В каталоге 183 730 навыков в 14 категориях.
Run a deliberation panel of lenses on one target (a conclusion, argument, bridge or draft section) under the checked pan...
Multi-provider deliberation panel for COMPLEX, multi-view questions — architecture, strategy, market research, and codeb...
Orchestrate a rigorous multi-agent implementation, review, and verification panel inside Herdr. Use when the user reques...
Architectural fit and cross-layer integration review of a delivered change for the review panel. Read-only. JSON report...
Adversarial correctness review of a delivered change for the review panel. Read-only. Hunt reachable bugs, concurrency,...
Master interactive dashboard and application development with Panel and Param. Use this skill when building custom web a...
Econometrics skill for panel data models. Activates when the user asks about: "panel data", "fixed effects", "random eff...
Hosts interactive expert panel discussions on any topic. Dynamically generates diverse master-level expert personas, fac...
Audit and harden a 3x-ui panel — scoped API tokens instead of admin passwords, credential rotation, fail2ban and per-cli...
Use when the task is panel method setup, source or doublet panels, Neumann or Dirichlet boundary conditions, Kutta condi...
Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates....
Get the take of the specific experts a situation actually needs — a lawyer, a therapist, an accountant, a doctor-minded...
On-demand procedures for the ComfyUI sidebar panel agent that are too long to sit in the system prompt. Read it when a t...
This skill should be used when the GM needs panel creation ideas or atmosphericenhancement suggestions. Triggers on:- "W...
Seven-role curriculum artefact review calibrated for wellbeing/SEL. Uses simulated perspectives in one session; mean>=88...
Seven-role depersonalised panel review of framework artefacts (KUD, criterion bank, LT definition, crosswalk, scope-and-...
Reviews a code target by launching a panel of specialist auditor agents and merging their reports. Use when asked to run...
Security and privacy review of a delivered change for the review panel. Read-only. Check authz, secrets, injection, SSRF...
Host interactive expert panel discussions on any topic. Dynamically generates master-level expert personas, facilitates...
Write unit and E2E tests for Grafana visualization panels and viz utilities to the conventions this repo expects. Use wh...
Turns Panelin Signal / Knowledge Antenna outputs into evaluated improvement quests and concrete implementation plans for...
Panelin Co-Work Live + Admin cotizaciones + surfaces (Admin / Gmail OCR / CRM). Use when working on Co-Work, wolfboard,...
Closes remaining GPT-Cloud drifts and go-live risks for Panelin as one system. Use when endpoints are partially deployed...
Regenerates GPT configuration artifacts so instructions, actions, routing, checklists, and knowledge packaging remain al...
Operates Panelin as a single production system, always synchronizing GPT Builder configuration with Google Cloud runtime...
Panelin-Gym: preparar el entorno local y el flujo repetible para observabilidad del asistente (chat calculadora + canal...
Live-edit the Panelin Evolution dashboard (HTML/CSS/JS) from natural language descriptions. Interprets visual modificati...
Audits Panelin repositories to find already-implemented solutions and convert them into a concrete reuse plan for GPT Bu...
Make a repository runnable in the sandbox and on the owner's computers (targets in its `.intentic/run.json`, or a Procfi...
Skill for the Panels area of paddock. 727 symbols across 76 files.
PANELSIM — bandeja multi-cuenta (repo conexion-cuentas-email-agentes-bmc): sync IMAP, clasificación, reporte PANELSIM-UL...
Entry point for reading PANews cryptocurrency / blockchain news, market narratives, and Polymarket smart money leaderboa...
Refactors Pangea Ruby code following SOLID principles, dry-rb patterns, and file size guidelines. Use when splitting lar...
Creates and tests Pangea Ruby function resources with synthesis testing. Use when creating new resources, writing synthe...
Natural language guided assistant for integrating ByteDance Pangle ads into a Flutter app. Detects the user's language a...
Invoke first for Pango backend-app development. Establish worktree, slot, test, store, and environment ownership before...
Retrieve structured Google SERP and AI Overviews, run AI Mode follow-up queries, and optionally capture screenshots thro...
Triages a live incident — stop the bleeding first, smallest safe fix next, post-mortem once stable; invoke via /panic-mo...
Expert in residential hollow space detection, hidden room discovery, and safe room planning. Helps map house dimensions,...
Panjit International MPN encoding patterns, suffix decoding, and handler guidance. Use when working with Panjit diodes,...
Create a Realsee VR space from local equirectangular panoramas using PanoToVR. Use for image-directory or manifest submi...
Lock in on a single GitHub issue and STRIKE to fix it. High-energy, surgical focus. Prowl, investigate, plan, strike, ki...
Paper-textured, print-inspired design with minimal colors, clean serif/sans typography, and tactile surface qualities.
Work with research papers and TeX documents -- read, edit, compile, review.
Paper design canvas work, done by scripts. Use to capture a website or user flow into Paper as editable frames, copy or...
Layered paper texture with tactile depth, stacked sheets, and stationery charm.
This skill should be used when converting academic papers into promotional and presentation formats including interactiv...
Use when converting academic papers into dissemination assets such as Paper2Web websites, Paper2Video video abstracts, o...
A repository to store my skill files
研究 codex 使用 skill 生成 survey 這件事
当需要将学术论文转换为宣传和展示类格式时，应使用此技能，包括交互式网站（Paper2Web）、演示视频（Paper2Video）以及会议海报（Paper2Poster）。适用于论文传播、会议准备、创建可探索的学术主页、生成视频摘要，或基于...
