Create academic presentation slide decks and optionally demo videos from research papers. Use when the user asks to "make slides", "create a deck", "make a presentation", "demo video", "paper slides", "conference talk slides", or wants to turn a paper into a visual presentation. Covers slide generation, narration scripts, TTS audio, and video assembly.
Use when conducting literature reviews, summarizing papers, comparing methodologies, identifying research gaps, or supporting scholarly writing across disciplines.
Build crafted, highly detailed, interactive isometric SVG figures that explain a technical idea as a real physical object (a test rig, a dial gauge, a cabinet of drawers, a plotter, a lock), with many small precise solid parts, four-tone shading, correct painter's order, a framed card with title, hint and live readout, and calm eased motion. Use this whenever someone wants an isometric illustration, an explanatory diagram or figure for docs, a blog post, a landing page or an article, a "Linear-style" or "premium" technical drawing, an interactive explainer, or an SVG that shows how a system, algorithm or component works, even if they never say "isometric". Works framework-free (TypeScript/JS that writes SVG and HTML) and in React/Next.js, and can add realistic WebGL shaders (fire, exhaust, water, caustics, lamp light) that live inside the drawing in the same isometric perspective. Also publishes a finished figure to the Anatomy community gallery when asked.
Remove audit, defensive, self-critical, developer-facing and commitment writing from a manuscript, its Supplementary Information, figure legends, table notes, data and code statements and figure content, while keeping every number, definition, reproducibility fact, mandated statistical statement, null result and scope condition that sets a reported value. Audit voice is project process leaking into the paper (locked, frozen, hashed, verified, post hoc, leakage-safe, gate verdicts, implementation checks). Defensive voice argues with an imagined reviewer (does not establish, should not be read as, we do not claim, for completeness). Self-critical voice has the paper judge or apologize for itself (could not be identified, not directly comparable, only a small fraction, unused datasets listed, table columns that grade their own rows). Developer voice addresses whoever runs the repository instead of whoever reads the paper (folder paths, file names, workbook sheets, manifests, loaders, editable or generated LaTeX). Commitment voice promises what does not exist yet (will be released, planned before acceptance, access can be arranged). Also carries the rule for not adding any of these while editing. Runs at the rhetorical-posture layer, after the claim hierarchy is settled and before the sentence pass. Load when a draft or SI reads like an audit report, a rebuttal letter, a self-critique or a repository README, when a paragraph opens with a limitation, or on request: de-audit, less defensive, more direct, cut the hedging, remove developer notes, no promises, 去审计, 审计味, 防御性写作, 自我批评, 自我限制, 评判式写作, 去包装, 太多免责, 写得太怂, 太啰嗦, 让语气更肯定, 别老说自己不主张什么, 读者和编辑不关心的内容, 面向开发人员, 代码路径, 文件名, 事前承诺.
按目标期刊调用Awesome-Journal-Skills完整资源库，用于选刊、期刊风格写作、投稿前检查、模拟审稿与返修回复，支持Nature、Science、Cell及其子刊等。适用于指定期刊的写作与投稿要求，或明确请求使用Awesome-Journal-Skills。
Discover relevant specialist skills from the live awesome-skills list and install them when appropriate. Use proactively for non-trivial tasks that may benefit from a reusable specialist capability not already available, or when the user asks what skills or tools to use. Check the live list before searching for generic alternatives or rebuilding a known capability. Skip simple conversational requests and tasks already covered by installed skills.
把图片、截图、海报、PPT 页面截图、HTML 或 SVG 设计稿转换成可编辑 PPTX 的 Codex skill。 当用户需要 image2ppt、image2pptx、图片转 PPT、截图转 PPT、PNG/JPEG 转可编辑幻灯片、 HTML/SVG 转 PPTX、把设计图拆成图片组件和文本框再拼成 PowerPoint、 或希望复用 Codex 内置生图能力把平面图重建为多元素可编辑 PPT 时，应该使用此 skill。 在 Codex 中处理二进制图片时，默认结合 imagegen skill：先用 Codex 视觉理解版式， 再用内置图片生成/编辑能力生成或清理多个组件图片，最后用本 skill 的脚本拼装 PPTX。
Use when checking manuscript citations, bibliography hygiene, DOI or PMID completeness, placeholder references, or BibTeX consistency before submission or revision.
Use when a manuscript's claims need to be checked against the sources cited for them, when literature search results must be verified before they enter a draft, or when an agent or collaborator has proposed references that have not yet been adversarially reviewed. This is claim-to-evidence verification, not bibliography hygiene; for duplicate keys, DOI syntax, and metadata cleanup use citation-verifier instead.
Generate visually unified image-based PPT/PPTX decks from articles, reports, papers, notes, or outlines.
Use when writing or revising ML or AI conference papers for venues such as NeurIPS, ICML, ICLR, ACL, AAAI, or COLM, especially when the workflow is conference-first rather than Nature-style journal-first.
Use when drafting, auditing, or revising Data Availability statements, repository plans, accession-number placement, source-data coverage, or restricted-data wording for journal submission or resubmission.
