feat: transform awesome-data-engineering into definitive 2024-2025 resource

.github/ISSUE_TEMPLATE/add-tool.yml

@@ -0,0 +1,89 @@
+name: Add New Tool
+description: Suggest a new data engineering tool to be added to the list
+title: "[ADD] "
+labels: ["enhancement", "new-tool"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for suggesting a new tool! Please provide the following information to help us evaluate your suggestion.
+
+  - type: input
+    id: tool-name
+    attributes:
+      label: Tool Name
+      description: What is the name of the tool?
+      placeholder: ex. Apache Spark
+    validations:
+      required: true
+
+  - type: input
+    id: tool-url
+    attributes:
+      label: Tool URL
+      description: Official website or repository URL
+      placeholder: https://spark.apache.org/
+    validations:
+      required: true
+
+  - type: dropdown
+    id: category
+    attributes:
+      label: Category
+      description: Which category does this tool belong to?
+      options:
+        - Data Ingestion
+        - Data Storage
+        - Data Transformation
+        - Orchestration & Workflow
+        - Stream Processing
+        - Batch Processing
+        - Data Quality & Observability
+        - Data Discovery & Governance
+        - Reverse ETL
+        - Analytics & Visualization
+        - AI/ML & LLM Infrastructure
+        - Infrastructure & Deployment
+        - Other (specify in description)
+    validations:
+      required: true
+
+  - type: textarea
+    id: description
+    attributes:
+      label: Tool Description
+      description: Provide a one-sentence description (under 100 characters)
+      placeholder: "Unified analytics engine for large-scale data processing with SQL, streaming, ML, and graph capabilities."
+    validations:
+      required: true
+
+  - type: textarea
+    id: rationale
+    attributes:
+      label: Why should this tool be included?
+      description: |
+        Explain why this tool deserves to be on the list:
+        - Is it production-ready and actively maintained?
+        - Is it used by known companies at scale?
+        - Does it solve a problem not addressed by existing entries?
+      placeholder: |
+        - Used by 80% of Fortune 500 companies
+        - Active development with releases every 2 months
+        - Provides unique capabilities for X use case
+    validations:
+      required: true
+
+  - type: checkboxes
+    id: checklist
+    attributes:
+      label: Submission Checklist
+      description: Please confirm the following
+      options:
+        - label: The tool is production-ready and actively maintained
+          required: true
+        - label: I have checked that this tool is not already listed
+          required: true
+        - label: The tool has real-world production usage
+          required: true
+        - label: I have read the [contribution guidelines](../contributing.md)
+          required: true

.github/ISSUE_TEMPLATE/broken-link.yml

@@ -0,0 +1,53 @@
+name: Report Broken Link
+description: Report a broken or outdated link
+title: "[BROKEN LINK] "
+labels: ["broken-link", "bug"]
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for helping us maintain quality links!
+
+  - type: input
+    id: broken-url
+    attributes:
+      label: Broken URL
+      description: What is the broken link?
+      placeholder: https://example.com/tool
+    validations:
+      required: true
+
+  - type: input
+    id: tool-name
+    attributes:
+      label: Tool/Resource Name
+      description: What tool or resource does this link belong to?
+      placeholder: Apache Kafka
+    validations:
+      required: true
+
+  - type: dropdown
+    id: issue-type
+    attributes:
+      label: Issue Type
+      options:
+        - 404 - Page not found
+        - 500 - Server error
+        - Timeout - Site not responding
+        - Moved - URL has changed
+        - Other
+    validations:
+      required: true
+
+  - type: input
+    id: suggested-url
+    attributes:
+      label: Suggested Replacement URL (if known)
+      description: If you know the new URL, please provide it
+      placeholder: https://new-url.com
+
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: Additional Context
+      description: Any other information that might help

.github/ISSUE_TEMPLATE/update-tool.yml

@@ -0,0 +1,57 @@
+name: Update Existing Tool
+description: Suggest updates to an existing tool entry
+title: "[UPDATE] "
+labels: ["update"]
+body:
+  - type: input
+    id: tool-name
+    attributes:
+      label: Tool Name
+      description: Which tool needs updating?
+      placeholder: ex. dbt
+    validations:
+      required: true
+
+  - type: dropdown
+    id: update-type
+    attributes:
+      label: Update Type
+      description: What kind of update is needed?
+      options:
+        - Description update
+        - URL change
+        - Category change
+        - Add sub-tool/related project
+        - Remove deprecated tool
+        - Other
+    validations:
+      required: true
+
+  - type: textarea
+    id: current-entry
+    attributes:
+      label: Current Entry
+      description: Copy the current entry from README
+      placeholder: |
+        * [Tool](url) - Current description
+    validations:
+      required: true
+
+  - type: textarea
+    id: proposed-change
+    attributes:
+      label: Proposed Change
+      description: What should it be changed to?
+      placeholder: |
+        * [Tool](new-url) - Updated description
+    validations:
+      required: true
+
+  - type: textarea
+    id: rationale
+    attributes:
+      label: Rationale
+      description: Why is this update necessary?
+      placeholder: The tool was acquired, URL changed, new features added, etc.
+    validations:
+      required: true

