diff --git a/.github/dependabot.yml b/.github/dependabot.yml
index 4dcc1c5..85c1d1b 100644
--- a/.github/dependabot.yml
+++ b/.github/dependabot.yml
@@ -13,9 +13,3 @@ updates:
     directory: "/.github/workflows"
     schedule:
       interval: "daily"
-
-  # Maintain dependencies for Python scripts
-  - package-ecosystem: "pip"
-    directory: "/.github/scripts"
-    schedule:
-      interval: "daily"
diff --git a/.github/scripts/requirements.txt b/.github/scripts/requirements.txt
deleted file mode 100644
index 1e6548c..0000000
--- a/.github/scripts/requirements.txt
+++ /dev/null
@@ -1,3 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-
-check-jsonschema>=0.28.2
diff --git a/.github/workflows/actionlint.yml b/.github/workflows/actionlint.yml
index 24bdfc8..6fac671 100644
--- a/.github/workflows/actionlint.yml
+++ b/.github/workflows/actionlint.yml
@@ -38,7 +38,6 @@ jobs:
         uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
         with:
           fetch-depth: 0
-          submodules: true
 
       - name: "Download actionlint"
         run: |
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
index 208f567..200e081 100644
--- a/.github/workflows/docs.yml
+++ b/.github/workflows/docs.yml
@@ -40,7 +40,6 @@ jobs:
         uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
         with:
           fetch-depth: 0
-          submodules: true
       - name: "Check Markdown documents"
         uses: DavidAnson/markdownlint-cli2-action@b4c9feab76d8025d1e83c653fa3990936df0e6c8 # v16.0.0
         with:
diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
index c4a405b..6cb96bc 100644
--- a/.github/workflows/lint.yml
+++ b/.github/workflows/lint.yml
@@ -1,24 +1,29 @@
 # SPDX-License-Identifier: Apache-2.0
 
-name: Lint Schema
+name: Lint
 
 on:
-  workflow_dispatch:
   push:
     branches:
-      - main
+      - "main"
     paths:
-      - 'v*/**/*.json'
+      - '**.py'
+      - 'src/instructlab/schema/v*/**/*.json'
+      - 'pyproject.toml'
+      - 'tox.ini'
+      - 'scripts/**'
       - '.github/workflows/lint.yml' # This workflow
-      - '.github/scripts/**' # Scripts used by this workflow
 
   pull_request:
     branches:
-      - main
+      - "main"
     paths:
-      - 'v*/**/*.json'
+      - '**.py'
+      - 'src/instructlab/schema/v*/**/*.json'
+      - 'pyproject.toml'
+      - 'tox.ini'
+      - 'scripts/**'
       - '.github/workflows/lint.yml' # This workflow
-      - '.github/scripts/**' # Scripts used by this workflow
 
 env:
   LC_ALL: en_US.UTF-8
@@ -33,6 +38,25 @@ permissions:
 jobs:
   lint:
     runs-on: ubuntu-latest
+    name: "${{ matrix.lint.name }}"
+    strategy:
+      fail-fast: false
+      matrix:
+        lint:
+          - name: "jsonschema"
+            commands: |
+              tox -e jsonschema
+          - name: "ruff"
+            commands: |
+              tox -e ruff -- check
+          - name: "pylint"
+            commands: |
+              echo "::add-matcher::.github/workflows/matchers/pylint.json"
+              tox -e pylint
+          - name: "mypy"
+            commands: |
+              echo "::add-matcher::.github/workflows/matchers/mypy.json"
+              tox -e mypy
     steps:
       - name: "Harden Runner"
         uses: step-security/harden-runner@17d0e2bd7d51742c71671bd19fa12bdc9d40a3d6 # v2.8.1
@@ -49,24 +73,13 @@ jobs:
         with:
           python-version: "3.11"
 
-      - name: "Install Python Packages"
+      - name: "Install tox"
         run: |
-          pip install -r .github/scripts/requirements.txt
+          python -m pip install --upgrade pip
+          python -m pip install tox tox-gh
 
-      - name: "Find changed schema files"
-        id: changed-files
-        uses: tj-actions/changed-files@d6babd6899969df1a11d14c368283ea4436bca78 # v44.5.2
-        with:
-          files: |
-            v*/**/*.json
-
-      - name: "Check changed schema file contents"
-        if: steps.changed-files.outputs.any_changed == 'true'
-        run: |
-          check-jsonschema --verbose --schemafile https://json-schema.org/draft/2020-12/schema ${{ steps.changed-files.outputs.all_changed_files }}
-
-      - name: "Check all schema file contents"
-        if: steps.changed-files.outputs.any_changed != 'true'
+      - name: "${{ matrix.lint.name }}"
         run: |
-          # shellcheck disable=SC2046
-          check-jsonschema --verbose --schemafile https://json-schema.org/draft/2020-12/schema $(find v* -name "*.json")
+          ${{ matrix.lint.commands }}
+        env:
+          RUFF_OUTPUT_FORMAT: github
diff --git a/.github/workflows/matchers/mypy.json b/.github/workflows/matchers/mypy.json
new file mode 100644
index 0000000..f048fce
--- /dev/null
+++ b/.github/workflows/matchers/mypy.json
@@ -0,0 +1,16 @@
+{
+  "problemMatcher": [
+    {
+      "owner": "mypy",
+      "pattern": [
+        {
+          "regexp": "^(.+):(\\d+):\\s(error|warning):\\s(.+)$",
+          "file": 1,
+          "line": 2,
+          "severity": 3,
+          "message": 4
+        }
+      ]
+    }
+  ]
+}
diff --git a/.github/workflows/matchers/pylint.json b/.github/workflows/matchers/pylint.json
new file mode 100644
index 0000000..5624ca6
