1912 个 · 按相关度排序
"Implement content-based recommendation by matching item features to user preference profiles. Use this skill when the user needs to recommend items based on attributes, solve the cold start problem for new items, or build recommendations without collaborative data — even if they say 'recommend similar products', 'items like this', or 'feature-based matching'.".
中文简介正在准备中。当前显示原文说明。
"Implement session-based recommendation from short-term user behavior sequences without long-term profiles. Use this skill when the user needs to recommend in anonymous sessions, predict next click from browsing sequence, or build recommendations for non-logged-in users — even if they say 'what should they click next', 'anonymous user recommendations', or 'browsing sequence prediction'.".
中文简介正在准备中。当前显示原文说明。
"Design hybrid recommendation systems combining multiple strategies for improved accuracy. Use this skill when the user needs to overcome single-method limitations, combine collaborative and content-based filtering, or build a production recommendation pipeline — even if they say 'combine recommendation approaches', 'best recommendation architecture', or 'cold start plus personalization'.".
中文简介正在准备中。当前显示原文说明。
Turn a raw idea into ONE honest recommendation: interview one question at a time until the problem, requirements, goals, non-goals, and constraints are CONFIRMED, then deliver a single verdict — do, don't, cheaper alternatives, trade-offs, ordered checklist, success metrics. Required: the user wants exactly ONE recommendation — not options, not a debate — and their framing is open to challenge (advise may answer a different question than the one asked). Triggers on "what should I do about X", "advise me on X", "am I approaching this right", "is this the right move". Do NOT use to be interrogated with no recommendation (→ mk:grill) — advise also interviews one question at a time, but only to reach a verdict. Do NOT use when the framing is settled and only the options are open (→ mk:brainstorming). Do NOT use to decide whether something is worth building (→ mk:office-hours). Do NOT use when you want several perspectives to argue it out (→ mk:party).
中文简介正在准备中。当前显示原文说明。
Evaluate recommender system quality for the CSX4207 Vinyl Record Store. Use whenever you must compute or report recommender metrics (Precision@k, Recall@k, HitRate@k, MRR, MAP@k, NDCG@k, coverage, diversity, novelty, serendipity, personalization), design an evaluation protocol/split, run a baseline comparison, or write the evaluation section of a course deliverable. Covers formulas, JavaScript reference implementations, and the reporting checklist.
中文简介正在准备中。当前显示原文说明。
根据学习 Claude 用法或团队引入需求，查看 Claude Academy 的课程、教程和应用实例，提供符合学习目标的资料。
深入检查PR、分支或大规模代码变更，生成HTML或Markdown报告。除差异外，还梳理系统设计与运行方式，按重要程度列出问题，并提出是否合并及如何修改的建议。
将笔记和分析资料整理为适合客户提案、技术分享或产品发布的HTML幻灯片，支持主题选择、演讲稿、演讲者视图及逐页PNG导出。
将经营决策所需的选项、风险与建议整理为HTML幻灯片，以深海军蓝和金色呈现，适合向首席执行官、战略团队及董事会说明决策依据。
Create an HTML slide deck for weekly growth reviews, connecting metrics such as stars, installs, and activation to their drivers and recommended actions. The supplied template includes presentation features and separate speaker notes.
中文简介正在准备中。当前显示英语简介。
Turn research findings stored in memory into structured reports with evidence ratings, source references, and practical recommendations. Compare conflicting claims, identify unresolved questions, and explain limitations so accumulated research can support decisions and next steps.
中文简介正在准备中。当前显示英语简介。
Research products against a budget and required features, then compare prices, specifications, and review findings in a table. Get one recommendation with its tradeoff, plus a price history check for deals when available.
中文简介正在准备中。当前显示英语简介。
Analyze proxy, DNS, and firewall traffic logs to uncover unapproved SaaS and cloud services. Group usage by domain, compare it with approved applications, and produce a report with traffic volumes, user counts, risk scores, and remediation recommendations.
中文简介正在准备中。当前显示英语简介。
Research recommended practices for a chosen technology using official documentation and maintainer sources. Get a cited recommendation that explains version context, local project constraints, uncertainties, and the next steps for planning or implementation.
中文简介正在准备中。当前显示英语简介。
Review product performance by comparing usage, retention, revenue, and other metrics with previous periods and targets. Turn the numbers into a scorecard, explain meaningful trends and uncertainties, and recommend investigations or improvement experiments.
中文简介正在准备中。当前显示英语简介。
Review a development milestone using sprint reports, feature status, bugs, and risks. Summarize completion, quality, and delivery pace, then recommend whether to proceed, proceed with conditions, or stop, with scope choices and action items.
中文简介正在准备中。当前显示英语简介。
Review Google Cloud workloads against the security principles of the Well-Architected Framework. Identify gaps in access control, network protection, data handling, and security operations, then receive prioritized recommendations linked to relevant Google Cloud products.
中文简介正在准备中。当前显示英语简介。
Review Google Cloud workloads using the Performance Optimization pillar of the Well-Architected Framework. Assess performance requirements and architecture, then get actionable recommendations for resource allocation, caching, independent components, automatic scaling, and ongoing monitoring.
中文简介正在准备中。当前显示英语简介。
Choose a Google Cloud database by clarifying data needs, workload, and scale. The skill explains its recommendation and prepares validated Terraform configurations or provisioning scripts for review before infrastructure changes are made.
中文简介正在准备中。当前显示英语简介。
Analyze won and lost HubSpot deals by customer segment, competitor, deal value, and the stage before a loss. Group recorded loss reasons into themes and post a weekly Slack summary with concrete recommendations, leaving deal records unchanged.
中文简介正在准备中。当前显示英语简介。
Review daily Google Ads and Meta Ads results for budget pacing, declining performance, and unusual activity. Get prioritized findings with supporting numbers and concrete recommendations for a marketing team to assess and carry out.
中文简介正在准备中。当前显示英语简介。
Build and publish a browser demo for a supplied LoRA, a model adaptation for image or video tasks. Tailor the Gradio interface to its inputs and follow the model’s recommended settings on Hugging Face Spaces.
中文简介正在准备中。当前显示英语简介。
Find AI models for a specific task using official Hugging Face benchmark leaderboards. Compare scores, model sizes, and licenses, with memory-based estimates of device suitability and flags for models requiring quantization or API access.
中文简介正在准备中。当前显示英语简介。
Find a starting set of community legal skills through an interview about role, practice area, industry, and daily work. Review recommendations, install selected skills, and save preferences for trusted sources, updates, and available integrations.
中文简介正在准备中。当前显示英语简介。