Codebase explorer agent, deadline countdown statusline, change logger
hook, deadline prep skill, commit smart skill, and test detect skill.
Designed for rapid onboarding on unfamiliar codebases with time pressure.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Opens a 3-panel Ghostty layout (Claude | lazygit / yazi) when creating
worktrees in sibling directories. Handles both WorktreeCreate and
WorktreeRemove events with a single companion script.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
The installer (`installIndividualHook` in index.js) places companion
Python scripts in `.claude/hooks/`, but the hook config referenced
`.claude/scripts/`. This meant the hook would always fail with a
"file not found" error at runtime, silently rendering it non-functional.
Also removed the `2>&1` stderr redirect which masked the error by
merging stderr into stdout, causing the hook runner to report the
unhelpful "No stderr output" message instead of the actual cause.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Add AI-powered football match predictions for Premier League and Champions League.
Includes remote MCP endpoint integration and bash skill wrapper with team filtering.
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
New global setting to display custom announcements in Claude Code.
Users can replace the example messages with their own org announcements.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
New global setting to customize Claude Code spinner tips with custom messages.
Users can replace the default tips array and toggle excludeDefault.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Adds DevPlan - an MCP server for generating Haiku-executable
development plans with validation, lessons learned, and
issue remediation workflows.
- 21 tools for planning, generation, validation, and analytics
- SSE transport via Cloudflare Workers
- Website: devplanmcp.store
Co-authored-by: Radarr O'Really <radarroreally@gmail.com>
* feat: Add Telegram Bot Builder skill with complete Bot API v9.4 reference
Comprehensive skill for building Telegram bots covering Node.js and Python
ecosystems with production-ready patterns, 100+ API methods, 200+ types,
and deployment guides.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: Update components.json with telegram-bot-builder skill
Regenerated components catalog via generate_components_json.py.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Complete skill for building MCP servers with FastMCP 3.0 covering tools,
resources, authentication, providers, middleware, and deployment.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Previously used endpoints[0] which could return the wrong branch's
compute (e.g., development/idle instead of production/active).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
New skill that generates production-ready GitHub Actions workflows for any
language or framework. Includes project auto-detection, security best practices,
and 15+ ready-to-use templates (CI, deploy, Docker, release, security scanning).
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Added 21 new skills from https://github.com/openai/skills:
Development (6):
- cloudflare-deploy: Deploy to Cloudflare Workers, Pages, and platform services
- netlify-deploy: Deploy web projects to Netlify with CLI
- render-deploy: Deploy applications to Render with Blueprint generation
- vercel-deploy: Deploy applications and websites to Vercel
- playwright: Automate browsers with Playwright CLI
- jupyter-notebook: Create and edit Jupyter notebooks for data analysis
AI Research (1):
- openai-docs: Access OpenAI developer documentation via MCP
Creative Design (4):
- figma: Fetch Figma design context and translate to code via MCP
- figma-implement-design: Implement Figma designs in production code
- imagegen: Generate images using OpenAI's image generation API
- develop-web-game: Develop web-based games
Document Processing (2):
- doc: Work with document files and formats
- spreadsheet: Work with spreadsheet files and data
Security (3):
- security-best-practices: Language-specific security review and guidance
- security-ownership-map: Map security ownership and responsibilities
- security-threat-model: Perform security threat modeling
Media (3):
- screenshot: Capture desktop and application screenshots
- speech: Generate speech using OpenAI's speech API
- transcribe: Transcribe audio using OpenAI's transcription API
Video (1):
- sora: Generate and manage videos using OpenAI's Sora API
Workflow Automation (1):
- yeet: Quick git workflow automation (stage, commit, push, PR)
All skills validated and include author: openai metadata.
Skipped 11 duplicates already in the project.
Regenerated catalog: 663 total skills
https://claude.ai/code/session_01Rmh2xrBZ36jHWDUCnnq6UX
Co-authored-by: Claude <noreply@anthropic.com>
Hook that sends Telegram notification when a new PR is created via
`gh pr create`, including the PR URL and Vercel preview URL.