--- /dev/null
+++ b/.github/workflows/matchers/pylint.json
@@ -0,0 +1,32 @@
+{
+  "problemMatcher": [
+    {
+      "owner": "pylint-error",
+      "severity": "error",
+      "pattern": [
+        {
+          "regexp": "^(.+):(\\d+):(\\d+):\\s(([EF]\\d{4}):\\s.+)$",
+          "file": 1,
+          "line": 2,
+          "column": 3,
+          "message": 4,
+          "code": 5
+        }
+      ]
+    },
+    {
+      "owner": "pylint-warning",
+      "severity": "warning",
+      "pattern": [
+        {
+          "regexp": "^(.+):(\\d+):(\\d+):\\s(([CRW]\\d{4}):\\s.+)$",
+          "file": 1,
+          "line": 2,
+          "column": 3,
+          "message": 4,
+          "code": 5
+        }
+      ]
+    }
+  ]
+}
diff --git a/.github/workflows/pypi.yml b/.github/workflows/pypi.yml
new file mode 100644
index 0000000..eeb0ca0
--- /dev/null
+++ b/.github/workflows/pypi.yml
@@ -0,0 +1,130 @@
+# SPDX-License-Identifier: Apache-2.0
+
+name: Build, test, and upload PyPI package
+
+on:
+    push:
+        branches:
+            - "main"
+        tags:
+            - "v*"
+    pull_request:
+        branches:
+            - "main"
+    release:
+        types:
+            - published
+
+env:
+    LC_ALL: en_US.UTF-8
+
+defaults:
+    run:
+        shell: bash
+
+permissions:
+    contents: read
+
+jobs:
+    # Create and verify release artifacts
+    # - build source dist (tar ball) and wheel
+    # - validate artifacts with various tools
+    # - upload artifacts to GHA
+    build-package:
+        name: Build and check packages
+        runs-on: ubuntu-latest
+        steps:
+            - name: "Harden Runner"
+              uses: step-security/harden-runner@17d0e2bd7d51742c71671bd19fa12bdc9d40a3d6 # v2.8.1
+              with:
+                  egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
+
+
+            - name: "Checkout"
+              uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
+              with:
+                  # for setuptools-scm
+                  fetch-depth: 0
+
+            - name: "Build and Inspect"
+              uses: hynek/build-and-inspect-python-package@b4fc3f6ba2b3da04f09659be99e2a29fb6146a61 # v2.6.0
+
+    # push to Test PyPI on
+    # - a new GitHub release is published
+    # - a PR is merged into main branch
+    publish-test-pypi:
+        name: Publish packages to test.pypi.org
+        # environment: publish-test-pypi
+        if: ${{ false && (github.repository_owner == 'instructlab') && ((github.event.action == 'published') || ((github.event_name == 'push') && (github.ref == 'refs/heads/main'))) }}
+        permissions:
+            contents: read
+            # see https://docs.pypi.org/trusted-publishers/
+            id-token: write
+        runs-on: ubuntu-latest
+        needs: build-package
+
+        steps:
+            - name: "Harden Runner"
+              uses: step-security/harden-runner@17d0e2bd7d51742c71671bd19fa12bdc9d40a3d6 # v2.8.1
+              with:
+                  egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
+
+            - name: "Download build artifacts"
+              uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
+              with:
+                  name: Packages
+                  path: dist
+
+            - name: "Upload to Test PyPI"
+              uses: pypa/gh-action-pypi-publish@81e9d935c883d0b210363ab89cf05f3894778450 # v1.8.14
+              with:
+                  repository-url: https://test.pypi.org/legacy/
+
+    # push to Production PyPI on
+    # - a new GitHub release is published
+    publish-pypi:
+        name: Publish release to pypi.org
+        # environment: publish-pypi
+        if: ${{ false && (github.repository_owner == 'instructlab') && (github.event.action == 'published') }}
+        permissions:
+            # see https://docs.pypi.org/trusted-publishers/
+            id-token: write
+            # allow gh release upload
+            contents: write
+
+        runs-on: ubuntu-latest
+        needs: build-package
+
+        steps:
+            - name: "Harden Runner"
+              uses: step-security/harden-runner@f086349bfa2bd1361f7909c78558e816508cdc10 # v2.8.0
+              with:
+                  egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
+
+            - name: "Download build artifacts"
+              uses: actions/download-artifact@65a9edc5881444af0b9093a5e628f2fe47ea3b2e # v4.1.7
+              with:
+                  name: Packages
+                  path: dist
+
+            - name: "Sigstore sign package"
+              uses: sigstore/gh-action-sigstore-python@61f6a500bbfdd9a2a339cf033e5421951fbc1cd2 # v2.1.1
+              with:
+                  inputs: |
+                      ./dist/*.tar.gz
+                      ./dist/*.whl
+
+            - name: "Upload artifacts and signatures to GitHub release"
+              run: |
+                  gh release upload '${{ github.ref_name }}' dist/* --repo '${{ github.repository }}'
+              env:
+                  GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+            # PyPI does not accept .sigstore artifacts and
+            # gh-action-pypi-publish has no option to ignore them.
