Sfoglia il registro

Tutte le voci, in ordine alfabetico — 56.437 in totale. Pagina 166 di 226.

• p13b-systemic-thinker系统性思维——结构化分析、关系映射、反馈回路识别
• p13c-product-psychology产品心理学——用户心理模型、行为设计、动机分析
• p13d-intuition-training直觉训练——将直觉转化为可压缩的认知模型与模式识别
• p13e-nine-step-frameworkAI产品决策九步闭环总论——覆盖做什么、值不值得、用不用AI、做成什么、用户托付、怎么做、怎么验证、怎么卖、反馈回路
• p13f-first-half-judgment九步前半段——做什么、值不值得、用不用AI的判断框架
• p13g-mid-judgment九步中段——做成什么形态、用户托付度、怎么做的决策框架
• p13h-validation-market九步后段——怎么验证、怎么进入市场、反馈回路的决策框架
• p13i-judgment-traps判断陷阱与认知偏误——识别常见判断错误模式及其防范策略
• p13j-organizational-judgment组织判断力——将个人判断转化为团队判断能力的系统方法
• p13k-intuition-evolution直觉进化——持续训练判断力、建立标准提升机制
• p14-beauty-orchestrator《AI Beauty》全书编排器——审美主导权与美感体系化训练的路由器
• p14a-beauty-redefinition美感的重新定义——生成焦虑、美感六维度、美感双轴模型
• p14b-beauty-ai-rolesAI在审美中的角色定位——放大器/陪练器/协作者，而非审美本身
• p14c-beauty-selection从生产美感到选择美感——选择力是新核心技能，Context决定输出上限
• p14d-beauty-narrative故事力即美感——叙事结构、情感节奏、信息架构的审美维度
• p14e-beauty-human-edge人的不可替代性——美感作为护城河、标准进化、人的核心优势
• p14f-beauty-commercial美感的商业价值——市场接受度、美感溢价、体验美感、物理世界平衡
• p14g-beauty-system审美训练体系——系统化积累与校准审美标准、人机协作流程、标准进化机制
• p14h-beauty-preface前言与核心命题——当一切都能生成之后，审美主导权成为核心竞争力
• p1b流水线 P1b：吃 P1 套路 JSON，发散 5–7 个"换设定外壳、换走向"的换壳候选供作者挑，金手指内核＋题材调性双留死。吐候选清单＋一行对标防撞基准（作者挑定后落 00_脑洞.md）。何时用：作者说 换壳、切入候
• p2流水线 P2：在作者选定的脑洞下挖市场钩子与事件毛坯，按 a→c→b 顺序产出书名卖点 12 组（P2-a）、简介 3 版（P2-c）、18 个事件毛坯（P2-b）供作者挑约 70% 改写；含可选素材对齐机（P2-d）。
• p2a-experiment-overviewAI Native 产品方法论——试验展开概述的实操 Skill。
• p2b-product-form-explorationAI Native 产品方法论——产品形态探索的实操 Skill。
• p2c-process-redesignAI Native 产品方法论——流程重构与任务设计的实操 Skill。
• p2clawPublishes apps you've built locally as peer-to-peer URLs that anyone with the link can open in a browser. Use
• p2d-convergence-decisionAI Native 产品方法论——目标收敛与产品决策的实操 Skill。
• p2e-shadow-validationAI Native 产品方法论——影子验证的实操 Skill。
• p2p-wiki-categoriesBrowse and navigate P2P Foundation Wiki categories. List all categories, view articles within a category, or f
• p2p-wiki-exploreDiscover random, recent, or trending content on the P2P Foundation Wiki. Get random articles for serendipitous
• p2p-wiki-readRead full article content from the P2P Foundation Wiki. Fetches and extracts clean text or raw wikitext from a
• p2p-wiki-searchSearch the P2P Foundation Wiki for articles on peer-to-peer, commons, open-source, and decentralized topics. R
• p3流水线 P3：先锁调性卡＋文风卡两张随身卡，再扩出分层大纲 ABCD（世界观金手指／势力反派梯队／前 30 章逐章剧情点／人物感情线）；含 P3C 续卷（挖本卷事件＋扩散下一卷）。吃 P1 套路 JSON＋作者选定的脑洞
• p3b流水线 P3b：从蓝图大纲 A/B/D 整理两份每章喂正文的活文档——人物圣经（主角卡 ≤300 字＋核心配角 ≤5 张各 ≤150 字）和设定卡（5 块 ≤500 字）。吃 01_蓝图.md，吐 02_人物圣经.md＋
• p4a流水线 P4a：把大纲 C 第 N 章那行拆成 3–5 条核心事件序列（每条 ≤20 字），标爽点位置、结尾钩子方向、章节名；只列发生了什么，不展开怎么发生。吃大纲 C 本章行＋上章结尾 200 字，吐 章纲/第NNN章
