Recently Added
Fresh skills just added to the collection. Be the first to try them out!
k-kernel — REPL-agnostic cell execution for AI agents
by rangersui
```
ai-startup-due-diligence
by PiroteQueen
"Evidence-driven due diligence for AI startups: turns decks, interviews, demos, and public research into an auditable evidence ledger, then derives a verdict and decision documents. Use when evaluating an AI startup or investment target, reviewing a pitch deck or data room, comparing companies' AI products, preparing investor or founder questions, writing a DD memo or IC note, or assessing VC-fit, PMF, GTM maturity, fundability, and red flags."
abdurohman-karim-design
by abdurohman-karim
Use this skill to generate well-branded interfaces and assets for Abdurohman Karim's portfolio brand — a strict-monochrome, crypto/web3-minimal aesthetic for a fintech backend developer. Use for production or throwaway prototypes/mocks. Contains design guidelines, colors, type, fonts, icons, and UI kit components for prototyping.
Sv Audio Recording
by harrylabsj
Generated for project short-video-skills-2026-04-27
postkit
by varunchopra
PostgreSQL-native identity, configuration, metering, and job queues. SQL functions that work with any language or driver. Use when working with user management, sessions, permissions, access control, login/logout, MFA, password resets, relationship-based access, versioned configuration, prompts, usage tracking, quotas, billing periods, or background jobs in PostgreSQL. Covers authn (user/session management), authz (ReBAC permissions), config (versioned key-value storage), meter (usage tracking with reservations), and queue (job scheduling with retries and dead letters).
nlm-to-editable-pptx
by Laggom
Use when the user has an image-based / non-editable PPTX or PDF (especially exported from NotebookLM, or any "scanned" deck where the slides are full-page pictures with no selectable text) and wants it converted into an editable PowerPoint with real, editable text boxes. Trigger this whenever the user mentions NotebookLM slides, "make this PPT editable", "the text isn't selectable", "convert this PDF deck to editable slides", Korean slide OCR, or rebuilding a deck so the text can be edited — even if they don't say the word "skill". Works on Windows/macOS/Linux and is portable to Databricks.
ui-ux-doctor
by rahulcommercial
"Zero-dependency UI/UX bug doctor for React + FastAPI apps. Finds and fixes button issues, rendering bugs, accessibility gaps, component problems (modals, dialogs, sidebars/drawers), form/input/textarea issues, light/dark mode (theming) gaps, and React<->FastAPI integration mistakes, then suggests enhancements and verifies the fix. Pure Python stdlib — no pip, no npm, no network — safe for locked-down / offline / office machines. Actions: find, detect, scan, audit, review, debug, diagnose, fix, repair, improve, enhance, test, verify UI/UX. Elements: button, modal, dialog, sidebar, drawer, form, input, textarea, select, navbar. Symptoms: button does nothing, button not clickable / not keyboard accessible, modal has no escape, no focus trap, input has no label, textarea unlabeled, form reloads page on enter, no dark mode, white flash in dark mode, list re-renders wrong, stray 0 on screen, missing key warning, input loses focus, infinite re-render, fetch loop, blank page, CORS error, data not loading, image no alt, screen reader. Topics: accessibility, dark mode, theming, focus management, forms. Stack: React, JSX, TSX, Tailwind, FastAPI, Vite, fetch, CORS. Use after writing or before shipping UI code, or when a UI element misbehaves."
workday-mcp
by chrischall
Read your Workday HR data — tasks, pay, benefits, compensation — via MCP through your own signed-in session. Triggers on phrases like "check my workday", "what's in my workday", "read my workday compensation", "my workday benefits", "pull this workday page", or any request involving your Workday tasks, pay, or benefits. Read-only. Requires workday-mcp installed and the fetchproxy extension active (see Setup below).
microcap-pnd-system
by Lzh-xbccz
"极端山寨P&D交易系统 v3.0 — 全自动深度分析。一次扫描完成发现+基本面+合约+垃圾币过滤+量价诊断+综合评分+交易建议。检测器/追踪器/退出信号器/鲸鱼监控四件套。"
wiki-builder
by tianaegidi
Create and edit Confluence wiki pages on wiki.cfdata.org. Use this skill whenever the user asks to create a wiki page, build a dashboard, make a Confluence page, set up wiki documentation with macros (Jira issues, panels, status lozenges, tables, charts, roadmaps, table filters), edit existing pages, or replicate/copy existing wiki pages. Also use when the user mentions wiki.cfdata.org, Confluence, or wants to revamp/redesign a wiki page.
chinese-ppt2
by brycewang-stanford
Upgrade of chinese-ppt for Chinese Beamer decks (xelatex + ctex + fandol, CUFE template). Same 7-section outline and X→M→Y framework, but adds (a) mandatory 1.3 line-spacing + 3pt paragraph spacing, (b) overflow-prevention line budget + balanced split-frame rules, (c) prose rewrites that strip AI-ish "关键比较/理论映射" labels and redundant 章节括号注释, (d) stricter CJK-space + middle-dot rules, (e) retrofit workflow for existing chinese-ppt decks, (f) mandatory local linespread reset inside TikZ / table / fixed-geometry frames. Use for "做中文学术PPT 2 版"、"中文 Beamer 改进版"、"答辩 PPT chinese-ppt2"、"防越界 PPT"等请求。用户在 Overleaf 编译，只产出 .tex + figures/，不要附加 compile 脚本。
fix-chinese
by brycewang-stanford
PROACTIVE SKILL — automatically apply whenever writing, generating, or editing any text that is mainly in Chinese. No user trigger needed. Also use when the user explicitly asks to "fix Chinese", "修改中文", "去翻译腔", "去AI味", "fix Chinese formatting", or "review Chinese text". Eliminates AI-sounding expressions and translation artifacts. Enforces Chinese-English mixed formatting rules (spacing, punctuation, bold formatting).
