feat(slash-commands): add generator for AI assistant native slash commands

.github/workflows/ci.yml

@@ -39,7 +39,7 @@ jobs:
         run: uv sync --all-groups --frozen
 
       - name: Run tests with coverage
-        run: uv run pytest -vv --cov=mcp_server --cov-report=term-missing:skip-covered --cov-report=xml
+        run: uv run pytest -vv --cov=mcp_server --cov=slash_commands --cov-report=term-missing:skip-covered --cov-report=xml
 
 
       - name: Upload coverage.xml artifact

.gitignore

@@ -2,7 +2,10 @@
 __pycache__
 .venv
 
-# Misc
-temp/
+# Coverage
+htmlcov
 .coverage
 coverage.xml
+
+# Misc
+temp/

.pre-commit-config.yaml

@@ -32,3 +32,13 @@ repos:
         stages: [commit-msg]
         args:
           - "--extends=@commitlint/config-conventional"
+
+  - repo: local
+    hooks:
+      - id: run-tests
+        name: Run pytest before push
+        entry: pytest
+        language: system
+        stages: [pre-push]
+        pass_filenames: false
+        always_run: true

CONTRIBUTING.md

@@ -32,7 +32,7 @@ pre-commit install
 ### Common Commands
 
 ```bash
-# Run tests
+# Run tests with coverage
 uv run pytest
 
 # Run full pre-commit checks across the repo
@@ -55,14 +55,19 @@ See `docs/operations.md` for more details on transports and configuration.
 
 ## Testing
 
-- Tests use `pytest`.
+- Tests use `pytest` with coverage reporting via `pytest-cov`.
 - Before submitting a PR, run:
 
 ```bash
+# Run tests with coverage report
 uv run pytest
-uv run pre-commit run --all-files
+
+# View HTML coverage report (opens in default browser)
+uv run python -m webbrowser htmlcov/index.html
 ```
 
+The test suite generates both terminal and HTML coverage reports showing which code paths are tested.
+
 ## Branching and Commit Conventions
 
 ### Branch Naming

README.md

@@ -15,6 +15,28 @@
     <a href="docs/operations.md"><img src="https://img.shields.io/badge/docs-Operations-blue" alt="Documentation"/></a>
 </p>
 
+## TLDR
+
+**Install the workflow prompts as slash commands:**
+
+```bash
+uvx --from git+https://github.com/liatrio-labs/spec-driven-workflow sdd-generate-commands generate --yes
+```
+
+**Use `/generate-spec` with your idea:**
+
+```text
+I want to add user authentication to my app
+```
+
+→ AI asks clarifying questions → You provide answers → Spec created in `tasks/0001-spec-user-auth.md`
+
+**Continue the flow:**
+
+- Run `/generate-task-list-from-spec` → Task list created in `tasks/tasks-0001-spec-user-auth.md`
+- Use `/manage-tasks` → Execute tasks one-by-one with proof artifacts
+- **SHIP IT** 🚢💨
+
 ## Highlights
 
 - **Prompt-first workflow:** Use curated prompts to go from idea → spec → task list → implementation-ready backlog.
@@ -115,19 +137,40 @@ sequenceDiagram
 - **Status Keys:** `[ ]` not started, `[~]` in progress, `[x]` complete, mirroring the manage-tasks guidance.
 - **Proof Artifacts:** URLs, CLI commands, screenshots, or tests captured per task to demonstrate working software.
 
-## Hands-On Usage (No MCP Required)
+## Hands-On Usage
+
+The SDD workflow can be used in three ways, from simplest to most automated:
+
+### Option 1: Manual Copy-Paste (No Tooling Required)
 
 1. **Kick off a spec:** Copy or reference `prompts/generate-spec.md` inside your preferred AI chat. Provide the feature idea, answer the clarifying questions, and review the generated spec before saving it under `/tasks`.
 2. **Plan the work:** Point the assistant to the new spec and walk through `prompts/generate-task-list-from-spec.md`. Approve parent tasks first, then request the detailed subtasks and relevant files. Commit the result to `/tasks`.
 3. **Execute with discipline:** Follow `prompts/manage-tasks.md` while implementing. Update statuses as you work, attach proof artifacts, and pause for reviews at each demoable slice.
 
-### Slash Command Integration (TBD)
+### Option 2: Native Slash Commands (Recommended)
 
-Guides are coming for wiring these prompts as first-class slash commands in popular IDEs and AI tools (Windsurf, VS Code, Cursor, Claude Code, Codex, and more).
+Generate slash commands for your AI coding assistant and use the prompts as native commands:
 
-## Optional: Automate with the MCP Server
+```bash
+# Clone and install locally
+git clone https://github.com/liatrio-labs/spec-driven-workflow-mcp.git
+cd spec-driven-workflow-mcp
+uv sync
+uv run sdd-generate-commands --yes
+
+# Or run directly from the git repo via uvx
+uvx --from git+https://github.com/liatrio-labs/spec-driven-workflow-mcp sdd-generate-commands --yes
+```
+
+This will auto-detect your configured AI assistants (Claude Code, Cursor, Windsurf, etc.) and generate command files in your home directory.
 
-Prefer tighter tooling? This repository also ships an MCP server that exposes the same prompts programmatically. Treat it as an accelerator—everything above works without it.
+**Note**: Once available on PyPI, you'll be able to run `uvx spec-driven-development-mcp sdd-generate-commands --yes` for a one-liner installation.
+
+See [docs/slash-command-generator.md](./docs/slash-command-generator.md) for details.
+
+### Option 3: MCP Server (Advanced)
+
+Run the prompts as an MCP server for programmatic access. This option is most useful for custom integrations and tools that support MCP.
 
 > Note: MCP prompt support is not uniformly supported across AI tools. See [docs/mcp-prompt-support.md](./docs/mcp-prompt-support.md) for details.
 
@@ -153,7 +196,11 @@ uv sync
 **STDIO (local development):**
 
