Results for “recommend”

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).

The English summary is being prepared. Showing the original description.

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.

The English summary is being prepared. Showing the original description.

Find Claude Academy learning resources that closely match questions about using Claude, its features, or team adoption. It supplements direct answers with a small selection of relevant courses, tutorials, worked examples, or product learning hubs.

• Find resources for getting started with Claude
• Learn how to use a specific Claude feature
• Choose learning materials for team adoption

Produces detailed HTML or Markdown reports on pull requests, branches, or large code contributions. It explains how the system works, ranks concrete findings, compares designs when needed, and recommends whether and how to merge the changes.

• Reviewing a large pull request in depth
• Explaining a contribution’s design and behavior
• Comparing a design with similar systems

Turn notes and analysis into HTML slide decks for client recommendations, technical talks, or reports. Choose from themes and layouts, add speaker scripts and animations, and export slides as PNG images using the supplied rendering script.

• Turn analysis into a client recommendation deck
• Prepare a technical talk with speaker scripts
• Create slides for a product launch

Build an HTML strategy presentation that lays out options, risks, and a recommendation for an executive decision. The template uses deep navy, paper tones, and muted gold for formal board and strategy discussions.

• Comparing options for a monetization decision
• Preparing a board presentation with a clear recommendation
• Organizing a strategy briefing for executives

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.

• Preparing slides for a weekly growth review
• Discussing KPI changes and their drivers
• Presenting recommended product actions

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.

• Combine findings from several research sessions
• Compare conflicting claims and their supporting evidence
• Prepare a research brief with recommended next steps

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.

• Build a product shortlist within a budget
• Compare prices, specifications, and reviews
• Check whether a discount is a good deal

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.

• Finding unapproved SaaS and cloud services
• Measuring traffic volumes and users by service
• Prioritizing services by potential data leakage risk

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.

• Check official guidance for a chosen technology
• Research version-specific migration advice
• Gather evidence before implementation planning

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.

• Prepare weekly, monthly, or quarterly metrics reviews
• Investigate sudden spikes or drops
• Compare product performance with targets

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.

• Reviewing progress before a milestone deadline
• Identifying blockers and quality risks
• Choosing features to protect or defer

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.

• Reviewing security during Google Cloud architecture design
• Checking access permissions and network defenses
• Identifying gaps in data protection and security monitoring

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.

• Review resource capacity for expected peak demand
• Assess automatic scaling for traffic spikes
• Review component design for independent scaling

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.

• Choosing a database for a new Google Cloud application
• Clarifying data models, workloads, and scale requirements
• Preparing and validating database provisioning code for review

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.

• Reviewing weekly win rates and won or lost deal value
• Comparing outcomes by customer segment and competitor
• Finding price bands and sales stages with frequent losses

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.

• Checking whether campaign budgets are being spent on schedule
• Investigating rising acquisition costs or falling ad returns
• Finding ads and keywords that spend without converting

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.

• Share a trained LoRA through a browser demo
• Build an interface tailored to image editing or video generation
• Apply recommended trigger words and generation settings

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.

• Compare coding or reasoning models by benchmark scores
• Find model candidates for a laptop's available memory
• Choose models for OCR or speech recognition

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.

• Choosing legal skills for an initial setup
• Finding a starter pack matched to daily legal work
• Setting trusted sources and license preferences

Evaluate an AI product or feature idea by connecting customer problems, business outcomes, testable assumptions, risks, and differentiation. Produce a structured recommendation with lightweight experiments, success measures, and next steps for an investment decision.

• Deciding whether to invest in an AI feature
• Comparing AI solution options by outcomes and risk
• Preparing a proposal for executive or budget approval

Review Linear issues, check for duplicates, and organize confirmed facts, reproduction details, impact, and missing information. The skill recommends priorities, labels, statuses, and owners using the team's existing conventions and available evidence.

• Check a reported issue for duplicates
• Organize reproduction details and impact
• Recommend issue priority and ownership

Analyzes your campaign history, conversion volume, CPA targets, and auction dynamics, then recommends the right bid strategy for each campaign — manual CPC, target CPA, target ROAS, maximize conversions, or maximize conversion value. Not a blanket recommendation, but campaign-by-campaign based on the data. Platform: Google.

The English summary is being prepared. Showing the original description.