• p4b流水线 P4b：把章纲展开成 P5 能直接照着演的场景脚本（细纲）——分场分拍、要害台词原话、憋放焊进动作；铁律 3 关键步，细纲信息密度决定正文质量上限。吃本章章纲＋设定卡＋调性卡＋上章尾，吐 细纲/第NNN章.md。
• p5流水线 P5：把本章细纲一镜到底演成净 2100–2300 字正文，解析并删净括号控场指令，全程守调性卡＋文风卡。吃六槽（调性卡＋文风卡＋角色卡＋事件摘要＋本章细纲＋上章结尾），吐 正文/第NNN章.md（落盘后跑 ch
• p5jsProduction pipeline for interactive and generative visual art using p5.js. Creates browser-based sketches, gen
• p6流水线 P6：从正文切片里只挑五类硬伤（人设矛盾/逻辑断裂/设定冲突/时间线错乱/爽点铺了没爆），不改稿、对文笔完全免疫、宁漏报不凑数；必须开独立于写正文的全新会话跑。吃设定卡＋事件摘要＋正文切片，吐硬伤清单。何时用：作
• p6a-certainty-premium-calculator确定性溢价计算器。基于《AI确定性商业模式》核心公式， 帮助产品团队计算 AI 产品的确定性溢价，从而设计更高价值的收费模式。
• p6b-arbiter-mode-designer仲裁者模式设计器。设计以"真相即服务"为核心的商业模式： 提供可验证的真实信息和判断，让用户相信每个数字都是真的。 基于《AI确定性商业模式》概念卡。
• p6c-insurance-mode-designer保险模式设计器。设计以"结果担保"为核心的商业模式： 为 AI 的输出结果提供担保，出错则赔偿或免费。 基于《AI确定性商业模式》概念卡。
• p6d-prediction-arbitrage-designer预测套利设计器。设计以"超越人类预测能力"为核心的商业模式： 在 AI 预测能力强于人类的领域进行套利，将预测优势转化为商业价值。 基于《AI确定性商业模式》概念卡。
• p7a-data-flywheel-builder数据飞轮构建器。基于《AI Native 营销与增长》数据飞轮概念卡， 帮助产品团队评估和构建自增强的数据飞轮：使用→数据→模型→产品→更多用户→更多数据。
• p7b-intent-prediction-designer意图预测营销设计器。基于《AI Native 营销与增长》意图预测营销概念卡， 帮助产品从"人群定向"升级为"个体预见"——在用户明确表达之前就提供相关内容。
• p7c-predictive-retention-designer预测性留存设计器。基于《AI Native 营销与增长》预测性留存概念卡， 帮助产品从"流失后挽回"升级为"流失前阻止"——在用户流失之前主动干预。
• p7d-marketing-productizer营销产品化设计器。基于《AI Native 营销与增长》营销产品化概念卡， 帮助产品将营销活动设计为产品功能，让用户在使用中自然完成"被营销"。
• p7e-customer-loopAI Native 产品方法论——客户循环的实操 Skill。
• p8流水线 P8：滚动维护记忆层活文档——P8-a 事件摘要（每章）/ P8-b 设定卡重出（每 10 章）/ P8-c 数值台账＋新角色回流（每章顺手）/ P8-d 卷末收口快照（每卷一次）。吃本章正文＋旧活文档，回写 0
• p8a-rax-risk-assessorRAX 风险评估器。基于《AI时代的用户体验》RAX 框架（Risk, Ambiguity, eXposure）， 系统性评估 AI 产品的风险、模糊性和暴露程度，帮助产品团队识别和管理用户体验风险。
• p8b-trust-tier-designer信任度分级设计器。基于《AI时代的用户体验》信任分级理论， 设计 AI 产品的信任度分级体系，让用户渐进式地建立对 AI 的信任。
• p8c-progressive-disclosure渐进式披露清单。基于《AI时代的用户体验》渐进式披露理论， 提供 AI 产品逐步展示功能和能力的设计清单，避免一次性向用户交付过多信息。
• pab1it0/awesome-a2aAgent2Agent (A2A) – awesome A2A agents, tools, servers & clients, all in one place.
• pab1it0/google-maps-a2aAn open-source Agent2Agent (A2A) compliant server that provides Google Maps capabilities to other agents via a
• pace-planBuild, coordinate, operate, troubleshoot, exercise, and improve an authorized Primary, Alternate, Contingency,
• pacing-and-the-player-journeyUse when designing, auditing, or generating the macro arc of an experience — how engagement rises and falls ac
• pack-creatorGuide a PACK-X author through the SPF fill cycle 01-11. Calls R28 Diagnostician to select mode (assembly/hybri
• pack-newCreate a new Pack — guided flow through SPF: choose domain, name Pack, scaffold structure, fill roadmap.
