job.steps[0], platform, temp_dir
-        )
+        command_path = generator.generate_step_command(job, job.steps[0], platform, temp_dir)
 
         content = command_path.read_text()
         assert "# competitive_research.identify_competitors" in content
@@ -94,9 +88,7 @@ def test_generate_step_command_complex_job_middle_step(
         platform = PLATFORMS["claude"]
 
         # Generate primary_research (step 2)
-        command_path = generator.generate_step_command(
-            job, job.steps[1], platform, temp_dir
-        )
+        command_path = generator.generate_step_command(job, job.steps[1], platform, temp_dir)
 
         content = command_path.read_text()
         assert "# competitive_research.primary_research" in content
@@ -121,9 +113,7 @@ def test_generate_step_command_complex_job_final_step(
         platform = PLATFORMS["claude"]
 
         # Generate comparative_report (step 4)
-        command_path = generator.generate_step_command(
-            job, job.steps[3], platform, temp_dir
-        )
+        command_path = generator.generate_step_command(job, job.steps[3], platform, temp_dir)
 
         content = command_path.read_text()
         assert "# competitive_research.comparative_report" in content
@@ -230,9 +220,7 @@ def test_generate_step_command_different_platform(
             generator = CommandGenerator()
             platform = PLATFORMS["gemini"]
 
-            command_path = generator.generate_step_command(
-                job, job.steps[0], platform, temp_dir
-            )
+            command_path = generator.generate_step_command(job, job.steps[0], platform, temp_dir)
 
             # Gemini uses same filename format
             assert command_path.name == "simple_job.single_step.md"
diff --git a/tests/unit/test_hooks_syncer.py b/tests/unit/test_hooks_syncer.py
index 2750eefb..5a8d4ea0 100644
--- a/tests/unit/test_hooks_syncer.py
+++ b/tests/unit/test_hooks_syncer.py
@@ -3,17 +3,14 @@
 import json
 from pathlib import Path
 
-import pytest
-
+from deepwork.core.detector import PlatformConfig
 from deepwork.core.hooks_syncer import (
     HookEntry,
-    HooksSyncError,
     JobHooks,
     collect_job_hooks,
     merge_hooks_for_platform,
     sync_hooks_to_claude,
 )
-from deepwork.core.detector import PlatformConfig
 
 
 class TestHookEntry:
@@ -280,9 +277,7 @@ def test_does_not_duplicate_existing_hooks(self, temp_dir: Path) -> None:
         # Settings with existing hook
         existing_settings = {
             "hooks": {
-                "Stop": [
-                    {"matcher": "", "hooks": [{"type": "command", "command": "hook.sh"}]}
-                ]
+                "Stop": [{"matcher": "", "hooks": [{"type": "command", "command": "hook.sh"}]}]
             },
         }
         settings_file = claude_dir / "settings.json"
diff --git a/tests/unit/test_policy_parser.py b/tests/unit/test_policy_parser.py
index 8e79cfca..031c506e 100644
--- a/tests/unit/test_policy_parser.py
+++ b/tests/unit/test_policy_parser.py
@@ -210,10 +210,7 @@ def test_multiple_safety_patterns(self) -> None:
 
         # Should not fire if any safety file is changed
         assert evaluate_policy(policy, ["src/auth/login.py", "SECURITY.md"]) is False
-        assert (
-            evaluate_policy(policy, ["src/auth/login.py", "docs/security_review.md"])
-            is False
-        )
+        assert evaluate_policy(policy, ["src/auth/login.py", "docs/security_review.md"]) is False
 
         # Should fire if no safety files changed
         assert evaluate_policy(policy, ["src/auth/login.py"]) is True
diff --git a/tests/unit/test_stop_hooks.py b/tests/unit/test_stop_hooks.py
index bc84b406..cd0fcc77 100644
--- a/tests/unit/test_stop_hooks.py
+++ b/tests/unit/test_stop_hooks.py
@@ -1,7 +1,6 @@
 """Tests for stop hook functionality."""
 
 from pathlib import Path
-from unittest.mock import patch
 
 import pytest
 
@@ -388,9 +387,7 @@ def test_build_context_with_prompt_hook(
         self, generator: CommandGenerator, job_with_hooks: JobDefinition
     ) -> None:
         """Test context building includes prompt stop hook."""
-        context = generator._build_step_context(
-            job_with_hooks, job_with_hooks.steps[0], 0
-        )
+        context = generator._build_step_context(job_with_hooks, job_with_hooks.steps[0], 0)
         assert "stop_hooks" in context
         assert len(context["stop_hooks"]) == 1
         assert context["stop_hooks"][0]["type"] == "prompt"
@@ -451,9 +448,7 @@ def test_build_context_with_missing_prompt_file(
         with pytest.raises(GeneratorError, match="prompt file not found"):
             generator._build_step_context(job, job.steps[0], 0)
 
-    def test_build_context_no_hooks(
-        self, generator: CommandGenerator, tmp_path: Path
-    ) -> None:
+    def test_build_context_no_hooks(self, generator: CommandGenerator, tmp_path: Path) -> None:
         """Test context with no stop hooks."""
         job_dir = tmp_path / "test_job"
         job_dir.mkdir()