Use when a manuscript is being drafted across many sessions and needs auditable open-question tracking: in-source draft markers with distinct jobs, triage of open items by what would actually resolve each one, word counts that exclude draft apparatus, safe archival of superseded material, and assertion-guarded scripted edits. Load before doing a batch pass over TODO markers or before quoting a manuscript's length.
Use when designing, restructuring, or auditing manuscript figures and you need to define one main claim per figure, assign panel roles, align legends with the text, or decide what belongs in main figures versus supplement.
Publication-grade figure correctness and legibility rules for final-deliverable figures — not every plot. Quick look or iterating on the analysis (EDA scatters, sanity-check histograms)? Plot plainly without this skill. Producing a figure that ships — report, paper, export, or kept artifact — load this skill first and call apply_figure_style() — sets a role-mapped font-size ladder, outward ticks, frameless legends, and 300-dpi output. The skill is a checklist, not a house look: data fidelity (claim-titles tested against every row, excluded data never enters summaries), label economy (floor and ceiling), color threading, chart-choice-by-data-shape, layout, and a render-then-verify QA loop (bbox collision + per-panel perceptual check). Ships helpers: focal_palette, bar_with_points, strip_with_median, end_of_line_labels, panel_letter, set_frame, panel_crops. For figure planning (one claim per figure, panel roles) use figure-planner; for the full Nature figure production workflow use nature-figure.
Create, repair, validate, visually QA, and package Codex-compatible v2 animated pets from character art, generated images, company or prospect brand cues, or visual references. Use for any new Codex pet, custom mascot, non-pixel pet style, brand-inspired pet, existing-pet repair, or 8x11 spritesheet workflow requiring all 9 standard animation rows, 16 look directions, deterministic assembly, QA artifacts, and spriteVersionNumber 2 packaging.
Rebuild slide images, image-based or scanned PPT/PPTX files, and PDF decks into object-level editable PowerPoint (.pptx). Use whenever the user provides any visual slide source and wants slides they can edit — "make this PPT editable", "把图片/截图转成可编辑 PPT", "this PDF is a scanned deck, restore it", recreating slides from screenshots, reconstructing slide objects, or preserving speaker notes — even if they do not say "convert". Not for authoring new presentations from scratch.
Use when auditing, restructuring, or revising a research manuscript whose scientific question, claim hierarchy, evidence chain, section logic, figures, terminology, or prose may be unclear or out of sync. Apply before sentence-level polishing, especially for whole drafts, major revisions, resubmissions, overclaiming, experiment-by-experiment Results, inaccessible narratives, or manuscripts that need a claim-driven architecture.
Use when choosing among Nature, Nature Methods, or Nature Biotechnology, or when preparing a Nature Portfolio life-science manuscript for venue fit, article-type framing, and policy-aware pre-submission checks.
Use when deeply analyzing a single paper and producing structured notes on claims, methods, figures, evaluation, strengths, limitations, and related work.
Use when starting a new manuscript project or cleaning up an existing paper directory and you need a standard structure, active source files, project memory, and venue defaults before deeper writing begins.
Referee-side skill for Nature Portfolio manuscripts, in four modes. Write a referee report: methodology, statistics, reporting standards, reproducibility, and data and code availability. Inventory a report you received: split it into every ask and sub-ask, in the referee's own words, own numbering, and own order, so that each one can be answered separately and nothing is missed. Grade a drafted reply the way an impatient referee reads it: one reply per ask, the referee's own comment verbatim above its answer, the answer in the first sentence, no invented vocabulary, and every reply landing somewhere in the manuscript. Use when the ask is review this manuscript, write a referee report, what will reviewers attack, turn these reviewer comments into a checklist, answer each comment one by one, did I miss a reviewer point, would this reply satisfy the reviewer, 审稿, 写审稿意见, 模拟审稿, 拆解审稿意见, 逐个回复, 逐条对照, 有没有漏回, 审稿人会不会接受, 以审稿人视角检查回复, 回复够不够直白. To choose the stance on each ask, calibrate a claim to the evidence, and assemble and audit the whole letter, use rebuttal-response: this skill decides what must be answered and what counts as an answer, that one decides what to say.
Route general manuscript requests such as improve my paper, revise this draft, 优化论文, 润色论文 or 投稿前检查. Identify the article type, requested scope and available evidence, then choose the necessary writing or checking steps. Use direct specialist skills for a named, narrow task. Do not route ordinary emails, code documentation or non-manuscript writing through this workflow.
This skill should be used when the user asks for a publication-quality scientific figure or table, wants help choosing the right chart for results, needs a paper-ready pubfig or pubtab workflow, wants a figure + companion table for a results section, wants an Excel sheet turned into publication-ready LaTeX, or wants an existing scientific figure/table reviewed and upgraded.
Analyze, draft, revise, or audit scientific peer-review response letters and point-by-point rebuttals. Use for reviewer comments, response letters, rebuttals, revision summaries, quoted manuscript changes, replies that must align with a manuscript or Supplementary Information, and submission-ready checks of direct question-answer alignment, evidence, figures, tables, notes, panels, terminology, numbers, and internal citations. Especially useful when replies must reuse the reviewer's terms, map every sub-question to an explicit answer, report new analyses or experiments, identify exact revision locations, or distinguish mandatory fixes from optional polishing.
