Loading...
Loading...
Found 2,086 Skills
Guides rollout configuration for experiments: variant splits, overall rollout percentage, and the critical disambiguation when a user mentions a specific percentage. Covers both initial setup and mid-experiment changes. TRIGGER when: user mentions a rollout percentage, asks about variant splits, wants to change distribution on a running experiment, or asks 'who sees what variant?' DO NOT TRIGGER when: user is asking about metrics, analytics, or experiment results.
A hybrid pattern where the system pauses execution to request human approval, input, or disambiguation before proceeding with critical actions. Use when user asks to "add human approval", "require human review", "human-in-the-loop", or mentions approval workflows, human oversight, or escalation.
This skill is to be used when users explicitly request "migrate LaTeX templates", "integrate old projects into ChineseResearchLaTeX", "apply old bids/papers/graduation theses/resumes to the current template", "organize Word/PDF/Markdown/scattered tex files into existing projects", or directly mention `transfer-old-latex-to-new`. The old alias `migrating-latex-templates` is also supported. This skill only migrates the main content to the content layer of the existing templates in the current repository; it must never modify the source code of public packages in `packages/`, nor modify the template styles or entry skeletons in `projects/`, and can only write to content files allowed to carry the main content in the target project.
Online Novel Topic Planning, suitable for user needs such as "I don't know what to write for a novel", "Help me come up with a novel genre", "Find online novel ideas", "Analyze which genres are popular", "Novel topic evaluation", "Which online novel genres are profitable now", "Give me some novel ideas", "Come up with a golden finger for a novel", "Help me find a popular genre", "Which novel genre is easy to become popular", "Online novel market trend analysis", "Help me plan novel topics", etc. It generates multiple sets of topic proposals and market analysis, including golden finger design, core selling points, cool point patterns, and feasibility evaluation.
Direct visual and creative work for campaigns, photography, illustration, video, and branded experiences. Use this skill whenever the user wants to brief a photographer, direct illustrators, plan a creative campaign, develop visual concepts, write a creative direction document, or evaluate creative work for fit. Triggers on art direction, photo brief, photography brief, illustration brief, campaign concept, creative concept, visual direction, mood board, look and feel, visual treatment, video direction. Also triggers when the user has approved brand identity but needs to extend it into specific creative deliverables.
Decide when DuckLake is the right MotherDuck storage pattern. Use when evaluating fully managed DuckLake, BYOB, own-compute DuckLake access, data inlining, object-storage layout, or file-aware maintenance instead of native MotherDuck storage.
Machine-learning prediction strategy framework via Longbridge Securities — walk-forward rolling training with feature engineering (MACD, RSI, Bollinger Band width, volume change rate) and a scikit-learn classifier (Random Forest / Gradient Boosting); retrains every 60 days, predicts 5-day direction; buy signal when probability > 0.6, sell when < 0.4; evaluates win rate, profit factor, and Sharpe ratio. Triggers: "机器学习", "ML策略", "预测模型", "随机森林", "梯度提升", "深度学习", "AI选股", "walk-forward", "機器學習", "ML策略", "預測模型", "隨機森林", "梯度提升", "machine learning", "ML strategy", "predictive model", "random forest", "gradient boosting", "AI stock selection", "walk-forward", "rolling training", "feature engineering", "scikit-learn", "XGBoost".
Buffett-style single-stock moat diagnostic — "Would Buffett buy this stock?" Five dimensions: business & moat / financial health / management & capital allocation / valuation & margin of safety / long-term visibility. Data from Longbridge CLI first, MCP fallback, WebSearch only for gaps. Runs cross-statement reconciliation (勾稽校验) BEFORE scoring; data-source appendix closes with a one-line reconciliation summary. Output: star-rated radar card, dimension detail, Buffett-voice narrative, mandatory holding-period education block. Triggers: "巴菲特", "护城河", "巴菲特会买吗", "价值投资", "好生意", "宽护城河", "定价权", "诊股", "巴菲特诊股", "巴菲特视角", "长期持有", "護城河", "巴菲特會買嗎", "價值投資", "寬護城河", "定價權", "診股", "巴菲特診股", "巴菲特視角", "長期持有", "Buffett", "Warren Buffett", "moat", "economic moat", "wide moat", "pricing power", "value investing", "owner earnings", "would Buffett buy", "Berkshire-style", "quality compounder".
On-chain data analysis framework — covers active addresses, whale behaviour, TVL (total value locked), DEX liquidity, and on-chain valuation metrics: MVRV (market cap / realised value), NVT (network value / transaction volume), SOPR. Longbridge provides spot crypto quotes (.HAS); raw on-chain data requires external sources (Glassnode / Dune Analytics). Triggers: "链上数据", "链上分析", "MVRV", "NVT", "活跃地址", "鲸鱼地址", "TVL", "SOPR", "链上指标", "链上估值", "鏈上數據", "鏈上分析", "活躍地址", "鯨魚地址", "鏈上指標", "鏈上估值", "on-chain data", "on-chain analysis", "MVRV ratio", "NVT ratio", "active addresses", "whale activity", "TVL", "SOPR", "on-chain valuation", "DeFi TVL", "crypto on-chain".
Security review and penetration testing: evaluate your application against OWASP Top 10, authentication security, HTTP headers, CORS, CSP, supply chain risks, and common attack vectors with browser-based validation.
Drive a remote chrome-devtools-mcp server (typically on a tailnet) over HTTPS using the chrome-devtools CLI. Use this when the user wants to navigate, screenshot, inspect, or evaluate JavaScript on a browser running on another host (e.g. a Tailscale-connected Mac mini or a CI runner) — and you don't have a local Chrome to control. Examples of triggers ("open <url> on the lab mac", "take a screenshot of the browser on host X", "evaluate this on the remote browser").
Generates performance-focused guidance for Google Cloud workloads based on the design principles and recommendations in the Performance Optimization pillar of the Google Cloud Well-Architected Framework (WAF). Use this skill to evaluate a workload, identify performance requirements, and provide actionable recommendations for resource allocation, modular design, and elasticity.