• pack-prerequisite-checkerVerify brief completeness, runtime posture, skill coverage, and evidence habits before starting a pack workflo
• packagePackage a product for distribution across 33+ platforms. Strips WHY comments, generates triple manifests (vaul
• package-dirCryptographic integrity and provenance for AI instruction files (SKILL.md, CLAUDE.md, prompt packs) - local se
• package-evaluatorEvaluates Claude Code package quality across 6 dimensions for all 7 package types, producing scored audit repo
• package-lock-parsingParse and extract package information from npm package-lock.json files to identify dependencies and their inst
• package-managementManage NuGet packages using Central Package Management (CPM) and dotnet CLI commands. Never edit XML directly
• package-npm-nixPackage npm/TypeScript/Bun CLI tools for Nix. Use when creating Nix derivations for JavaScript/TypeScript tool
• package-private-ml-artifactsInventories, hashes, scans, and verifies datasets, adapters, checkpoints, logs, and evaluation evidence before
• package-public-skillPrepare a private agent skill for public release on GitHub — evaluate standalone usefulness, scrub personal na
• package-releasePrepare, publish, repair, or verify package releases and changelogs. Always use for package/version release, p
• package-release-snifferLoad when tracking newly published package or model-package releases across package registries and release fee
• package-usageTrack which stacks across a Pulumi organization use a specific package and at what versions. Use for cross-sta
• packer-imaging-expertspecialized protocol for automated machine image creation using HashiCorp Packer, OS auto-installs (Kickstart/
• packet-factoryCreates, reviews, and dispatches atomic work packets. Every task with a side effect requires an APPROVED packe
• packmind-onboardComplete automated onboarding: analyzes codebase, creates package, and generates standards & commands via CLI.
• packmind-update-playbookUse when updating, adding, fixing, changing, or deprecating Packmind playbook artifacts (standards, commands,
• packmindhub-skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to c
• packmol-generate-mixtureA tool for generating initial packed molecular configurations (XYZ format) from single-molecule structures by
• PacktPublishing/Design-Multi-Agent-AI-Systems-Using-MCP-and-A2ADesign Multi-Agent AI Systems Using MCP and A2A, by Packt Publishing
• pacmanRetro arcade-inspired design with pixel fonts, dotted borders, playful high-contrast colors, and 8-bit game ae
• pacsomaticOperator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs. Use this skill when th
• paddleProduction-ready AI coding skills for APIs. Installable skills for Claude Code, Cursor, Codex CLI, Gemini CLI,
• paddle-ui-skillsPaddle's UI design system. Use when building interfaces inspired by Paddle's aesthetic - light mode, Inter fon
• paddle-webhooksReceive and verify Paddle webhooks. Use when setting up Paddle webhook handlers, debugging signature verificat
• padrao-ptsAplica o padrão PZCT-PTS100 (Português Técnico Simplificado, citado como STP) a textos objetivos: guias, e-boo
• padremprendedor-create-codex>
• padremprendedor-create-spec>
• page-analysisAnalyze web page content, structure, and layout to understand what a page contains and how it is organized. Tr
• page-auditOperator-grade AI agent skills for Claude Code, Cursor, Codex, and opencode.
• page-briefCreate OR review a page-brief — the artifact BETWEEN a wireflow and the full PRD. It turns each unique page/sc
• page-builderUse when generating frontend pages and components. Integrated page and component construction, generating comp
• page-croWhen the user wants to optimize, improve, or increase conversions on any marketing page — including homepage,
• page-cro-thวิเคราะห์ landing page + เสนอวิธีเพิ่ม conversion | สำหรับ นักการตลาด ครีเอเตอร์ฟรีแลนซ์ . Triggers when user
• page-layout-builderGenerates complete page layouts and shells for common patterns (dashboard, authentication, settings, CRUD page
• page-level-tdd-testing创建页面级集成测试，覆盖 loading/empty/error/success/auth 等全状态，遵循 TDD 的 RED→GREEN→REFACTOR 流程。同时基于产品需求自动枚举所有交互流程和非正常状态 UI
• page-load-animationsFix janky page-load animations, layout shift, or skeletons in a Sui dapp. Use when the user wants to fix loadi
• page-monitoringWeb page monitoring, change detection, and availability tracking. Use when tracking content changes, detecting
• page-play-builderUse when the user asks to "build programmatic SEO pages", "generate pages at scale", "rank on a high-authority
• page-speedPage speed optimization guidelines and implementation patterns. Ensures all funnel pages meet Core Web Vitals
• page-stylingDefine agentconfig.org page layout and hero styling for new pages that match the site.
