How to write analyses, research reports, recommendations, and decision memos so a reader can answer "How should I update my view in response to this?" — open with linked key takeaways, flag which considerations matter most, and state confidence + kind of support for every major claim. Load when drafting or reviewing a…
Review an existing GitHub PR with the parallel pr-review-toolkit agents, post inline findings, fix them, run the quality pipeline, push, resolve threads, and post a summary. Right-sizes small / delta PRs to a direct single-pass review with no sub-agents. Use when asked to review and fix a PR, do a thorough multi-agent…
Search previous Claude Code session history by keyword. Use when the user asks to find a past conversation, recall what was discussed, or locate a session where a topic came up.
Set up a local agent replay server for Raindrop Workshop. Use when the user wants Workshop to replay a captured trace against their real local agent code and tools. Creates/updates .raindrop/agents.yaml, scaffolds a language-appropriate replay server, registers the project with raindrop replay register, and verifies…
Bidirectional sync between a Slidev markdown deck and Google Slides as native, editable objects (not images). Push markdown -> Slides, pull Slides -> markdown, and round-trip. Use when the user wants to author/version a Google Slides deck from markdown, replicate a deck's styling, or keep a .slidev.md in sync with a…