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,58 @@
+# Pull Request
+
+## Description
+
+<!-- Provide a clear description of what this PR does -->
+
+## Type of Change
+
+<!-- Check all that apply -->
+
+- [ ] Add new tool(s)
+- [ ] Update existing tool(s)
+- [ ] Fix broken link(s)
+- [ ] Update documentation
+- [ ] Fix typo/formatting
+- [ ] Remove deprecated tool(s)
+
+## Checklist
+
+<!-- Make sure you've completed all items before submitting -->
+
+### General
+- [ ] I have read the [contribution guidelines](../contributing.md)
+- [ ] My PR follows the project's formatting standards
+- [ ] I have checked that no similar PR exists
+
+### For New Tools
+- [ ] Tool is actively maintained (commits within last 6 months)
+- [ ] Tool is production-ready and used at scale
+- [ ] Tool solves a problem not addressed by existing entries
+- [ ] Description is clear, concise, and actionable (< 100 characters)
+- [ ] Link uses HTTPS where available
+- [ ] Link points to official source (not third-party)
+- [ ] Tool is placed in the correct category and subcategory
+- [ ] Tool is added to the **bottom** of the appropriate subcategory
+
+### For Updates
+- [ ] Changes accurately reflect current state of the tool
+- [ ] Links have been verified and are working
+- [ ] Description improvements are factually correct
+
+### For Link Fixes
+- [ ] New URL has been verified and tested
+- [ ] New URL points to official source
+
+## Additional Context
+
+<!-- Add any additional information, screenshots, or context here -->
+
+## Related Issues
+
+<!-- Reference any related issues using #issue_number -->
+
+Closes #
+
+---
+
+**Thank you for contributing to Awesome Data Engineering!** 🚀

.github/workflows/link-check.yml

@@ -0,0 +1,62 @@
+name: Check Links
+
+on:
+  schedule:
+    # Run weekly on Mondays at 9am UTC
+    - cron: '0 9 * * 1'
+  workflow_dispatch:
+  pull_request:
+    paths:
+      - 'README.md'
+      - 'contributing.md'
+
+jobs:
+  link-check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Check links in README
+        uses: lycheeverse/lychee-action@v1
+        with:
+          files: README.md contributing.md
+          args: '--verbose --no-progress --exclude-mail --exclude twitter.com --exclude linkedin.com --max-retries 3 --timeout 20'
+          fail: true
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Create issue if links are broken
+        if: failure()
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const title = '🔗 Broken Links Detected';
+            const body = `Automated link checking has detected broken links in the repository.
+
+            Please review the [workflow run](${context.payload.repository.html_url}/actions/runs/${context.runId}) for details.
+
+            Common causes:
+            - Website temporarily down
+            - URL changed/deprecated
+            - Typo in URL
+
+            Action required: Update or remove broken links.`;
+
+            // Check if issue already exists
+            const issues = await github.rest.issues.listForRepo({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              state: 'open',
+              labels: ['broken-links']
+            });
+
+            if (issues.data.length === 0) {
+              await github.rest.issues.create({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                title: title,
+                body: body,
+                labels: ['broken-links', 'automated']
+              });
+            }

.github/workflows/markdown-lint.yml

@@ -0,0 +1,28 @@
+name: Markdown Lint
+
+on:
+  pull_request:
+    paths:
+      - '**.md'
+  push:
+    branches:
+      - main
+      - master
+    paths:
+      - '**.md'
+
+jobs:
+  markdown-lint:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Lint markdown files
+        uses: DavidAnson/markdownlint-cli2-action@v15
+        with:
+          globs: '**/*.md'
+          config: '.markdownlint.json'
+
+      - name: Check awesome list
+        uses: max/awesome-lint@v2

.markdownlint.json

@@ -0,0 +1,11 @@
+{
+  "default": true,
+  "MD001": true,
+  "MD003": { "style": "atx" },
+  "MD004": { "style": "dash" },
+  "MD007": { "indent": 2 },
+  "MD013": false,
+  "MD024": { "siblings_only": true },
+  "MD033": false,
+  "MD041": false
+}