+            - name: "Remove sigstore signatures before uploading to PyPI"
+              run: |
+                  rm ./dist/*.sigstore
+
+            - name: "Upload to PyPI"
+              uses: pypa/gh-action-pypi-publish@81e9d935c883d0b210363ab89cf05f3894778450 # v1.8.14
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
new file mode 100644
index 0000000..b6c6de3
--- /dev/null
+++ b/.github/workflows/test.yml
@@ -0,0 +1,73 @@
+# SPDX-License-Identifier: Apache-2.0
+
+name: Test
+
+on:
+  push:
+    branches:
+      - "main"
+    paths:
+      - '**.py'
+      - 'src/instructlab/schema/v*/**/*.json'
+      - 'pyproject.toml'
+      - 'tox.ini'
+      - 'scripts/**'
+      - '.github/workflows/test.yml' # This workflow
+  pull_request:
+    branches:
+      - "main"
+    paths:
+      - '**.py'
+      - 'src/instructlab/schema/v*/**/*.json'
+      - 'pyproject.toml'
+      - 'tox.ini'
+      - 'scripts/**'
+      - '.github/workflows/test.yml' # This workflow
+
+env:
+  LC_ALL: en_US.UTF-8
+
+defaults:
+  run:
+    shell: bash
+
+permissions:
+  contents: read
+
+jobs:
+  test:
+    name: "${{ matrix.python }} on ${{ matrix.platform }}"
+    runs-on: "${{ matrix.platform }}"
+    strategy:
+      matrix:
+        python:
+          - "3.9"
+          - "3.10"
+          - "3.11"
+          - "3.12"
+        platform:
+          - "ubuntu-latest"
+    steps:
+      - name: "Harden Runner"
+        uses: step-security/harden-runner@17d0e2bd7d51742c71671bd19fa12bdc9d40a3d6 # v2.8.1
+        with:
+          egress-policy: audit # TODO: change to 'egress-policy: block' after couple of runs
+
+      - name: "Checkout"
+        uses: actions/checkout@a5ac7e51b41094c92402da3b24376905380afc29 # v4.1.6
+        with:
+          fetch-depth: 0
+
+      - name: "Setup Python ${{ matrix.python }}"
+        uses: actions/setup-python@82c7e631bb3cdc910f68e0081d67478d79c6982d # v5.1.0
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: "Install tox"
+        run: |
+          python -m pip install --upgrade pip
+          python -m pip install tox tox-gh
+
+      - name: "Unit tests"
+        run: |
+          tox
diff --git a/.gitignore b/.gitignore
index 701ff28..7fd12a9 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,32 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# generated by setuptools_scm
+/src/instructlab/schema/_version.py
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
 # Environments
 .env
 .venv
@@ -11,5 +40,9 @@ venv.bak/
 .vscode/
 .idea/
 
+# Caches
+.tox/
+.*_cache/
+
 # Mac personalization files
 .DS_Store
diff --git a/README.md b/README.md
index 7756104..d5d5953 100644
--- a/README.md
+++ b/README.md
@@ -1,3 +1,5 @@
 # Taxonomy Schema
 
-This repository defines the JSON schema for the [Taxonomy](https://github.com/instructlab/taxonomy) YAML.
+This Python package defines the JSON schema for the InstructLab [Taxonomy](https://github.com/instructlab/taxonomy) YAML.
+
+Consumers of this schema can `pip install instructlab-schema`, and access the schema files using `importlib.resources` on the `instructlab.schema` package.
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..5a28a04
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,606 @@
+# SPDX-License-Identifier: Apache-2.0
+
+[build-system]
+requires = ["setuptools>=64", "setuptools_scm>=8"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "instructlab-schema"
+authors = [
+    { name="InstructLab", email="dev@instructlab.ai" },
+]
+description = "InstructLab Taxonomy Schema"
+readme = "README.md"
+license = {text = "Apache-2.0"}
+requires-python = ">=3.9"
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+]
+dynamic = ["dependencies", "optional-dependencies", "version"]
+
+[project.urls]
+homepage = "https://instructlab.ai"
+source = "https://github.com/instructlab/schema"
+issues = "https://github.com/instructlab/schema/issues"
+
+[tool.setuptools_scm]
+version_file = "src/instructlab/schema/_version.py"
+# do not include +gREV local version, required for Test PyPI upload
+local_scheme = "no-local-version"
+
+[tool.mypy]
+python_version = "3.9"
+exclude = ["^src/instructlab/schema/_version\\.py$"]
+
+[tool.ruff]
+src = ["src"]
+target-version = "py39"
+
+[tool.ruff.lint]
+select = [
+    "B",  # flake8-bugbear
+    "E",  # pycodestyle
+    "F",  # Pyflakes
+    "Q",  # flake8-quotes
+    "I",  # isort
+    "UP",  # pyupgrade
+    "SIM",  # flake8-simplify
+    "TID",  # flake8-tidy-imports
+]
+
+[tool.pylint.main]
+# Analyse import fallback blocks. This can be used to support both Python 2 and 3
+# compatible code, which means that the block might have code that exists only in
+# one or another interpreter, leading to false positives when analysed.
+# analyse-fallback-blocks =
+
+# Clear in-memory caches upon conclusion of linting. Useful if running pylint in
+# a server-like mode.
+# clear-cache-post-run =
+
+# Always return a 0 (non-error) status code, even if lint errors are found. This
+# is primarily useful in continuous integration scripts.
+# exit-zero =
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code.
+# extension-pkg-allow-list =
+
+# A comma-separated list of package or module names from where C extensions may
+# be loaded. Extensions are loading into the active Python interpreter and may
+# run arbitrary code. (This is an alternative name to extension-pkg-allow-list
+# for backward compatibility.)