• page-template-libraryUse when the user says 'save this as a template', 'create a playbook from this page', 'capture this layout', o
• page-transition-animationThis skill should be used when the user asks to "animate page or route transitions", "add a page transition or
• page-transitionsUse when implementing route changes, view transitions, modal opens/closes, or navigation animation in web and
• page-weight-budgetAudit a page's weight against a performance budget — total transfer bytes, request count, render-blocking JS/C
• page.details/details-pageManage your details.page link-in-bio from Claude: edit details, post updates, read analytics.
• page.invoker/mcpDeploy forms and sites to live URLs from AI conversations with automatic form capture.
• page.quicky/quickypagePublish, update, read, rename, and share single-URL web pages from any AI agent.
• pagerdutyEvery PagerDuty incident, on-call and service operation from the terminal, plus a local SQLite mirror that ans
• pagerduty/pagerduty-mcp-serverPagerDuty's official MCP server for incident management and on-call operations
• pagesRoot index for the pages-* family — a five-step pipeline that deploys a Vite project to GitHub Pages via GitHu
• pages-build-viteLocally builds the Vite project and verifies the dist/ output before committing. Auto-detects package manager
• pages-commit-viteStages and commits the GitHub Pages configuration files to the local git repo. Commits .github/workflows/deplo
• pages-prepare-vitePrepares a Vite project for GitHub Pages deployment via GitHub Actions. Patches vite.config.ts with the correc
• pages-publish-viteMonitors the GitHub Actions deployment workflow and reports the live GitHub Pages URL. Polls the workflow run
• pages-push-vitePushes the current branch to the git remote, triggering the GitHub Actions workflow that builds and deploys th
• paginated-reportAuthor, validate, publish, and test Power BI paginated reports in the RDL format. Automatically invoke when th
• paginationGenerates pagination infrastructure with offset or cursor-based patterns, infinite scroll, and search support.
• paiKaizen AI core. The authoritative reference for how PAI works. USE WHEN KAI system, how PAI works, PAI documen
• pai-skills-rootIndex of all PAI skills.
• paid-acquisitionRun profitable paid advertising end to end: strategy, creative, targeting, testing, and measurement across Met
• paid-adsThis skill should be used when the user asks "should I run ads", "paid ads", "run ads", "Meta ads strategy", "
• paid-ads-amazonPlan and review Amazon Ads with margin-aware ACoS, product, and search-term guardrails. Use for Amazon adverti
• paid-ads-chatgptPlan and review ChatGPT Ads experiments without assuming ad inventory, account access, or platform capabilitie
• paid-ads-creativeCreate grounded paid-media creative concepts, copy angles, refresh hypotheses, and measurable test briefs acro
• paid-ads-guideExplain NotFair's paid-ads skills, installation, platform boundaries, account connections, and current product
• paid-ads-integrationsDiscover, connect, and verify NotFair paid-ad integrations and their actual capabilities. Use when asked to co
• paid-ads-launchPlan and prepare a new paid-media campaign or cross-channel test before it can spend. Use when asked to create
• paid-ads-linkedinAudit, diagnose, plan, and safely operate connected LinkedIn Ads accounts through the NotFair MCP, with an exp
• paid-ads-optimizeDiagnose wasted paid-ad spend, pacing, and allocation, then propose safe evidence-backed optimizations. Use fo
• paid-ads-reviewProduce a read-only, evidence-based paid-media performance review across connected platforms or supplied expor
• paid-ads-setupConnect NotFair paid-ad accounts and establish reusable campaign context. Use when setting up paid media in a
• paid-ads-tiktokPlan and review TikTok Ads creative experiments with measurement, rights, and conversion guardrails. Use for T
• paid-ads-xAudit, diagnose, and safely operate connected X Ads (Twitter Ads) accounts through the NotFair MCP. Use for X
• paid-advertisingBuild and manage paid advertising campaigns across B2B platforms — LinkedIn Ads, Google Ads, Meta (Facebook/In
• paid-channel-prioritizerFor founders who don't know where to start with paid ads. Analyzes ICP, competitor ad presence, budget constra
• paid-creative-aiWhen the user wants to create AI-generated ad creative, test performance creative, manage creative fatigue, or
