claude/ai-resources-plugin/skills/changelog-review/SKILL.md
Review the Claude Code changelog and summarize recent changes and their significance.
npx skillsauth add amhuppert/my-ai-resources changelog-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Fetch the Claude Code changelog, analyze recent changes, and produce a report that explains the significance and implications of the most important updates.
<arguments> $ARGUMENTS </arguments>Extract from the arguments:
--comprehensive flag)--since <date> specifiedFetch the Claude Code changelog from:
https://code.claude.com/docs/en/changelog
Use WebFetch to retrieve the full page content. If the fetch fails, try WebSearch to locate the current changelog URL — it may have moved.
Parse the fetched content and identify all changelog entries that fall within the target time range.
Classify each change into one of these categories:
| Category | Description | Default mode | Comprehensive mode | |----------|-------------|--------------|-------------------| | Major feature | New capabilities, workflows, or integrations | Include | Include | | Significant enhancement | Meaningful improvements to existing features | Include | Include | | Developer experience | CLI UX, performance, configuration changes | Include if impactful | Include | | Minor enhancement | Small quality-of-life improvements | Omit | Include | | Bug fix | Corrections to existing behavior | Omit | Include | | Internal/infrastructure | Build, CI, dependency updates | Omit | Omit |
In default mode, focus on changes that would affect how a user works with Claude Code — new capabilities, changed workflows, or features that unlock new use cases.
In comprehensive mode, cover all user-facing changes including minor enhancements and bug fixes. Still omit purely internal changes.
For each included change, determine whether additional research is needed to explain its significance:
Use WebSearch and WebFetch to gather this context. The goal is to provide enough background that the reader understands why a change matters, not just what changed.
Generate a markdown report with the following structure:
# Claude Code Changelog Review
**Period**: [start date] to [end date]
**Mode**: [Default | Comprehensive]
**Generated**: [current date]
## Highlights
[2-3 sentence executive summary of the most significant changes in this period]
## [Category Name]
### [Change Title]
[1-2 paragraph explanation covering:]
- What changed
- Why it matters — how it affects workflows, unlocks new capabilities, or changes existing behavior
- How to use it — brief practical guidance if applicable
- Any caveats or limitations discovered during research
[Repeat for each change in this category]
[Repeat for each category that has changes]
## Summary
[Brief closing that ties together themes across changes, if any patterns emerge]
Save the report as claude-code-changelog-review.md in the current working directory.
After saving, present a brief summary to the user highlighting the 2-3 most impactful changes.
tools
Use when picking or vetting a keyboard shortcut on macOS. Triggers include "what hotkey should I use for X", "is `<combo>` available", "does this shortcut conflict", "recommend a keybinding for…", "check `<combo>` against my setup", "pick a hotkey for…", or any mention of choosing/binding/changing a shortcut in WezTerm, tmux, Zed, Chrome, Claude Code, or macOS. Determines whether a proposed combo collides with OS-reserved bindings, app defaults, or the user's customizations, and recommends ergonomic alternatives when needed.
development
Detect and remove dead code with knip. Use when the user asks to "run knip", "find unused files", "find unused exports", "find unused dependencies", "clean up dead code", "remove dead code", "set up knip", "configure knip", "knip.json", "knip false positive", "knip CI", or mentions a `knip` config, dependency bloat, bundle bloat from unused imports, or tree-shaking unused exports. Covers the configuration-first workflow, confidence-gated deletion, framework-specific gotchas (Next.js 15+, Tailwind, Storybook, Jest, Bun's test runner and `bun build --compile`), monorepos, CI integration, and performance tuning.
tools
This skill should be used when the user asks to "set up react-scan", "install react-scan", "diagnose React re-renders", "find unnecessary renders", "find unstable props", "automate React render checks with Playwright", "react-scan + playwright", "measure component renders programmatically", "check why a React component is slow", or mentions React rendering issues, slow React interactions, render counts, or component-level perf attribution. Covers install across Next.js/Vite/Remix/script-tag/browser-extension, the lite headless API for CI, and the canonical render-attribution → fix → validate loop driven through Playwright.
documentation
This skill should be used when integrating source material into a knowledge base, including when the user asks to "integrate this document into the knowledge base", "add this transcript to the memory bank", "ingest this document", "update the knowledge base", "analyze a new source document", or "sync current-state docs with this source".