+# extension-pkg-whitelist =
+
+# Return non-zero exit code if any of these messages/categories are detected,
+# even if score is above --fail-under value. Syntax same as enable. Messages
+# specified are enabled, while categories only check already-enabled messages.
+# fail-on =
+
+# Specify a score threshold under which the program will exit with error.
+fail-under = 10.0
+
+# Interpret the stdin as a python script, whose filename needs to be passed as
+# the module_or_package argument.
+# from-stdin =
+
+# Files or directories to be skipped. They should be base names, not paths.
+ignore = ["_version.py"]
+
+# Add files or directories matching the regular expressions patterns to the
+# ignore-list. The regex matches against paths and can be in Posix or Windows
+# format. Because '\\' represents the directory delimiter on Windows systems, it
+# can't be used as an escape character.
+# ignore-paths =
+
+# Files or directories matching the regular expression patterns are skipped. The
+# regex matches against base names, not paths. The default value ignores Emacs
+# file locks
+ignore-patterns = ["^\\.#"]
+
+# List of module names for which member attributes should not be checked and will
+# not be imported (useful for modules/projects where namespaces are manipulated
+# during runtime and thus existing member attributes cannot be deduced by static
+# analysis). It supports qualified module names, as well as Unix pattern
+# matching.
+# ignored-modules =
+
+# Python code to execute, usually for sys.path manipulation such as
+# pygtk.require().
+# init-hook =
+
+# Use multiple processes to speed up Pylint. Specifying 0 will auto-detect the
+# number of processors available to use, and will cap the count on Windows to
+# avoid hangs.
+jobs = 1
+
+# Control the amount of potential inferred values when inferring a single object.
+# This can help the performance when dealing with large functions or complex,
+# nested conditions.
+limit-inference-results = 100
+
+# List of plugins (as comma separated values of python module names) to load,
+# usually to register additional checkers.
+# load-plugins =
+
+# Pickle collected data for later comparisons.
+persistent = true
+
+# Resolve imports to .pyi stubs if available. May reduce no-member messages and
+# increase not-an-iterable messages.
+# prefer-stubs =
+
+# Minimum Python version to use for version dependent checks. Will default to the
+# version used to run pylint.
+py-version = "3.9"
+
+# Discover python modules and packages in the file system subtree.
+# recursive =
+
+# Add paths to the list of the source roots. Supports globbing patterns. The
+# source root is an absolute path or a path relative to the current working
+# directory used to determine a package namespace for modules located under the
+# source root.
+# source-roots =
+
+# When enabled, pylint would attempt to guess common misconfiguration and emit
+# user-friendly hints instead of false-positive error messages.
+suggestion-mode = true
+
+# Allow loading of arbitrary C extensions. Extensions are imported into the
+# active Python interpreter and may run arbitrary code.
+# unsafe-load-any-extension =
+
+[tool.pylint.basic]
+# Naming style matching correct argument names.
+argument-naming-style = "snake_case"
+
+# Regular expression matching correct argument names. Overrides argument-naming-
+# style. If left empty, argument names will be checked with the set naming style.
+# argument-rgx =
+
+# Naming style matching correct attribute names.
+attr-naming-style = "snake_case"
+
+# Regular expression matching correct attribute names. Overrides attr-naming-
+# style. If left empty, attribute names will be checked with the set naming
+# style.
+# attr-rgx =
+
+# Bad variable names which should always be refused, separated by a comma.
+bad-names = ["foo", "bar", "baz", "toto", "tutu", "tata"]
+
+# Bad variable names regexes, separated by a comma. If names match any regex,
+# they will always be refused
+# bad-names-rgxs =
+
+# Naming style matching correct class attribute names.
+class-attribute-naming-style = "any"
+
+# Regular expression matching correct class attribute names. Overrides class-
+# attribute-naming-style. If left empty, class attribute names will be checked
+# with the set naming style.
+# class-attribute-rgx =
+
+# Naming style matching correct class constant names.
+class-const-naming-style = "UPPER_CASE"
+
+# Regular expression matching correct class constant names. Overrides class-
+# const-naming-style. If left empty, class constant names will be checked with
+# the set naming style.
+# class-const-rgx =
+
+# Naming style matching correct class names.
+class-naming-style = "PascalCase"
+
+# Regular expression matching correct class names. Overrides class-naming-style.
+# If left empty, class names will be checked with the set naming style.
+# class-rgx =
+
+# Naming style matching correct constant names.
+const-naming-style = "UPPER_CASE"
+
+# Regular expression matching correct constant names. Overrides const-naming-
+# style. If left empty, constant names will be checked with the set naming style.
+# const-rgx =
+
+# Minimum line length for functions/classes that require docstrings, shorter ones
+# are exempt.
+docstring-min-length = -1
+
+# Naming style matching correct function names.
+function-naming-style = "snake_case"
+
+# Regular expression matching correct function names. Overrides function-naming-
+# style. If left empty, function names will be checked with the set naming style.
+# function-rgx =
+
+# Good variable names which should always be accepted, separated by a comma.
+good-names = ["i", "j", "k", "ex", "Run", "_"]
+
+# Good variable names regexes, separated by a comma. If names match any regex,
+# they will always be accepted
+# good-names-rgxs =
+
+# Include a hint for the correct naming format with invalid-name.
+# include-naming-hint =
+
+# Naming style matching correct inline iteration names.