• paid-extension-stripe-licensingMonetize a client-side app (Chrome/Firefox extension, desktop app, or any downloadable code) with a free tier
• paid-measurement-loopUse when the user asks to "read back" a paid campaign change, "did this ad change work", or "compare ROAS/CPA
• paid-media-strategyA discipline for running paid media that does not light money on fire. Hypothesis writing for paid spend, chan
• paid-social-strategyB2B paid social strategy — LinkedIn, Meta, TikTok ad platform strategy, audience building, creative testing, b
• paintPaint a complete visual universe with genjutsu - art direction brainstorm, design system, implementation, audi
• painterProfessional painter with 12+ years in residential and commercial painting. Specializes in surface preparation
• painterly-stylePainterly art direction spanning watercolor and oil-painting looks for Blender using soft edges, pigment textu
• pair企画・設計・実装・デザインの壁打ちを短い反復で進める。アイデアの整理、技術選定の相談、設計方針の議論、プロトタイピングの方向性検討で使う。
• pair-agentPair a remote AI agent with your browser. (gstack)
• pair-modeWhen activated, Claude becomes a pair programming partner rather than a code-generation tool. Explains reasoni
• pair-programPair-programming protocol for collaborative coding. Codex narrates each change briefly before writing, keeping
• pair-programmingAI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality mo
• pair-trade-screenerStatistical arbitrage tool for identifying and analyzing pair trading opportunities. Detects cointegrated stoc
• pairingBuild work collaboratively in reviewable pieces, handing each piece back for review before starting the next,
• paletteImproving usability, interaction quality, cognitive load reduction, feedback design, and a11y compliance. Use
• palette-stylistCreate cohesive UI color systems from vibes and reference images. Use when starting a new page/component, unif
• palmier-pro-shortsVertical short-form video editing workflow using Palmier Pro (the local desktop NLE controlled via MCP) instea
• paloaltonetworks-shipShip current branch — CI, SonarCloud, code review, security review, fix all issues, merge. Assumes code is alr
• pandadocEvery PandaDoc endpoint, plus an offline document pipeline no other PandaDoc tool has - stalled deals, aging
• pandasPandas data manipulation with DataFrames. Use for data analysis.
• pandas-aggregations-groupbys-syntaxGuidelines and instructions for Pandas aggregations groupbys syntax
• pandas-csv-import-parser-parametersGuidelines and instructions for Pandas CSV import parser parameters
• pandas-data-analysisSkill de engenharia e análise de dados com Pandas e NumPy. Contém boas práticas de vetorização, method chainin
• pandas-data-analystAgente Cientista e Analista de Dados. Responsável por ler, processar, limpar e analisar dados estruturados uti
• pandas-data-cleaningCleans messy tabular datasets in pandas end-to-end — fixing dtypes, parsing dates and numbers, standardizing t
• pandas-dataframe-columns-selectorsGuidelines and instructions for Pandas DataFrame columns selectors
• pandas-datetime-column-parsing-rulesGuidelines and instructions for Pandas datetime column parsing rules
• pandas-idiomsVectorised transformations, groupby patterns, and the chained assignment that appears to work until it does no
• pandas-memory-usage-optimizationsGuidelines and instructions for Pandas memory usage optimizations
• pandas-mergejoin-syntax-alignmentsGuidelines and instructions for Pandas merge/join syntax alignments
• pandas-proPerforms pandas DataFrame operations for data analysis, manipulation, and transformation. Use when working wit
• pandas-qaSkill de Quality Assurance para pipelines de dados Pandas. Checklist de validação de schemas, testes de transf
• pandas-qa-engineerAgente QA Engineer para pipelines de dados. Responsável por validar a qualidade de dados, rodar testes unitári
• pandoc-pdf-generationPDF generation from markdown via Pandoc/XeLaTeX. TRIGGERS - markdown for PDF, print document, pandoc
• panel-node-pack-syncKeep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp
• panel-of-expertsMulti-persona expert panel framework for critical analysis, refinement, and creative insight
• panewsEntry point for reading PANews cryptocurrency / blockchain news, market narratives, and Polymarket smart money
• panews-creatorCreate and manage articles on the PANews platform. All operations require a valid user session. Triggers: writ
• panews-web-viewerRead public PANews website pages as Markdown. Use for homepage, article-page, and column-page reads.