Files added:
- cli-tool/components/hooks/automation/telegram-pr-webhook.json (component)
- cli-tool/components/hooks/automation/telegram-pr-webhook.py (component script)
- .claude/settings.json (project hook config)
- .claude/hooks/telegram-pr-webhook.py (project hook script)
- .gitignore updated to track the hook script
Uses TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID environment variables.
https://claude.ai/code/session_013aBUK67VEy9Q2MaUGUVRJQ
Co-authored-by: Claude <noreply@anthropic.com>
This commit introduces a comprehensive Technical Debt Manager agent that
systematically identifies, quantifies, and prioritizes technical debt
across 7 categories: code quality, test coverage, documentation,
dependencies, design, infrastructure, and performance.
Key Features:
- Comprehensive debt detection using industry-standard tools and metrics
- Quantitative prioritization via Fowler's Technical Debt Quadrant
- Sprint-ready work items with effort estimates and ROI analysis
- Automated workflow integration (CI/CD, PR templates, quality gates)
- Stakeholder-specific communication guidelines
- Real-world examples and actionable deliverables
Technical Details:
- Category: development-tools (complements code-reviewer, dx-optimizer)
- Model: sonnet (balanced performance for complex analysis)
- Tools: Read, Grep, Bash, TodoWrite, WebFetch
- Size: 502 lines, comprehensive documentation
Research Foundation:
- Martin Fowler's Technical Debt frameworks
- SonarQube code quality patterns
- OWASP security standards
- Industry best practices for debt management
Expected Impact:
- 30% reduction in bugs from high-debt modules
- 2 days saved per sprint on debugging
- 15-25% velocity increase after debt reduction
- Data-driven prioritization for engineering teams
This agent addresses a critical gap identified through analysis of 156
existing agents - no current agent provides systematic technical debt
management with quantitative prioritization and actionable roadmaps.
Follows all contribution guidelines from CONTRIBUTING.md with proper
YAML frontmatter, comprehensive sections, and real-world examples.
Co-authored-by: tonightlife <tonightlife@users.noreply.github.com>
Co-authored-by: Claude Code <claude@anthropic.com>
- Update description to list 30+ supported providers
- Simplify hook command by removing git commit grep filter
- Parse Claude Code JSON input from stdin to detect git commit
- Handle git commit -a and chained git add && git commit scenarios
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* feat: Add roier-seo skill for technical SEO auditing
Add a new skill for technical SEO auditing and automatic fixing:
- Lighthouse/PageSpeed audit integration (localhost and live URLs)
- 50+ SEO fix patterns for meta tags, structured data, accessibility
- Framework support for Next.js, React, Vue, Nuxt
- Core Web Vitals tracking and optimization
- WCAG accessibility compliance fixes
- JSON-LD structured data schemas
Includes audit scripts that require Node.js 18+ and Chrome/Chromium.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: Address cubic code review feedback
- Use stderr for status logs to avoid polluting JSON output (P2)
- Fix Chrome cleanup on error by deferring process.exit until after finally (P2)
- Add Node.js 18+ version check for native fetch support (P1)
- Add engines field to package.json
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* Add BettorEdge Value Finder agent
- Find +EV betting opportunities on BettorEdge prediction markets
- Kelly criterion bet sizing with quarter-Kelly default
- Built-in bankroll management (max bet %, daily stop-loss, exposure limits)
- MCP server for Claude Desktop and Claude Code
- npm package: bettoredge-value-finder
Co-Authored-By: Claude <noreply@anthropic.com>
* Update API access email to support@bettoredge.com
---------
Co-authored-by: gregs_coding <greg.kajewski@bettoredge.com>
Co-authored-by: Claude <noreply@anthropic.com>
Added two new programmatic video creation skills similar to Remotion:
- Motion Canvas: TypeScript framework for creating animated videos using generator functions, signals, and real-time preview editor
- Manim: Python framework for creating mathematical animations and educational videos (popularized by 3Blue1Brown)
Both skills include:
- Comprehensive SKILL.md with usage examples
- Reference documentation for core concepts
- Best practices and quick start guides
- Links to official documentation
Updated components catalog with new skills.
https://claude.ai/code/session_01RDZmhhTHKZzAEh9rJRzJjD
Co-authored-by: Claude <noreply@anthropic.com>
* feat: Add Remotion skill component for programmatic video creation
Add comprehensive Remotion skill with 28 reference guides and 3 code examples covering:
- Core animation and timing techniques
- Compositions and metadata configuration
- Assets and media handling (video, audio, images, GIFs)
- Text animations and typography
- Caption generation and display
- Data visualization with charts
- Advanced features (3D, Lottie, transitions)
- Styling with Tailwind CSS
- Media processing with Mediabunny
Author: remotion-dev
Repository: https://github.com/remotion-dev/skillshttps://claude.ai/code/session_Y3TRI
* fix: Use 'repo' field instead of 'repository' in Remotion skill metadata
Change frontmatter field from 'repository:' to 'repo:' to match the schema
expected by generate_components_json.py script. This ensures the repository
URL is properly displayed on the website.
https://claude.ai/code/session_Y3TRI
---------
Co-authored-by: Claude <noreply@anthropic.com>
Add new security hook to prevent accidental execution of dangerous shell
commands like rm -rf, dd, mkfs, and other destructive operations.