+inlinevar-naming-style = "any"
+
+# Regular expression matching correct inline iteration names. Overrides
+# inlinevar-naming-style. If left empty, inline iteration names will be checked
+# with the set naming style.
+# inlinevar-rgx =
+
+# Naming style matching correct method names.
+method-naming-style = "snake_case"
+
+# Regular expression matching correct method names. Overrides method-naming-
+# style. If left empty, method names will be checked with the set naming style.
+# method-rgx =
+
+# Naming style matching correct module names.
+module-naming-style = "snake_case"
+
+# Regular expression matching correct module names. Overrides module-naming-
+# style. If left empty, module names will be checked with the set naming style.
+# module-rgx =
+
+# Colon-delimited sets of names that determine each other's naming style when the
+# name regexes allow several styles.
+# name-group =
+
+# Regular expression which should only match function or class names that do not
+# require a docstring.
+no-docstring-rgx = "^_"
+
+# List of decorators that produce properties, such as abc.abstractproperty. Add
+# to this list to register other decorators that produce valid properties. These
+# decorators are taken in consideration only for invalid-name.
+property-classes = ["abc.abstractproperty"]
+
+# Regular expression matching correct type alias names. If left empty, type alias
+# names will be checked with the set naming style.
+# typealias-rgx =
+
+# Regular expression matching correct type variable names. If left empty, type
+# variable names will be checked with the set naming style.
+# typevar-rgx =
+
+# Naming style matching correct variable names.
+variable-naming-style = "snake_case"
+
+# Regular expression matching correct variable names. Overrides variable-naming-
+# style. If left empty, variable names will be checked with the set naming style.
+# variable-rgx =
+
+[tool.pylint.classes]
+# Warn about protected attribute access inside special methods
+# check-protected-access-in-special-methods =
+
+# List of method names used to declare (i.e. assign) instance attributes.
+defining-attr-methods = ["__init__", "__new__", "setUp", "__post_init__"]
+
+# List of member names, which should be excluded from the protected access
+# warning.
+exclude-protected = ["_asdict", "_fields", "_replace", "_source", "_make"]
+
+# List of valid names for the first argument in a class method.
+valid-classmethod-first-arg = ["cls"]
+
+# List of valid names for the first argument in a metaclass class method.
+valid-metaclass-classmethod-first-arg = ["mcs"]
+
+[tool.pylint.design]
+# List of regular expressions of class ancestor names to ignore when counting
+# public methods (see R0903)
+# exclude-too-few-public-methods =
+
+# List of qualified class names to ignore when counting class parents (see R0901)
+# ignored-parents =
+
+# Maximum number of arguments for function / method.
+max-args = 5
+
+# Maximum number of attributes for a class (see R0902).
+max-attributes = 7
+
+# Maximum number of boolean expressions in an if statement (see R0916).
+max-bool-expr = 5
+
+# Maximum number of branch for function / method body.
+max-branches = 12
+
+# Maximum number of locals for function / method body.
+max-locals = 15
+
+# Maximum number of parents for a class (see R0901).
+max-parents = 7
+
+# Maximum number of public methods for a class (see R0904).
+max-public-methods = 20
+
+# Maximum number of return / yield for function / method body.
+max-returns = 6
+
+# Maximum number of statements in function / method body.
+max-statements = 50
+
+# Minimum number of public methods for a class (see R0903).
+min-public-methods = 2
+
+[tool.pylint.exceptions]
+# Exceptions that will emit a warning when caught.
+overgeneral-exceptions = ["builtins.BaseException", "builtins.Exception"]
+
+[tool.pylint.format]
+# Expected format of line ending, e.g. empty (any line ending), LF or CRLF.
+# expected-line-ending-format =
+
+# Regexp for a line that is allowed to be longer than the limit.
+ignore-long-lines = "^\\s*(# )?<?https?://\\S+>?$"
+
+# Number of spaces of indent required inside a hanging or continued line.
+indent-after-paren = 4
+
+# String used as indentation unit. This is usually "    " (4 spaces) or "\t" (1
+# tab).
+indent-string = "    "
+
+# Maximum number of characters on a single line.
+max-line-length = 100
+
+# Maximum number of lines in a module.
+max-module-lines = 1100
+
+# Allow the body of a class to be on the same line as the declaration if body
+# contains single statement.
+# single-line-class-stmt =
+
+# Allow the body of an if to be on the same line as the test if there is no else.
+# single-line-if-stmt =
+
+[tool.pylint.imports]
+# List of modules that can be imported at any level, not just the top level one.
+# allow-any-import-level =
+
+# Allow explicit reexports by alias from a package __init__.
+# allow-reexport-from-package =
+
+# Allow wildcard imports from modules that define __all__.
+# allow-wildcard-with-all =
+
+# Deprecated modules which should not be used, separated by a comma.
+# deprecated-modules =
+
+# Output a graph (.gv or any supported image format) of external dependencies to
+# the given file (report RP0402 must not be disabled).
+# ext-import-graph =
+
+# Output a graph (.gv or any supported image format) of all (i.e. internal and
+# external) dependencies to the given file (report RP0402 must not be disabled).
+# import-graph =
+
+# Output a graph (.gv or any supported image format) of internal dependencies to
+# the given file (report RP0402 must not be disabled).
+# int-import-graph =
+
+# Force import order to recognize a module as part of the standard compatibility
+# libraries.
+# known-standard-library =
+
+# Force import order to recognize a module as part of a third party library.
+known-third-party = ["enchant"]
+
+# Couples of modules and preferred modules, separated by a comma.
