Generate clean + tracked/diff outputs for revise-and-resubmit
Package a revision the way editors and coauthors want it: clean manuscript, changes-marked version, and a concise change log. Produces a repeatable packaging checklist and QA pass before you hit submit.
Create a skill called "Revision Diff Packager". Ask for: - Previous submission and revised manuscript (or instructions on where they are) - Writing system: Word / Google Docs / LaTeX / other (if unknown: unspecified) - Journal/conference requirements for marked changes (if unknown: unspecified) Output: - A packaging checklist: - Clean manuscript - Marked-changes version (method depends on tool) - Change log summary - File naming convention + version tag - A QA checklist: missing figures/tables, broken references, track-changes leaks, anonymity issues (if blind review). Rules: - If tool-specific steps are unknown, clearly mark them as unspecified and provide generic alternatives.
Revision requests often require "highlighted changes" alongside a clean version.
This recipe builds a packaging checklist so you don't miss anything and don't
repeat the work next time.
Turn reviewer comments into an action table and a response letter draft
Peer review comments arrive as a wall of text. This recipe converts them into a clear execution plan — what to change, where, how to respond — plus a point-by-point response letter draft.
Turn an overwhelming reading backlog into a prioritized plan
Too many papers, too little time, no reliable way to decide what to read next. This recipe builds a time-boxed, prioritized reading queue for any topic, project, or thesis chapter — with a built-in "rabbit-hole safe" capture channel for questions to research later.
Wikipedia-grade AI pattern removal
Comprehensive AI writing cleanup based on Wikipedia's WikiProject AI Cleanup guidelines. Catches 24+ distinct patterns including inflated symbolism, em dash overuse, rule of three, copula avoidance, and sycophantic tone.
Make invisible labor visible and ownable
Convert the invisible cognitive labor of being the "default parent" into a shared, ownable task system with clear accountability. One owner per domain — sees it, plans it, does it, confirms it.