mirror of
https://github.com/davila7/claude-code-templates.git
synced 2026-09-19 01:30:23 +08:00
054c0e56e9
Removed the deprecated 'model: sonnet' field from command frontmatter to fix compatibility issues with Claude Code. Commands will now inherit the model from the active conversation instead of using a hardcoded deprecated model identifier. Changes: - Removed 'model: sonnet' from 142 command files across all categories - Commands now use default model inheritance behavior - Preserved 'model: claude-sonnet-4-5-20250929' in gemini-review.md (valid model) - 67 commands without model field remain unchanged This resolves the "model: sonnet not found" error reported in GitHub issues and aligns with Claude Code's recommended practice of letting commands inherit the conversation model. Affected categories: - Database/Supabase commands (8 files) - Documentation commands (8 files) - Deployment commands (11 files) - Setup commands (14 files) - Performance commands (8 files) - Team commands (14 files) - Security commands (6 files) - NextJS/Vercel commands (10 files) - Sync commands (14 files) - And more across other categories 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
2.0 KiB
2.0 KiB
allowed-tools: Read, Write, Edit, Bash
argument-hint: [pr-number] | --team | --estimate | --batch-process | --auto-create
description: Create Linear tasks from GitHub pull requests with intelligent content extraction and task sizing
Task from PR
Create Linear tasks from GitHub pull requests with intelligent analysis: $ARGUMENTS
Current PR Environment
- Repository: !
gh repo view --json nameWithOwner -q .nameWithOwner 2>/dev/null || echo "No repo context" - PR status: Based on $ARGUMENTS PR number or batch processing criteria
- Linear teams: Available teams for task assignment
- User mappings: GitHub username to Linear user correspondence
Task
Generate Linear tasks from GitHub pull requests with comprehensive content analysis:
PR Source: Use $ARGUMENTS to specify PR number, team assignment, size estimation, or batch processing mode
Task Generation Framework:
- PR Analysis - Extract comprehensive PR data, parse description structure, identify key components, analyze changes
- Content Extraction - Parse structured sections, extract checklists, identify technical details, capture requirements
- Intelligent Sizing - Estimate task complexity from code changes, file count, review comments, testing requirements
- Task Construction - Build Linear task with proper formatting, preserve PR context, maintain references, structure content
- Team Assignment - Map to appropriate Linear team, assign based on code areas, set priorities from labels
- Validation & Creation - Check for duplicates, validate task structure, create in Linear, establish bidirectional links
Advanced Features: Smart content parsing, automated size estimation, intelligent team mapping, comprehensive validation, batch processing.
Quality Assurance: Duplicate detection, content validation, proper formatting, relationship maintenance, comprehensive error handling.
Output: Successfully created Linear tasks with comprehensive PR context, accurate sizing estimates, proper team assignments, and complete bidirectional linking.