• panin-glitch-critiqueEvaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emot
• papanito-github-enterprise-eu-adminspecialized protocol for GHEC on ghe.com with EU Data Residency. Handles enterprise governance, IAM, audit str
• papanito-lazyvim-config-engineerspecialized protocol for Neovim/LazyVim configuration. Handles lazy.nvim plugin specs, Lua API integration (Sn
• papanito-nixos-expert-protocolspecialized protocol for NixOS system architecture and debugging. Handles declarative configurations, Flakes,
• papanito-packer-imaging-expertspecialized protocol for automated machine image creation using HashiCorp Packer, OS auto-installs (Kickstart/
• papanito-swiss-legal-expertspecialized protocol for Swiss law queries (Federal and Cantonal). Triggers on topics like Fedlex, BV, OR, ZGB
• papanito-terraform-platform-engineerspecialized protocol for Terraform architecture and module engineering. Focuses on HCL 1.x standards, provider
• paperPaper-textured, print-inspired design with minimal colors, clean serif/sans typography, and tactile surface qu
• paper-2-webThis skill should be used when converting academic papers into promotional and presentation formats including
• paper-abstractPaper 摘要提炼命令（正文→摘要提炼器）。当用户已有论文正文要写摘要、提炼摘要、凝练摘要、生成 abstract、整理论文摘要、学位论文摘要、期刊投稿摘要、关键词，或说"帮我写摘要""从正文提炼摘要""摘要怎么写""
• paper-agentFull academic manuscript skill for quantitative-science papers, currently calibrated for hydrology and water-r
• paper-analysisDeep analysis of AI research papers with type-specific prompts. Covers benchmark papers, methodology papers, a
• paper-analyzer将学术论文转化为深度HTML长文。6轮强制工作流、代码仓库搜索、公式渲染、Mermaid图表。 3种写作风格，输出可直接分享的精美HTML页面。
• paper-anchor文献支撑补齐命令（论断—支撑对照器）。当导师或审稿人说"这段缺文献支撑""文献综述不足""缺少与已有研究的对比"， 或用户要给已写好的论断补引用、问"这句话需要引用吗""哪些段落没引用""帮我找支撑这个观点的文献""我这
• paper-audit-claimsAudit claims, causal chains, and conclusions in the manuscript or project design docs for scientific rigor. Us
• paper-autoratersRun the four paper-quality autoraters from PaperOrchestra (arXiv:2604.05018, App. F.3) — Citation F1 (P0/P1 pa
• paper-backup-before-word在编辑任何 .docx / Word 文件之前，必须先用 cp 创建带时间戳的备份副本， 并优先评估"用 markitdown 转 LaTeX 后再改"是否更安全； 只有在确认必须直接编辑 .docx 时才动手，且改完后
• paper-bananaAcademic diagram and workflow aesthetic evolution engine.
• paper-bilibili-uploaderValidate and upload narrated paper videos to Bilibili with biliup. Handles required landscape-first/portrait-s
• paper-captureResolve a paper from a DOI, arXiv id, URL, or Author-Year-keyword into the Obsidian vault. Fetches metadata, d
• paper-claude-md-bootstrap开始任何新的论文写作项目时（新建项目目录、第一次开会话、还没有 CLAUDE.md 文件）， 在写任何论文内容、改任何文件之前，必须先帮用户建一份项目级 CLAUDE.md， 把研究主题、投稿目标、术语保护清单、文件结构
• paper-comic论文方法图解——用视觉图解彻底讲清楚一篇论文到底做了什么、怎么做的。 自动分析论文核心方法，先推荐封面/概述图/机制细节图的生成方案，必须由用户确认范围、张数、语言、风格后再生成。 支持温暖笔记风和论文框架图风。
• paper-confirm-before-doing论文写作中遇到任何模糊指令（改、整理、润色、重写、找出、统一、清理、看看、处理一下…）， 在调用任何写文件 / 编辑文件 / 批量操作工具之前，必须先用一段话向用户陈述 「我打算怎么做、改哪里、不改哪里」，并明确等待用户
• paper-dailyPaper 每日学术雷达命令（抢发检测 + 新发泛读）。当用户手头有研究想法（RQ / 方法 / 想投的会议）、想确认是不是已被人抢发、或想每天泛读该方向新发论文时使用——即使用户只说"今天 arXiv 有什么新论文""
• paper-deck将论文、技术文章或知识内容制作成高真实感的 AIGC 幻灯片。先做叙事结构和逐页视觉导演，再调用生图模型生成每一页 16:9 slide image，最后合成为 PPTX/PDF。适合论文汇报、组会、公开课、技术分享、商
• paper-digestProduce a content/knowledge digest of ONE paper for fast absorption of its full content — not a quality critiq