chinese-quote-converter
by brycewang-stanford
Convert English straight quotation marks ("...") to Chinese curved quotation marks ("..." U+201C/D). Use when processing Chinese text documents, markdown files, or any content that needs proper Chinese typography with directional quotes. Triggers on keywords like "转换引号", "中文引号", "英文引号转中文", "quote conversion", "convert quotes".
Novelty Check Skill
by brycewang-stanford
🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文，并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.
Foreign-CF-Study
by brycewang-stanford
根据研究者提供的研究计划书（Research Proposal）执行基于外国（美国/欧盟/英国/日本/跨国）制度环境的公司金融类实证研究全流程。启动后第一件事：根据计划书的主题、识别策略、贡献边际与样本范围，从外国 CF 顶刊池（AER/QJE/JPE/JF/JFE/RFS/JFQA/JAR/JAE/MS/JCF/JBF 等 25+ 期刊）中推荐 5 本最匹配的目标期刊（[J1]–[J5]），等待研究者明确选定一本；该期刊决定 main.tex 的 bibliographystyle、Section 骨架、Introduction 风格与表注规范。然后用 Python 完成数据清洗、描述性统计、基准回归、内生性检验（IV/2SLS、DML）、平行趋势、异质性、机制、稳健性检验与图表绘制。LaTeX 表格和图像严格遵循 template/ 示例格式，研究逻辑与排版严格遵循 rule/ 下的《通用实证研究逻辑与规范总结》与《回归表写作规范总结》。数据集与政策集从 asset/ 中按计划书中的关键词检索（WRDS / NBER/Fed releases / FRED / 全球宏观库）。当计划书预期的实证结果无法实现时（系数不显著、平行趋势不通过、IV 弱工具、机制不成立等），skill 自动切换备选方案直至完成研究项目。最终交付物：Python 代码 + LaTeX 表格 + 图像（.pdf/.png）。触发条件：研究者提交研究计划书（含 X→Y 假设、识别策略、样本、政策冲击等）。
ols-regression
by brycewang-stanford
Econometrics skill for OLS regression and linear models. Activates when the user asks about: "run OLS", "linear regression", "ordinary least squares", "interpret regression results", "heteroskedasticity", "multicollinearity", "regression assumptions", "robust standard errors", "GLS", "WLS", "fit a regression model", "check regression diagnostics", "OLS假设", "最小二乘法", "线性回归", "回归系数", "残差检验", "异方差", "多重共线性", "普通最小二乘", "稳健标准误", "回归诊断"
Command Development
by brycewang-stanford
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
iv-estimation
by brycewang-stanford
Econometrics skill for instrumental variables and treatment effect estimation. Activates when the user asks about: "instrumental variables", "IV estimation", "2SLS", "two-stage least squares", "endogeneity", "weak instruments", "first stage", "Sargan test", "overidentification", "propensity score matching", "PSM", "average treatment effect", "ATT", "LATE", "local average treatment effect", "endogenous regressor", "instrument validity", "工具变量", "两阶段最小二乘", "内生性", "弱工具变量", "倾向得分匹配", "平均处理效应", "处理效应", "局部平均处理效应"
data-cleaning
by brycewang-stanford
Clean and transform messy data for analysis in Python, R, or Stata
journal-digest
by brycewang-stanford
经济金融顶刊文献速递与选题建议生成器。通过RSS和网页抓取获取经济学、金融学、会计学顶级期刊的最新论文， 筛选公司金融相关文献，生成中文综述摘要和研究选题建议。 当用户提到"期刊速递"、"文献周报"、"论文速递"、"最新文献"、"journal digest"、"paper digest"、 "选题建议"、"研究选题"、"顶刊追踪"、"文献追踪"、"周报"时触发此技能。 即使用户只是说"帮我看看最近有什么新论文"或"最近顶刊发了什么"，也应该触发。
agent-browser
by brycewang-stanford
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
data-fetcher
by brycewang-stanford
Fetch economic data from FRED, World Bank, BLS, OECD, and Yahoo Finance
markitdown
by brycewang-stanford
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.
did-analysis
by brycewang-stanford
Econometrics skill for Difference-in-Differences (DID) analysis. Activates when the user asks about: "difference in differences", "DID", "DiD", "diff-in-diff", "parallel trends", "treatment group", "control group", "pre-treatment", "post-treatment", "policy evaluation", "natural experiment", "staggered DID", "event study regression", "two-way fixed effects DID", "callaway santanna", "sun and abraham", "双重差分", "倍差法", "平行趋势", "处理组", "对照组", "政策评估", "事件研究", "交错DID", "渐进处理"