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.
Create a skill called "Reviewer Response Matrix". Intake: - Reviewer comments (full text; required) - Manuscript structure (optional; if missing, mark unspecified) - Who is responsible for edits (solo/coauthors; if unknown: unspecified) Output: 1) A response matrix table (as Markdown) with statuses. 2) A response letter draft: - Include all reviewer text (quoted) - Responses grouped logically (by theme) if helpful - Polite, specific, non-defensive 3) A "missing items" checklist: comments not yet addressed. Rules: - If you aren't sure how to address a comment, propose 2–3 options and mark uncertainty.
Paste the reviewer comments and the Claw parses them into atomic items,
groups them by theme, assigns actions, and drafts a professional response letter.
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.
Make your PDF library usable for writing and citation recall
You have "organized" folders and notes, but pulling everything together for writing still takes days. This recipe converts scattered paper notes into a synthesis-ready document — themes, key claims, and where each citation supports your argument.
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.
Keep your content off the AI slop list
Have your Claw periodically check the AI Slop Wiki and build a living filter of patterns to avoid. Every piece of content your Claw creates runs through this filter first, so you never publish anything that reads like generic AI-generated filler.