+# preferred-modules =
+
+[tool.pylint.logging]
+# The type of string formatting that logging methods do. `old` means using %
+# formatting, `new` is for `{}` formatting.
+logging-format-style = "old"
+
+# Logging modules to check that the string format arguments are in logging
+# function parameter format.
+logging-modules = ["logging"]
+
+[tool.pylint."messages control"]
+# Only show warnings with the listed confidence levels. Leave empty to show all.
+# Valid levels: HIGH, CONTROL_FLOW, INFERENCE, INFERENCE_FAILURE, UNDEFINED.
+confidence = ["HIGH", "CONTROL_FLOW", "INFERENCE", "INFERENCE_FAILURE", "UNDEFINED"]
+
+# Disable the message, report, category or checker with the given id(s). You can
+# either give multiple identifiers separated by comma (,) or put this option
+# multiple times (only on the command line, not in the configuration file where
+# it should appear only once). You can also use "--disable=all" to disable
+# everything first and then re-enable specific checks. For example, if you want
+# to run only the similarities checker, you can use "--disable=all
+# --enable=similarities". If you want to run only the classes checker, but have
+# no Warning level messages displayed, use "--disable=all --enable=classes
+# --disable=W".
+disable = ["raw-checker-failed", "bad-inline-option", "locally-disabled", "file-ignored", "suppressed-message", "useless-suppression", "deprecated-pragma", "use-symbolic-message-instead", "use-implicit-booleaness-not-comparison-to-string", "use-implicit-booleaness-not-comparison-to-zero", "invalid-name", "missing-class-docstring", "missing-module-docstring", "missing-function-docstring", "consider-using-f-string", "inconsistent-return-statements", "no-member", "too-many-arguments", "too-many-locals", "too-many-branches", "too-many-statements", "cyclic-import", "too-few-public-methods", "protected-access", "fixme", "logging-format-interpolation", "logging-too-many-args", "attribute-defined-outside-init", "abstract-method", "pointless-statement", "wrong-import-order", "line-too-long"]
+
+# Enable the message, report, category or checker with the given id(s). You can
+# either give multiple identifier separated by comma (,) or put this option
+# multiple time (only on the command line, not in the configuration file where it
+# should appear only once). See also the "--disable" option for examples.
+enable = ["c-extension-no-member"]
+
+[tool.pylint.method_args]
+# List of qualified names (i.e., library.method) which require a timeout
+# parameter e.g. 'requests.api.get,requests.api.post'
+timeout-methods = ["requests.api.delete", "requests.api.get", "requests.api.head", "requests.api.options", "requests.api.patch", "requests.api.post", "requests.api.put", "requests.api.request"]
+
+[tool.pylint.miscellaneous]
+# List of note tags to take in consideration, separated by a comma.
+notes = ["FIXME", "XXX", "TODO"]
+
+# Regular expression of note tags to take in consideration.
+# notes-rgx =
+
+[tool.pylint.refactoring]
+# Maximum number of nested blocks for function / method body
+max-nested-blocks = 5
+
+# Complete name of functions that never returns. When checking for inconsistent-
+# return-statements if a never returning function is called then it will be
+# considered as an explicit return statement and no message will be printed.
+never-returning-functions = ["sys.exit", "argparse.parse_error"]
+
+# Let 'consider-using-join' be raised when the separator to join on would be non-
+# empty (resulting in expected fixes of the type: ``"- " + " - ".join(items)``)
+suggest-join-with-non-empty-separator = true
+
+[tool.pylint.reports]
+# Python expression which should return a score less than or equal to 10. You
+# have access to the variables 'fatal', 'error', 'warning', 'refactor',
+# 'convention', and 'info' which contain the number of messages in each category,
+# as well as 'statement' which is the total number of statements analyzed. This
+# score is used by the global evaluation report (RP0004).
+evaluation = "max(0, 0 if fatal else 10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10))"
+
+# Template used to display messages. This is a python new-style format string
+# used to format the message information. See doc for all details.
+# msg-template =
+
+# Set the output format. Available formats are: text, parseable, colorized, json2
+# (improved json format), json (old json format) and msvs (visual studio). You
+# can also give a reporter class, e.g. mypackage.mymodule.MyReporterClass.
+# output-format =
+
+# Tells whether to display a full report or only the messages.
+reports = true
+
+# Activate the evaluation score.
+score = true
+
+[tool.pylint.similarities]
+# Comments are removed from the similarity computation
+ignore-comments = true
+
+# Docstrings are removed from the similarity computation
+ignore-docstrings = true
+
+# Imports are removed from the similarity computation
+ignore-imports = true
+
+# Signatures are removed from the similarity computation
+ignore-signatures = true
+
+# Minimum lines number of a similarity.
+min-similarity-lines = 4
+
+[tool.pylint.spelling]
+# Limits count of emitted suggestions for spelling mistakes.
+max-spelling-suggestions = 4
+
+# Spelling dictionary name. No available dictionaries : You need to install both
+# the python package and the system dependency for enchant to work.
+# spelling-dict =
+
+# List of comma separated words that should be considered directives if they
+# appear at the beginning of a comment and should not be checked.
+spelling-ignore-comment-directives = "fmt: on,fmt: off,noqa:,noqa,nosec,isort:skip,mypy:"
+
+# List of comma separated words that should not be checked.
+# spelling-ignore-words =
+
+# A path to a file that contains the private dictionary; one word per line.
+# spelling-private-dict-file =
+
+# Tells whether to store unknown words to the private dictionary (see the
+# --spelling-private-dict-file option) instead of raising a message.
