Browse reusable Agent Skills, each with a clear purpose and practical guidance.
在为《计算机科学》(Computer Science, JSJKX) 撰写或审校中文稿件体例时调用。覆盖本刊要求的报道性中文摘要与英文摘要(Abstract)、中英文关键词、中英文题名、中图分类号(TP 类)、参考文献 GB/T 7714-2015 顺序编码制(正文上标、文后按序编号、中文文献中英文对照)、量与单位用法定计量单位、图表中英文题注、公式排版与语言风格。适用于把计算机全学科的中文稿件(研究长文或综述)打磨到符合本刊中文科技写作规范、可通过编辑初审的场景。
Use when drafting or revising the 中文摘要 or 英文 abstract for a 《财贸经济》(Finance & Trade Economics, CTE) manuscript — the CSSCI 财经权威期刊 run by 中国社会科学院财经战略研究院. 当摘要写成"为高质量发展提供新思路"式套话、缺核心数据 / 识别策略 / 量化发现、或中英文语义不对齐时使用。Enforces the five-sentence pattern, requires quantified findings with named data sources (CSMAR / WIND / CEIC / 统计年鉴), and forbids empty-significance phrases.
Use when positioning a Current Anthropology (CA) manuscript against the literature so it reads as an all-fields, agenda-setting contribution that can withstand the CA✩ comment-and-reply Treatment. CA readers and commentators span every subfield and many world traditions, so the paper must engage the conversations they expect and decenter a US/Anglophone-only canon. Stakes the contribution and citational politics; it does not write the lit review.
Use when responding to a Current Anthropology (CA) decision OR writing the author's Reply to the published CA✩ Comments. CA has two distinct response tasks — a normal revise-and-resubmit letter to referees/editor before acceptance, and the public, signed Reply to invited commentators printed alongside an accepted Major Article. Structures both; it does not fabricate new evidence.
Use when building the conceptual/theoretical argument of a Current Anthropology (CA) manuscript into an agenda-setting, all-fields contribution that can anchor the CA✩ comment-and-reply Treatment — whether the work is ethnographic, archaeological, biological, or linguistic. CA rewards a portable, debatable concept and reflexive argument over a bare finding or thick description alone. Structures the argument; it does not run analyses or write fieldnotes.
Use when drafting or polishing a Current Anthropology (CA) manuscript so it reads across all subfields for a worldwide audience, follows CA house style (free-format accepted; final files use Chicago author-date), fits the article-type word caps (Major Article 6,000–10,000 words; Report 3,000–5,000; abstract ≤ 200 words), and uses clear, jargon-light, inclusive language. Tightens prose and format; it does not invent content.
Use when planning or drafting the CVPR one-page rebuttal after reviews are released, covering the official rebuttal template, the ban on new contributions and external links, triaging multiple reviews at 16k-submission scale, choosing which numbers fit in one page, and writing for the AC who reads the discussion.
Use when writing or revising a CVPR paper's prose and figures, covering the 8-page budget where figures and tables count against the limit, the page-1 teaser figure convention, benchmark-table craft, claim calibration for a skeptical vision audience, and taking responsibility for tool-assisted text under CVPR's rules.
Use when handling reviewer feedback for an ACM/IEEE Design Automation Conference (DAC) Research Manuscript — writing a concise, evidence-first rebuttal IF the cycle runs an author-response period (verify; DAC has historically not), and otherwise converting DAC reviews into a targeted response-to-reviewers when rerouting a rejected paper to ICCAD, DATE, ASP-DAC, or a journal.
Use when building the reproducibility story for an ACM/IEEE Design Automation Conference (DAC) Research Manuscript, covering pinned EDA benchmark suites and versions (ISPD, EPFL, ISCAS/ITC, TAU, CircuitNet), open-source flow provenance (OpenROAD, ABC, Yosys), PDK/library and tool-version disclosure, seed/variance reporting for stochastic and ML flows, and the anonymized-then-public repository path — absent a formal DAC artifact-badging track.