Verify that cited references actually exist and that their metadata matches, using the runnable scripts this skill ships for CrossRef, Semantic Scholar, arXiv, and PubMed. Use when the bibliography must be checked against live sources rather than inspected locally: detecting fabricated or hallucinated citations, confirming that DOIs resolve, and matching title, authors, venue, and year against the record. Also covers the underlying verification principles and reference-audit best practices. For an offline hygiene pass over a .bib or .tex file, run citation-verifier first; for whether a real source supports the sentence citing it, run claim-source-verification.
Use when analyzing experimental results, validating comparisons, generating paper-ready results text, or turning model-evaluation outputs into figures, tables, and defensible claims.
Use when revising a scientific manuscript Results section whose figures, evidence, and main claims are mostly fixed, but subsection flow, paragraph openings, reader guidance, and argumentative progression still feel abrupt, repetitive, or figure-by-figure.
Use when writing, restructuring, or auditing a Review, survey, or Perspective rather than a research article, especially a commissioned one written across many sessions. Covers the governing plan document, drift detection, single-definition thesis and field judgements, section-owns-figure allocation, display-item budgets, four-state status markers, and authorship-blank discipline. For research articles with Results and Methods, use manuscript-optimizer instead.
Prose-quality rules for writing scientific manuscript text — abstract, introduction, results, discussion. The headline rule is a strict em-dash budget: the long dash (—) is overused and reads as a stylistic tic, so cap it and rewrite with commas, colons, parentheses, or a period. Also covers hedging, sentence rhythm, and paragraph openers. Load whenever drafting or revising manuscript prose (not figures; that is figure-planner).
Use when writing or revising scientific manuscripts, abstracts, figures, or references for journal submission and you need full-paragraph prose, scientific structure, citation-style guidance, or reporting-guideline support.
SciPilot Skills 家族成员，负责科研数据可视化——但定位不是"画图工具"， 而是"可视化顾问"。先做数据剖析（列类型/样本量/分布/异常值/分组结构/相关性）， 再结合用户的论证目标推荐图型，主动拦截科研画图的经典错误（小样本画均值柱掩盖 分布、双 Y 轴、饼图、Y 轴不当截断、rainbow 色图、把分类点连成折线等），最后 产出 Nature / Science / IEEE / Elsevier / PNAS / 中文核心期刊级别的成图。 覆盖纯数据图：折线、柱状、散点、箱线 / 小提琴、热力图、误差棒、分布图（直方 图 / KDE）、相关性矩阵 / 散点矩阵、多面板组合。技术栈 matplotlib + seaborn + SciencePlots（静态）+ plotly（交互）。中英文双语，中文模式自动配置 Noto Sans CJK / Source Han Sans / SimHei 并修复负号方框，支持中文期刊"宋体正文 + Times New Roman 数字"混排。默认色盲安全配色 + 冗余编码 + 灰度预览。出图后做 "视觉自检闭环"：渲染 PNG 预览→程序自检缺字/文字裁切/刻度重叠→AI 读图复核遮盖 与子图对齐→回改重渲，直到通过。 当用户的任务涉及以下任何情况时主动触发：论文配图、科研画图、数据可视化、 不知道用什么图、怎么展示数据、用什么图好、期刊投稿图、figure、出版级图表、 matplotlib、seaborn、plotly、误差棒、显著性标注、色盲安全配色、矢量图导出、 中文论文图表、多面板。**即使用户只是给一批数据问"这个怎么画"或"用什么图 好"，也应使用本技能——本技能首要能力是"判断该用什么图"，其次才是绘制。** 不做示意图、流程图、架构图。
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model assumptions, figure legends, Results statistics wording, reviewer comments about statistics, or Chinese academic drafts needing publication-ready Statistical analysis text. Also trigger on general paper-statistics requests such as 统计审查、统计分析小节、统计方法、p值、样本量、重复数、多重比较、置信区间、效应量、图注统计、审稿人统计意见.
Use when a manuscript is close to submission or resubmission and you need a preflight audit for claim support, figure-panel coverage, legend sync, methods references, terminology stability, and venue-facing risks.
Use for browser navigation, inspection, interaction, and visual verification through Tabbit's installed CLI.
规划、生成、修改和检查数学建模与科研图表；包含143个完整源码配方、3套组合模板、统一配色和来源差异工具，以及Draw.io/TikZ、HTML/Mermaid和科学场景插图。
Diagnose and repair the clarity and logic of manuscript prose, journal-agnostic. Use when a passage is technically correct but hard to follow: buried topic sentences, missing logical bridges, ambiguous referents, abstract noun chains, overloaded sentences, incomplete comparisons with no stated dataset or metric or direction, scope qualifiers placed too far from the claim, and invented or inflated terminology that should have been an ordinary word. Also covers writing for a broad scientific reader without losing precision, section-by-section logic patterns, paragraph-level reverse outlines, and keeping observation separate from interpretation. This is the layer between structure and punctuation: use manuscript-optimizer when the claim hierarchy itself is unstable, and scientific-prose-style for the final sentence-level pass.