Features:
- Blocks rm with dangerous flags (recursive, force) on critical paths
- Detects wildcards and system directory targets (/, ~, *)
- Prevents disk operations (dd, mkfs, format)
- Blocks fork bombs and direct disk device access
- Provides clear safety guidelines in error messages
- Allows safe operations (e.g., rm -rf /tmp/specific-folder)
Reviewed by component-reviewer agent.
Co-authored-by: Claude <noreply@anthropic.com>
Add comprehensive Google Analytics 4 Skill for analyzing website performance data.
Features:
- Connect to GA4 Data API using service account credentials
- Fetch and analyze traffic, engagement, and conversion metrics
- Compare time periods and identify trends
- Analyze traffic sources, content, and device performance
- Generate actionable insights and prioritized recommendations
Components:
- SKILL.md: Main Skill file with setup and usage instructions
- REFERENCE.md: Comprehensive GA4 metrics and dimensions reference
- EXAMPLES.md: 7 detailed analysis patterns with sample outputs
- scripts/ga_client.py: CLI tool for fetching GA data
- scripts/analyze.py: Higher-level analysis and reporting
- requirements.txt: Python dependencies
- .env.example: Environment variable template
Security:
- Uses environment variables for all credentials
- No hardcoded API keys or secrets
- Service account authentication only
- Clear security guidance and warnings
Reviewed by component-reviewer agent with approval.
Co-authored-by: Claude <noreply@anthropic.com>
Imported and converted components from github.com/github/awesome-copilot:
- 135 agents covering various domains (security, devops, web development, etc.)
- 7 skills converted to commands (GitHub issues, NuGet, Azure, testing, etc.)
New agent categories:
- Programming languages experts (C#, Python, Rust, TypeScript, etc.)
- Azure and cloud infrastructure specialists
- Web development experts (React, Next.js, accessibility)
- Security and DevOps specialists
- Data and AI specialists
New command categories:
- Azure (AppInsights, role selector)
- Database (Snowflake)
- Design (web design reviewer)
- Project management (GitHub issues, NuGet manager)
- Testing (webapp testing)
All components converted from awesome-copilot format to claude-code-templates format with appropriate frontmatter and categorization.
Co-authored-by: Claude <noreply@anthropic.com>
* feat(agents): add diagram-architect agent for technical diagramming
Add a new agent specialized in creating technical diagrams in multiple
formats including ASCII, Mermaid, PlantUML, and Draw.io.
Features:
- Flowcharts, sequence diagrams, state machines
- ERD generation from SQL/Prisma schemas
- Dependency graphs from code analysis
- Format conversion between diagram types
- Syntax validation before output
Includes decision tree for diagram type selection, format recommendations,
and helper script references.
Author: Brad Shannon <7515709+fubak@users.noreply.github.com>
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* fix: address PR review feedback
- Add YAML frontmatter with name, description, tools, model
- Remove Tools and Scripts section (scripts don't exist in repo)
- Remove non-standard Tags section
Addresses feedback from cubic-dev-ai and Copilot reviewers.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* Create close-debug-window.sh
* Enhance debug window script with detailed comments
Refactor debug window script for clarity and functionality.
* Enhance debug window description and functionality
Updated the debug window description to include additional details about its functionality and platform support.
* Update cli-tool/components/hooks/development-tools/debug-window.json
Invalid JSON: missing comma after description makes configuration unparsable
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
* Update close-debug-window.sh for Windows compatibility
Replace taskkill with ps and kill for better compatibility in Git Bash/Cygwin environments.
* refac: merge close-debug-window.sh to debug-window.sh
- Parses input to get hook_event_name
- Based on hook_event_name, either opens or closes the window
* Delete cli-tool/components/hooks/development-tools/close-debug-window.sh
* Change debug window command script
---------
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
daniel