I'll read your final draft the way a hostile but fair referee would—finding the pressure points, specifying the most likely fatal objection, and giving you a clear publication recommendation with the specific revision that would change it. I start by characterizing your argument in my own words so you can check whether I've understood it before you weigh anything else I say. Optionally: tell me the target journal and I'll calibrate to its standards. Not for your peer reviewing commitments.
You have an R&R decision, two reviewer reports pulling in different directions, and a manuscript to revise. The hardest part isn't the revisions; it's the response letter. Capitulate and you weaken the paper. Push back and you alienate the editor. This agent drafts the letter the editor needs: an opening that names the substantive changes, a point-by-point response with page references for every change, and principled pushback where a reviewer request would weaken the argument.
Turn public replies to negative, positive, and mixed marketplace reviews into trust assets future buyers can see. This skill triages reviews, checks platform rules, decides escalation, and drafts brand-consistent public replies, DM or support handoffs, voice checks, and review-rate next actions.
Helps users turn rough prompts into clear, specific, reusable prompts in different LLMs through concise critique.
Studied hundreds of negative review cycles across Yelp, Google, TripAdvisor, and app stores. The pattern: most responses make things worse — defensive, generic, or copy-pasted. This skill applies the de-escalation and reputation management framework that actually works: acknowledge specifically, take responsibility without groveling, offer a clear path forward.
Paste any comment — praise, question, joke, or hate — and get 5 ready-to-post replies in different tones. Save 30+ minutes a day on comments for Shorts, TikTok, and Reels.
粘贴一段git diff，即可获得一份可直接提交评审的Pull Request材料包：结构化的PR描述(概要、改动与原因、测试说明)、风险提示(数据库迁移、API/契约变更、配置改动、删除操作)、把最高风险的改动优先呈现给评审者的"评审关注地图"，以及针对该diff量身定制的自查清单。专为使用Claude Code、Codex等编码智能体开发并提交PR的开发者打造。仅根据你粘贴的diff生成内容，无法判断的地方标注[FILL IN]。无需API密钥，不访问仓库，不涉及个人数据。
Drop any Amazon review and get 3 strategically different reply versions — Apology-First, Solution-First, and Stand-Firm — each checked against Seller Central TOS, customer psychology, and how future buyers will read your response. Includes TOS compliance flags, buyer diagnosis, and a Public Perception Score predicting brand impact. 5 minutes of clarity for FBA sellers, VAs, and reputation managers staring at a 1-star review.
Four independent AI reviewers — Security Skeptic, Reliability Realist, Maintainability Pragmatist, and Performance Pessimist — each review your diff blind to the others' verdicts, so real bugs don't get averaged away into one polite summary.