• paper-disclosePaper AI 使用说明生成命令（披露汇编器）。当用户要写论文投稿的 AI 使用说明、AI 使用披露、AI 辅助声明、学位论文 AIGC 使用报告,或说"帮我生成 AI 使用说明""要交一份 AI 披露""答辩材料要附
• paper-doctorPaper 环境就绪度体检命令。当用户要检查 Paper 核验/检索环境能不能用、数据源通不通、凭证配没配、运行环境是否满足要求，或说 doctor / 体检 / 自检 / 环境检查 / 能不能用 / 跑不跑得起来 /
• paper-downloadUse this skill when the user wants to download paper PDFs by DOI(s). Triggers: "下载这个/这几个 DOI的 PDF/全文", "把这个 DO
• paper-download-arxiv-paper-sourceDownload the TeX source (e-print tar.gz) of an arXiv paper from an arXiv URL or bare ID, and unpack it into pa
• paper-downloadingDownload, organize, and document research papers for AAO workflows using lawful access paths. Use when finding
• paper-draftPaper 分段正文共写命令（段落正文初稿共写器）。当用户已有论文大纲（/paper-outline 产物或手写大纲）、要逐段展开正文、起草段落、写论文正文、把大纲要点展开成段，或说"帮我把这段引言写一下""这段正文怎么
• paper-fetchUse whenever the user wants to obtain, download, or fetch a paper's PDF — given a DOI, an arXiv id, a paper ti
• paper-figurePaper 图表可视化辅助命令（B 诊断 + C 设计建议双模式自适应）。当用户要查图表、图表诊断、图表设计、画图建议、该用什么图、图注怎么写、配色选什么、色盲友好、坐标轴规范、误差棒标注，或说"帮我看看这张图""图表有
• paper-figuresProduce publication-quality statistical figures and tables for scientific papers, end-to-end from the paper's
• paper-framework-figure-studio-proHuman-in-the-loop research-paper framework figure workflow from S0-PAPER-FOUNDATION through terminal S5-CANDID
• paper-fulltext-harvestBatch download academic paper full-text (PDF/XML) from a list of DOIs. Handles 25 DOI prefixes across 19 publi
• paper-glossaryUse when building reusable Obsidian glossary notes from an existing paper source manifest, optionally with a r
• paper-helpPaper 命令导航器。当用户问 Paper 能做什么、有哪些命令、该用哪个命令，或说 help / 帮助 / 怎么用 / 命令一览 / 不知道从哪开始时使用——即使用户只说"我想写论文但不知道用什么"也应使用。行为铁律
• paper-importPaper 题录导入命令（题录整理器 + 题录-草稿一致性核对器）。当用户有从知网/Zotero/EndNote 导出的题录要批量整理、整理参考文献、题录入库、做题录与草稿引用的一致性核对、查哪些草稿引用有对应题录、查题
• paper-init为研究项目搭建标准科研工作目录的脚手架命令。当用户要开始一个新研究项目或新论文、想初始化或规范科研项目的目录结构、要搭多项目科研工作区，或提到 paper-init、科研工作目录时使用——即使用户只是说"帮我建个放论文材
• paper-logicPaper 论证链检查命令（结构对应检查器）。当用户已有论文大纲、要查论证逻辑、查 RQ 与方法结果结论是否对应、查论证链是否闭环、查论文逻辑结构，或说"帮我查查论证有没有问题""我的逻辑完整吗""RQ 和结论对应吗""
• paper-logical-consistency当用户改动论文里的核心声明（研究问题、核心论点、因果关系、边界条件、假设、关键结论、对已有研究的态度）时， 必须先扫描该声明在全文其他章节的出现位置，列出来让用户核对哪些需要联动修改，再开始动手。 本 Skill 抓的是
• paper-lookupUse as a metadata and discovery fallback for papers, preprints, citations, DOIs, PMIDs, and open-access signal
• paper-mapMaintain the cross-device paper index at {vault}/00-Claude-Context/paper-map.md. Use for "update paper-map", "
• paper-methodPaper 研究设计参谋命令（方法-RQ 匹配检查器 + 方法类引导器）。当用户已有研究问题（RQ）要定研究方法、检查方法能否回答 RQ、选什么方法类、查方法与 RQ 匹配度、研究设计行不行、涉人类被试要理伦理审查提示清
• paper-narrativeJudge and reshape the story told by a manuscript and its figure deck. Use when revising paper structure, testi
• paper-notesWrite structured notes for each paper in the core set into `papers/paper_notes.jsonl` (summary/method/results/
• paper-one-session-one-task当用户在一次对话里同时提出多个论文写作任务（"顺便也帮我..."、"另外..."、"还有..."）， 必须先把这些任务列出来让用户挑一个，拒绝在同一个会话里串行做完所有事。 Use when 用户的一条请求里出现两个以上
• paper-opportunity-radarRun a cumulative daily or retrospective sweep of research papers on a chosen topic, audit their claims, method
• paper-orchestraOrchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstruct
• paper-outlinePaper 论文大纲命令（结构草案共写器）。当用户已有研究问题（RQ）和文献笔记、要搭论文骨架、起草章节大纲、写论文结构、整理写作框架，或说"帮我把论文大纲列一下""论文应该怎么组织""章节怎么分""我有 RQ 和文献、
