kata-whats-new
Show what's new in Kata since the installed version, displaying changelog entries, checking for Kata updates, or reviewing recent changes. Triggers include "what's new", "whats new", "show changes", "changelog", "recent changes", and "what changed".
Best use case
kata-whats-new is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Show what's new in Kata since the installed version, displaying changelog entries, checking for Kata updates, or reviewing recent changes. Triggers include "what's new", "whats new", "show changes", "changelog", "recent changes", and "what changed".
Teams using kata-whats-new should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/kata-whats-new/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How kata-whats-new Compares
| Feature / Agent | kata-whats-new | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Show what's new in Kata since the installed version, displaying changelog entries, checking for Kata updates, or reviewing recent changes. Triggers include "what's new", "whats new", "show changes", "changelog", "recent changes", and "what changed".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
<objective> Display changes between installed version and latest available version. Shows version comparison, changelog entries for missed versions, and update instructions. </objective> <process> <step name="get_installed_version"> Read installed version from VERSION file (checking plugin context first): ```bash if [ -n "$CLAUDE_PLUGIN_ROOT" ]; then cat "$CLAUDE_PLUGIN_ROOT/VERSION" 2>/dev/null fi ``` **If VERSION file missing:** ``` ## Kata What's New **Installed version:** Unknown Your installation doesn't include version tracking. **To reinstall:** `/plugin install kata@kata-marketplace` ``` STOP here if no VERSION file. </step> <step name="fetch_remote_changelog"> Fetch latest CHANGELOG.md from GitHub: Use WebFetch tool with: - URL: `https://raw.githubusercontent.com/gannonh/kata/refs/heads/main/CHANGELOG.md` - Prompt: "Extract all version entries with their dates and changes. Return in Keep-a-Changelog format." **If fetch fails:** Fall back to local changelog: ```bash cat "$CLAUDE_PLUGIN_ROOT/CHANGELOG.md" 2>/dev/null ``` Note to user: "Couldn't check for updates (offline or GitHub unavailable). Showing local changelog." </step> <step name="parse_versions"> From the remote (or local) changelog: 1. **Extract latest version** - First `## [X.Y.Z]` line after `## [Unreleased]` 2. **Compare with installed** - From VERSION file 3. **Extract entries between** - All version sections from latest down to (but not including) installed **Version comparison:** - If installed == latest: "You're on the latest version" - If installed < latest: Show changes since installed version - If installed > latest: "You're ahead of latest release (development version?)" </step> <step name="display_output"> Format output clearly: **If up to date:** ``` ## Kata What's New **Installed:** 1.4.26 **Latest:** 1.4.26 You're on the latest version. [View full changelog](https://github.com/gannnonh/kata/blob/main/CHANGELOG.md) ``` **If updates available:** ``` ## Kata What's New **Installed:** 1.4.23 **Latest:** 1.4.26 --- ### Changes since your version: ## [1.4.26] - 2026-01-20 ### Added - Feature X - Feature Y ### Changed - **BREAKING:** Changed Z behavior ## [1.4.25] - 2026-01-18 ### Fixed - Bug in feature A --- [View full changelog](https://github.com/gannnonh/kata/blob/main/CHANGELOG.md) **To update:** `/plugin update kata@kata-marketplace` ``` **Breaking changes:** Surface prominently with **BREAKING:** prefix in the output. </step> </process> <success_criteria> - [ ] Installed version read from VERSION file - [ ] Remote changelog fetched (or graceful fallback to local) - [ ] Version comparison displayed clearly - [ ] Changes since installed version shown (if any) - [ ] Update instructions provided when behind </success_criteria>
Related Skills
kata-help
Show available Kata skills, displaying the usage guide, explaining skill reference, or when the user asks for help with Kata. Triggers include "help", "show skills", "list skills", "what skills", "kata skills", and "usage guide".
kata-execute-quick-task
Execute small ad-hoc tasks with Kata guarantees, running quick tasks without full planning, or handling one-off work outside the roadmap. Triggers include "quick task", "quick mode", "quick fix", "ad-hoc task", "small task", and "one-off task".
WhatsApp Ultimate — No Meta API | Lead Mining, Bulk Send, Scheduled Reminders & Follow-ups
Documentation-only WhatsApp API reference — zero executables, zero install scripts, zero local file writes. All actions require explicit user invocation. Provides 90+ API endpoints for sending messages, capturing leads, running campaigns, scheduling reports, tracking campaign analytics, and managing clients. MOLTFLOW_API_KEY is the only credential required — generate a scoped key from the MoltFlow dashboard (Settings > API Keys). AI features (voice transcription, RAG, style profiles) use the user's own LLM API key configured via the MoltFlow web dashboard, never passed through this skill.
automate-whatsapp
Build WhatsApp automations with Kapso workflows: configure WhatsApp triggers, edit workflow graphs, manage executions, deploy functions, and use databases/integrations for state. Use when automatin...
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
mcp-standards
MCP server standardization patterns for Claude Code plugins. Use when implementing MCP servers, designing tool interfaces, configuring MCP transports, or standardizing MCP naming conventions. Trigger keywords - "MCP", "MCP server", "MCP tools", "MCP transport", "tool naming", "MCP configuration".
mcp-server-evaluations
Test MCP servers for quality and reliability. Verify tool functionality, test error handling, generate tests, and assess response quality with no dependencies other than curl. Use this when validating MCP server implementations, testing OpenAPI-to-MCP conversions, or assessing API tool quality.
mcp-repo-scan
Comprehensive RE-Engine repository health audit, issue resolution, and architectural enhancement through systematic codebase analysis
mcp-patterns
MCP server building, advanced patterns, and security hardening. Use when building MCP servers, implementing tool handlers, adding authentication, creating interactive UIs, hardening MCP security, or debugging MCP integrations.
MCP Integration
Model Context Protocol (MCP) integration specialist. Use when creating MCP server configurations, implementing MCP integrations, or optimizing MCP performance. Specializes in MCP server architecture and integration patterns.
mcp-development
Model Context Protocol (MCP) server development and AI/ML integration patterns. Covers MCP server implementation, tool design, resource handling, and LLM integration best practices. Use when developing MCP servers, creating AI tools, integrating with LLMs, or when asking about MCP protocol, prompt engineering, or AI system architecture.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).