+# spelling-store-unknown-words =
+
+[tool.pylint.typecheck]
+# List of decorators that produce context managers, such as
+# contextlib.contextmanager. Add to this list to register other decorators that
+# produce valid context managers.
+contextmanager-decorators = ["contextlib.contextmanager"]
+
+# List of members which are set dynamically and missed by pylint inference
+# system, and so shouldn't trigger E1101 when accessed. Python regular
+# expressions are accepted.
+# generated-members =
+
+# Tells whether missing members accessed in mixin class should be ignored. A
+# class is considered mixin if its name matches the mixin-class-rgx option.
+# Tells whether to warn about missing members when the owner of the attribute is
+# inferred to be None.
+ignore-none = true
+
+# This flag controls whether pylint should warn about no-member and similar
+# checks whenever an opaque object is returned when inferring. The inference can
+# return multiple potential results while evaluating a Python object, but some
+# branches might not be evaluated, which results in partial inference. In that
+# case, it might be useful to still emit no-member and other checks for the rest
+# of the inferred objects.
+ignore-on-opaque-inference = true
+
+# List of symbolic message names to ignore for Mixin members.
+ignored-checks-for-mixins = ["no-member", "not-async-context-manager", "not-context-manager", "attribute-defined-outside-init"]
+
+# List of class names for which member attributes should not be checked (useful
+# for classes with dynamically set attributes). This supports the use of
+# qualified names.
+ignored-classes = ["optparse.Values", "thread._local", "_thread._local", "argparse.Namespace"]
+
+# Show a hint with possible names when a member name was not found. The aspect of
+# finding the hint is based on edit distance.
+missing-member-hint = true
+
+# The minimum edit distance a name should have in order to be considered a
+# similar match for a missing member name.
+missing-member-hint-distance = 1
+
+# The total number of similar names that should be taken in consideration when
+# showing a hint for a missing member.
+missing-member-max-choices = 1
+
+# Regex pattern to define which classes are considered mixins.
+mixin-class-rgx = ".*[Mm]ixin"
+
+# List of decorators that change the signature of a decorated function.
+# signature-mutators =
+
+[tool.pylint.variables]
+# List of additional names supposed to be defined in builtins. Remember that you
+# should avoid defining new builtins when possible.
+# additional-builtins =
+
+# Tells whether unused global variables should be treated as a violation.
+allow-global-unused-variables = true
+
+# List of names allowed to shadow builtins
+# allowed-redefined-builtins =
+
+# List of strings which can identify a callback function by name. A callback name
+# must start or end with one of those strings.
+callbacks = ["cb_", "_cb"]
+
+# A regular expression matching the name of dummy variables (i.e. expected to not
+# be used).
+dummy-variables-rgx = "_+$|(_[a-zA-Z0-9_]*[a-zA-Z0-9]+?$)|dummy|^ignored_|^unused_"
+
+# Argument names that match this expression will be ignored.
+ignored-argument-names = "_.*|^ignored_|^unused_"
+
+# Tells whether we should check for unused import in __init__ files.
+# init-import =
+
+# List of qualified module names which can have objects that can redefine
+# builtins.
+redefining-builtins-modules = ["six.moves", "past.builtins", "future.builtins", "builtins", "io"]
+
+
+
diff --git a/scripts/ruff.sh b/scripts/ruff.sh
new file mode 100755
index 0000000..6bf131f
--- /dev/null
+++ b/scripts/ruff.sh
@@ -0,0 +1,50 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: Apache-2.0
+set -e
+
+# wrapper to combine ruff check and ruff format
+#
+# "ruff.sh fix" runs fixes and reformats the code
+# "ruff.sh check" checks style, format, and imports
+# "ruff.sh <args>" passes abitrary args to ruff
+
+if [ -z "$1" ]; then
+    echo "USAGE: $0 [check|fix|<args>]" >&2
+    exit 2
+fi
+
+run() {
+    declare -i err
+
+    echo "RUN: '$*'"
+    "$@"
+    err=$?
+    echo
+    return $err
+}
+
+case $1 in
+    "check")
+        declare -i exitcode=0
+
+        set +e
+        run ruff check --diff
+        exitcode=$(( exitcode + $? ))
+
+        run ruff format --check
+        exitcode=$(( exitcode + $? ))
+        set -e
+
+        if [ $exitcode -ne 0 ]; then
+            echo "ERROR: one or more checks have failed." >&2
+            echo "Run 'tox -e ruff' to auto-correct all fixable errors." >&2
+            exit 3
+        fi
+        ;;
+    "fix")
+        run ruff check --fix
+        run ruff format
+        ;;
+    *)
+        ruff "$@"
+esac
diff --git a/src/instructlab/schema/__init__.py b/src/instructlab/schema/__init__.py
new file mode 100644
index 0000000..5ac6fdc
--- /dev/null
+++ b/src/instructlab/schema/__init__.py
@@ -0,0 +1,25 @@
+"""InstructLab Taxonomy Schema"""
+
+# Standard
+from importlib import resources
+
+try:
+    from importlib.resources.abc import Traversable  # type: ignore[import-not-found]
+except ImportError:  # python>=3.9,<3.11
+    from importlib.abc import Traversable
+
+__all__ = ["schema_versions"]
+
+
+def schema_versions() -> list[Traversable]:
+    """Return the sorted list of schema versions.
+
+    Returns:
+        list[Traversable]: A sorted list of schema versions.