• paper-parallel-audit在执行 ≥ 30 条目的批量核查 / 批量修改任务（引用核查、术语一致性检查、格式统一、文献元数据补齐）时， 必须采用"派多个 Agent 并行 + 每个 Agent 输出 JSON + 主进程汇总落盘 + 分批断点续跑
• paper-pilot-before-batch在执行任何 ≥ 30 条目的批量任务（批量改文件、批量核查引用、批量重命名、批量格式统一）之前， 必须先在 3–5 个样本上跑一遍，把样本结果给用户看，确认逻辑正确后再推全量。 Use when 用户请求处理"全部"、"
• paper-plotPaper 绘图代码生成命令（内建于 paper-figure，可独立调用）。当用户要生成绘图代码、plot 代码、画图代码、matplotlib 代码、ggplot2 代码、帮我生成图表代码、帮我写画图脚本、生成柱状图
• paper-polish-pipelineStaged, diagnosis-driven academic paper polishing pipeline (bilingual 中文/English). Use to revise a paper from
• paper-proposalPaper 开题报告组装命令（多源汇聚组装器）。当用户要写开题报告、组装学位论文开题材料、按中文学位论文制度节点整理立项文档，或说"帮我组装开题报告""开题报告怎么写""开题要准备什么""选题依据怎么写""文献综述部分帮
• paper-protect-terminology在跨多文件批改、术语统一、整篇论文润色、章节重写等可能改动专业术语 / 缩写 / 人名 / 概念命名的操作之前， 必须先显式列出"保护术语清单"，让用户确认哪些词不得被同义替换或改写，再开始执行。 Use when 用户
• paper-readingReads and analyzes academic papers (arXiv preprints, conference / journal PDFs, Zotero items) at three configu
• paper-reading-zh中文论文精读工作流。Use when the user provides a paper anchor such as a PDF, arXiv/OpenReview/ACM/IEEE/venue page link,
• paper-redteamSimulate rigorous, fair peer review on a paper — in two modes. (A) Red-team YOUR OWN draft before submission t
• paper-reviewSet up and run the botference document-review interface (Google-Docs-style comments on rendered LaTeX/Markdown
• paper-revisePaper 修订辅助命令（修订建议对照表 + 逐点回复信起草器）。当用户投稿/答辩后收到审稿意见要写回复信、要逐点回复审稿人、要改稿、要准备 point-by-point response、要 response lett
• paper-screenPaper 系统综述筛选命令（PRISMA 2020 筛选台账 + 流程图生成器）。当用户要做系统性文献综述、做 PRISMA 筛选、定纳入排除标准、两轮筛选文献、文献去重、要 PRISMA 流程图、要数据提取表、要偏倚
• paper-searchAcademic paper search via Google Scholar using Serper API
• paper-search-proFind academic papers across up to 7 sources (OpenAlex / Semantic Scholar / CrossRef / PubMed / arXiv for Engli
• paper-search-usageThis skill should be used when user asks to "search for papers", "find research papers", "search arXiv", "sear
• paper-signalPlan, art-direct, generate, edit, and quality-check tactile minimal-zine bitmap imagery from almost any subjec
• paper-signal-art-directorArt-direct and generate one high-craft minimal-zine bitmap from a landscape, portrait, person, object, product
• paper-signal-auditInspect and diagnose minimal-zine posters, photo restyles, editorial images, and social-card series for subjec
• paper-signal-seriesPlan, write, art-direct, generate, and package a coherent 2-10 image minimal-zine social series from notes, ar
• paper-slides-to-videoConvert Beamer PDF slides into a fail-closed narrated MP4 with page-aligned narration, TTS audio, cover, and u
• paper-stylePaper 风格校准命令（全文风格一致性校准 + 个人风格基线 + AIGC 误判申诉特征陈列）。当用户要查全文文风是否一致、要校准各章语体、要建立自己的写作风格基线供后续起草复用、或论文被 AIGC 检测判为 AI 生
• paper-submitPaper 投稿准备命令（投稿材料清单整理器 + 期刊常见投稿要求陈列）。当用户论文写完要投稿、要准备投稿材料、要写 cover letter、要整理投稿 checklist、要查期刊投稿要求、要准备投稿文件包、或说"帮
• paper-summarizerAgents should invoke this skill for academic or technical papers, arXiv/PubMed/IEEE/ACM links, PDFs, methodolo
• paper-summaryWrites expert academic paper summaries for social science research, particularly political science and applied
• paper-summary-thSummarize academic research papers in Thai. Breaks down abstract, methods, findings, and limitations into easy
• paper-to-beamerAutomated pipeline: paper (PDF or TeX source) → SUSTech Beamer slides (11-section 论文分享 structure) → compiled P