fix(ci): simplify to v1 with built-in slash command support

Based on maintainer feedback:
- Move commands directly to .claude/commands/ (no symlinks needed)
- Use v1 with minimal configuration (auto mode detection)
- Remove unnecessary parameters (mode, use_sticky_comment, etc.)
- v1 automatically finds commands in .claude/commands/

Author: zealoushacker

.claude/commands/link-review.md

@@ -0,0 +1,30 @@
+---
+description: Review links in changed files for quality and security issues
+---
+
+Review the links in the changed files and check for potential issues:
+
+## Link Quality Checks
+1. **Broken Links**: Identify any links that might be broken or malformed
+2. **Outdated Links**: Check for links to deprecated resources or old documentation
+3. **Security**: Ensure no links to suspicious or potentially harmful sites
+4. **Best Practices**: 
+   - Links should use HTTPS where possible
+   - Internal links should use relative paths
+   - External links should be to stable, reputable sources
+
+## Specific Checks for Anthropic Content
+- Links to Claude documentation should point to the latest versions
+- API documentation links should be current
+- Model documentation should reference current models, not deprecated ones
+- GitHub links should use the correct repository paths
+
+## Report Format
+Provide a clear summary with:
+- ✅ Valid and well-formed links
+- ⚠️ Links that might need attention (e.g., HTTP instead of HTTPS)
+- ❌ Broken or problematic links that must be fixed
+
+If all links look good, provide a brief confirmation.
+
+Format your response as a helpful PR review comment.

.claude/commands/link-review.md

@@ -0,0 +1,16 @@
+---
+description: Validate Claude model usage against current public models
+---
+
+Review the changed files for Claude model usage.
+
+First, fetch the current list of allowed models from:
+https://docs.anthropic.com/en/docs/about-claude/models/overview.md
+
+Then check:
+1. All model references are from the current public models list
+2. Flag any deprecated models (older Sonnet 3.5, Opus 3 versions)
+3. Flag any internal/non-public model names
+4. Suggest using aliases ending in -latest for better maintainability
+
+Provide clear, actionable feedback on any issues found.

.claude/commands/model-check.md

@@ -0,0 +1,43 @@
+---
+description: Comprehensive review of Jupyter notebooks and Python scripts
+---
+
+Review the changes to Jupyter notebooks and Python scripts in this PR. Please check for:
+
+## Model Usage
+Verify all Claude model references against the current list at:
+https://docs.anthropic.com/en/docs/about-claude/models/overview.md
+- Flag any deprecated models (older Sonnet 3.5, Opus 3 versions)
+- Flag any internal/non-public model names
+- Suggest current alternatives when issues found
+- Recommend aliases ending in -latest for stability
+
+## Code Quality
+- Python code follows PEP 8 conventions
+- Proper error handling
+- Clear variable names and documentation
+- No hardcoded API keys (use os.getenv("ANTHROPIC_API_KEY"))
+
+## Notebook Structure
+- Clear introduction explaining what the notebook demonstrates and why it's useful
+- Configuration instructions (how to set up API keys, install dependencies, etc.)
+- Connecting explanations between cells that help users understand the flow
+- Clear markdown explanations between code cells
+- Logical flow from simple to complex
+- Outputs preserved for educational value
+- Dependencies properly imported
+
+## Security
+- Check for any hardcoded API keys or secrets (not just Anthropic keys)
+- Ensure all sensitive credentials use environment variables (os.environ, getenv, etc.)
+- Flag any potential secret patterns (tokens, passwords, private keys)
+- Note: Educational examples showing "what not to do" are acceptable if clearly marked
+- Safe handling of user inputs
+- Appropriate use of environment variables
+
+Provide a clear summary with:
+- ✅ What looks good
+- ⚠️ Suggestions for improvement
+- ❌ Critical issues that must be fixed
+
+Format your response as a helpful PR review comment.

.claude/commands/model-check.md

@@ -23,13 +23,8 @@ jobs:
           fetch-depth: 0
 
       - name: Run Claude Link Review
-        uses: anthropics/claude-code-action@beta
+        uses: anthropics/claude-code-action@v1
         with:
-          mode: agent
-          use_sticky_comment: true
           anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
           github_token: ${{ secrets.GITHUB_TOKEN }}
-          timeout_minutes: "30"
-          allowed_bots: "*"
-          experimental_slash_commands_dir: ${{ github.workspace }}/.github/slash-commands
           prompt: "/link-review"