+    """
+    schema_base = resources.files(__package__)
+    versions = sorted(
+        (v for v in schema_base.iterdir() if v.name[0] == "v" and v.name[1:].isdigit()),
+        key=lambda k: int(k.name[1:]),
+    )
+    return versions
diff --git a/src/instructlab/schema/py.typed b/src/instructlab/schema/py.typed
new file mode 100644
index 0000000..e69de29
diff --git a/src/instructlab/schema/v1/__init__.py b/src/instructlab/schema/v1/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/v1/compositional_skills.json b/src/instructlab/schema/v1/compositional_skills.json
similarity index 100%
rename from v1/compositional_skills.json
rename to src/instructlab/schema/v1/compositional_skills.json
diff --git a/v1/knowledge.json b/src/instructlab/schema/v1/knowledge.json
similarity index 100%
rename from v1/knowledge.json
rename to src/instructlab/schema/v1/knowledge.json
diff --git a/v1/version.json b/src/instructlab/schema/v1/version.json
similarity index 100%
rename from v1/version.json
rename to src/instructlab/schema/v1/version.json
diff --git a/src/instructlab/schema/v2/__init__.py b/src/instructlab/schema/v2/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/v2/compositional_skills.json b/src/instructlab/schema/v2/compositional_skills.json
similarity index 100%
rename from v2/compositional_skills.json
rename to src/instructlab/schema/v2/compositional_skills.json
diff --git a/v2/knowledge.json b/src/instructlab/schema/v2/knowledge.json
similarity index 100%
rename from v2/knowledge.json
rename to src/instructlab/schema/v2/knowledge.json
diff --git a/v2/version.json b/src/instructlab/schema/v2/version.json
similarity index 100%
rename from v2/version.json
rename to src/instructlab/schema/v2/version.json
diff --git a/tests/test_versions.py b/tests/test_versions.py
new file mode 100644
index 0000000..ed08865
--- /dev/null
+++ b/tests/test_versions.py
@@ -0,0 +1,48 @@
+# SPDX-License-Identifier: Apache-2.0
+
+# Standard
+import json
+from importlib import resources
+
+# Third Party
+from referencing import Resource
+from referencing.jsonschema import DRAFT202012
+
+from instructlab.schema import schema_versions
+
+
+class TestVersions:
+    def test_versions(self):
+        versions = schema_versions()
+        assert versions is not None
+        assert len(versions) > 1
+        for i, v in enumerate(versions):
+            assert v.name == f"v{i+1}"
+
+    def _load_schema(self, path):
+        text = path.read_text(encoding="utf-8")
+        assert text
+        assert len(text) > 1
+        contents = json.loads(text)
+        assert contents
+        assert len(contents) > 1
+        resource = Resource.from_contents(
+            contents=contents, default_specification=DRAFT202012
+        )
+        assert resource
+        assert resource.contents == contents
+
+    def test_import_schema_base(self):
+        schema_base = resources.files("instructlab.schema")
+        for i in range(len(schema_versions())):
+            schema_version = schema_base.joinpath(f"v{i+1}")
+            for schema_name in ("compositional_skills", "knowledge", "version"):
+                path = schema_version.joinpath(f"{schema_name}.json")
+                self._load_schema(path)
+
+    def test_import_schema_versions(self):
+        for i in range(len(schema_versions())):
+            schema_version = resources.files(f"instructlab.schema.v{i+1}")
+            for schema_name in ("compositional_skills", "knowledge", "version"):
+                path = schema_version.joinpath(f"{schema_name}.json")
+                self._load_schema(path)
diff --git a/tox.ini b/tox.ini
new file mode 100644
index 0000000..91da27e
--- /dev/null
+++ b/tox.ini
@@ -0,0 +1,64 @@
+# SPDX-License-Identifier: Apache-2.0
+
+[tox]
+# py3-unit runs unit tests with 'python3'
+# py311-unit runs the same tests with 'python3.11'
+envlist = ruff, pylint, mypy, jsonschema, py3-unit
+minversion = 4.4
+
+[testenv]
+description = Run tests (unit)
+package = wheel
+wheel_build_env = pkg
+deps =
+    pytest
+    jsonschema
+commands =
+    unit: {envpython} -m pytest {posargs:tests}
+
+[testenv:pylint]
+description = Lint with pylint
+deps =
+    pylint
+    pylint-pydantic
+    jsonschema
+commands =
+    {envpython} -m pylint --load-plugins pylint_pydantic {posargs:src/instructlab/schema/ tests/}
+
+[testenv:ruff]
+description = Reformat and fix code with Ruff
+skip_install = True
+skipsdist = true
+deps =
+    ruff
+    jsonschema
+commands =
+    ./scripts/ruff.sh {posargs:fix}
+allowlist_externals = ./scripts/ruff.sh
+
+[testenv:mypy]
+description = Python type checking with mypy
+namespace_packages = True
+explicit_package_bases = True
+deps =
+    mypy
+    jsonschema
+commands =
+    {envpython} -m mypy {posargs:src tests}
+
+[testenv:jsonschema]
+description = JSON schema file validation with check-jsonschema
+skip_install = True
+skipsdist = true
+deps =
+    check-jsonschema
+commands =
+    bash -c "{envpython} -m check_jsonschema --verbose --schemafile https://json-schema.org/draft/2020-12/schema {posargs:$(find src/instructlab/schema/v* -name \"*.json\" -print)}"
+allowlist_externals = bash
+
+[gh]
+python =
+    3.12 = py312-unit
+    3.11 = py311-unit
+    3.10 = py310-unit
+    3.9 = py39-unit