 ```bash
+# From local clone
 uvx fastmcp run server.py
+
+# Or run directly from the git repo via uvx
+uvx --from git+https://github.com/liatrio-labs/spec-driven-workflow-mcp spec-driven-development-mcp
 ```
 
 **With MCP Inspector:**
@@ -165,9 +212,15 @@ uvx fastmcp dev server.py
 **HTTP Transport:**
 
 ```bash
+# Use fastmcp CLI for HTTP transport
 uvx fastmcp run server.py --transport http --port 8000
+
+# Or run directly from the git repo via uvx
+uvx --from git+https://github.com/liatrio-labs/spec-driven-workflow-mcp spec-driven-development-mcp --transport http --port 8000
 ```
 
+**Note**: Once available on PyPI, you'll be able to run `uvx spec-driven-development-mcp` for a one-liner installation with optional `--transport` and `--port` arguments. The `fastmcp run` approach remains available for development and advanced options.
+
 See [docs/operations.md](docs/operations.md) and [CONTRIBUTING.md](CONTRIBUTING.md) for advanced configuration, deployment, and contribution guidelines.
 
 ## References

__version__.py

@@ -0,0 +1,26 @@
+"""Centralized version management for the project.
+
+This module reads the version from pyproject.toml to ensure a single source of truth.
+"""
+
+from __future__ import annotations
+
+import tomllib
+from importlib.metadata import version as get_package_version
+from pathlib import Path
+
+
+def _get_version() -> str:
+    """Get the version from pyproject.toml."""
+    pyproject_path = Path(__file__).parent / "pyproject.toml"
+    if pyproject_path.exists():
+        # Local development mode
+        with pyproject_path.open("rb") as f:
+            data = tomllib.load(f)
+        return data["project"]["version"]
+    else:
+        # Installed package mode
+        return get_package_version("spec-driven-development-mcp")
+
+
+__version__ = _get_version()

docs/operations.md

@@ -147,10 +147,10 @@ uv run pytest
 ### Run with Coverage
 
 ```bash
-uv run pytest --cov=mcp_server --cov-report=html
+uv run pytest --cov=mcp_server --cov=slash_commands --cov-report=html
 ```
 
-### Run Specific Test File
+Open `htmlcov/index.html` in your browser to view the detailed coverage report.
 
 ```bash
 uv run pytest tests/test_prompts.py -v