Paper 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""我的论文摘要""ab...
Use when an agent needs to resolve OA URLs, probe PDF endpoints, and download local paper artifacts from DOI or URL inpu...
Paper Analysis
根据arXiv论文网址自动下载PDF并进行多维度分析，包括文本提取、词频分析、语音播报、播客对话生成、交互式网页、PPT、总结图和引用分析
论文与长文深度分析助手，运用SCQA、5W2H、批判性思维、逆向思维、心智模型、第一性原理、系统思维、六顶帽子10+思维框架，支持URL/PDF/DOCX/TXT输入，四级深度（15~120min+），输出问题解决/学习笔记/写作参考/决策...
深度分析单篇论文，生成详细笔记和评估，图文并茂
自动分析Zotero库中的文献，生成带LaTeX公式的Markdown报告，使用Auto-Annotation工具将AI的深度见解以无损批注形式注入回 Zotero，并将报告上传为Zotero Note。
Transform academic papers into in-depth technical articles with multiple writing style options. Use the MinerU Cloud API...
For all readers, with a specialty in experimental and behavioral research: analyze, explain, critically read, and verify...
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""我这个论断有没有文献支持...
Turns an approved ad angle into a shot-by-shot cut-paper video ad: one of three named paper sub-styles picked from the a...
Use only when `workflow/paper-anonymizer-board.json` explicitly selects paper-anonymizer-scope-binder and names one acti...
Reviewer-style audit and submission gate for academic papers in .tex, .typ, or .pdf. Use for peer-review critique, readi...
Deep-review-first audit for Chinese and English academic papers across LaTeX, Typst, and PDF formats. Use whenever the u...
Final "author pass" for an AI-assisted ML research paper — refine from high level (story, research taste, scale vs. clai...
Run the four paper-quality autoraters from PaperOrchestra (arXiv:2604.05018, App. F.3) — Citation F1 (P0/P1 partition +...
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，且改完后必须提醒用户先打开...
Place exactly one paper order per approved ticket through exec.quote, exec.simulate, and exec.place, and report UNKNOWN...
Categorize ML/AI research papers into 11 types based on their title and abstract. Returns structured JSON with a primary...
学术辅导的检查与修订入口。用于引用真实性与参考文献格式核验、结论与论证链检查、模拟审稿或答辩、处理审稿意见和起草逐点回复；核验依赖真实证据，采纳与研究判断由用户决定。
Check a paper against its code, results and citations before submission (numbers, terms, code vs paper, formulas vs code...
Zero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a f...
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、写作风格、导师偏好...
For creators, educators, and social-video editors who need a tactile paper-collage language for narration, knowledge poi...
Plan and produce one editorial paper-collage explainer from a concept, narration line, or story beats: approve visual me...
Turn a supplied video plus transcript or 逐字稿 into review-gated handmade paper-collage motion graphics. Analyze spoken me...
Generate educational comics from academic papers, using visual storytelling to explain core ideas and innovations. Suppo...
Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says "编译论文", "compile paper", "build PDF", "生成P...
논문 원고를 쪽 수 상한에 맞추거나 군더더기, 연구 과정 이력, 과잉 한정을 잘라 간략하게 만들 때 사용. "논문 줄여", "쪽 수 맞춰", "간략화", "잘라낼 서술 찾아" 같은 요청에 적용.
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」，并明确等待用户确认后再动手。 Us...
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository fil...
Converts the final Markdown manuscript from `paper-draft` / `paper-review-loop` into a submission package for the target...
Turn travel photos with recognizable people into 3:4 posters where real photographed environments contain warm-white pap...
Paper 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""这个方向最近有什么新...
Minimal, spacious, high-end slide design for Paper boards. Use when creating or extending presentations in Paper that sh...
Create beginner-friendly deep-reading notes for journal and research paper PDFs. Use when Codex needs to learn a paper,...
Design and prototype in Paper Design (app.paper.design) — read/write designs via MCP, convert to React/Tailwind code, im...
Produce a content/knowledge digest of ONE paper for fast absorption of its full content — not a quality critique. Use wh...
Paper 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 AI 使用情况""...
Use when searching for academic papers related to a topic, finding papers similar to one already in the vault, or discov...
Use when the user wants to add source identity from PDF, URL, arXiv, DOI, note, experiment result, manual reference, or...
Paper 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 / 为什么核验不了 时使...
Paper 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""这段正文怎么展开""基于大纲写一...
Transforms output/PAPER_PLAN.md into a journal-quality Markdown manuscript draft for GIScience, GeoAI, spatial data scie...
Paper editing with built-in style constraints for academic writing quality, including anti-AI detection, LaTeX validatio...
Creates and revises branded Paper Engine illustrations featuring Yuki, the recurring polar-bear inventor, in a clean han...
当使用者说“这篇建模论文还能怎么提升”“按评分表排修改优先级”“时间不够先改什么”“给我一个论文改进清单”“要不要再加一个高级模型”时使用。基于现有草稿、模型工作包、批判 findings、评分规则和真实剩余资源建立可定位的 gap reg...
PaperCraft 用于研究论文的创新定位、工作量呈现、图文精修和透明审阅。按已有证据交付实际修订稿、黄色审阅标记与中文诊断，也支持仅审阅、局部修改、续改和实验未完成的稿件。
Use when a user asks to review or revise Chinese academic papers, theses, proposals, or research reports for formulaic,...