Results for “ml”

Build video edits through commands: import media, arrange and trim clips, and add effects or transitions. Save project state as JSON and generate Kdenlive/MLT XML, with undo and redo support during editing.

• Arrange imported clips across timeline tracks
• Trim and split clips at specified points
• Configure effects and transitions

Configure SAML identity federation, a way to share authentication between systems, linking on-premises Active Directory with Microsoft Entra ID. Cover single sign-on for cloud applications, user attribute mapping, authentication model choices, and signing certificate management.

• Extending on-premises authentication to cloud resources
• Comparing authentication models for hybrid identity
• Setting up SAML single sign-on for SaaS applications

Build complex claude.ai artifacts with React, Tailwind CSS, and shadcn/ui. Create interfaces with multiple components, state management for changing data, and routing between views, then package the app into one self-contained HTML file for sharing.

• Creating interfaces with multiple components
• Building artifacts with changing data and multiple views
• Sharing a React app as a single HTML file

Automate Bigml operations through Rube MCP, a connection to external tools. Find tools for a specific task, review their required inputs, verify the account connection, and execute operations within a shared workflow session.

• Find Bigml tools for a specific task
• Check connectivity before running operations
• Run multiple operations within one session

Automate AI ML API tasks through Rube MCP, a connection for accessing external tools. The skill guides tool discovery, connection checks, and execution using current input requirements, with guidance for bulk operations and paginated results.

• Finding available AI ML API tools
• Checking the service connection before execution
• Running tools with their current input requirements

Build machine learning workflows that connect data checks, training, evaluation, and deployment. The skill implements experiment tracking, model version management, and automated retraining, with reproducible environments and explicit validation thresholds before models enter production.

• Automate model training and retraining workflows
• Record and compare machine learning experiments
• Build a feature store for model input data

Upload local images, HTML pages, and Markdown design documents to a Stitch project. The included Python script sends files directly over HTTP, avoiding the text output limits that can interrupt transfers through MCP tools.

• Upload local mockup images to Stitch
• Add extracted HTML pages to a Stitch project
• Upload Markdown design documents

Create live HTML product demos that show an app’s workflow inside a Mac-style window. Reproduce real interface text and results, animate a scripted pointer, and support step navigation, scrubbing, and consistent frozen frames.

• Adding an animated app demo to a landing page
• Explaining a feature through step-by-step UI playback
• Replacing UI recordings or GIFs with live HTML

Turn long Markdown reports into a single HTML page with a design shaped by the subject. Reorganize text, evidence, and charts for easier reading while preserving the source’s factual claims and the strength of its conclusions.

• Turning an industry analysis into a shareable web page
• Reorganizing research notes around findings and evidence
• Presenting weekly reports and retrospectives as web pages

Classical end-to-end empirical analysis workflow in the modern tidyverse + econometrics R ecosystem — dplyr + tidyr + haven + fixest + sandwich + lmtest + clubSandwich + AER + ivreg + did + bacondecomp + HonestDiD + eventstudyr + rdrobust + rddensity + Synth + gsynth + synthdid + MatchIt + WeightIt + cobalt + ebal + grf + DoubleML + mediation + marginaleffects + modelsummary + kableExtra + gt + ggplot2 + ggpubr + cowplot + binsreg. **Defaults to economics empirical-paper style** (AER / QJE / AEJ) — every run produces a publication-ready output set with a multi-column regression table (M1→M6 progressive controls/FE) as the centerpiece, plus Table 1 (descriptives), mechanism / heterogeneity / robustness tables, and event-study + coefficient + trend figures. Covers the full 8-step R pipeline an applied economist runs on every paper — (1) data import & cleaning (read_dta/read_csv, naniar, janitor, validate-merges), (2) variable construction (mutate/across/winsorize/group_by + lag/lead with dplyr), (3) descriptive statistics & Table 1 (gtsummary, modelsummary::datasummary, tableone), (4) classical diagnostic tests (shapiro/jarque.bera.test/bptest/dwtest/bgtest/vif/adf.test/kpss.test/Hausman), (5) baseline modeling (fixest::feols, ivreg, did::att_gt, eventstudyr, sun_ab, did_imputation, synthdid, rdrobust, MatchIt, WeightIt, grf::causal_forest, DoubleML, mediation), (6) robustness battery (modelsummary stack, clubSandwich CRSE, fwildclusterboot, ri2, robomit Oster, bacondecomp, HonestDiD), (7) further analysis (interactions + marginaleffects, mediation::mediate, gsem via lavaan, dose-response splines, grf CATE), (8) publication-ready tables & figures (modelsummary, kableExtra, gt, stargazer, texreg, flextable to LaTeX/Word/HTML; ggplot2 + ggpubr + cowplot + binsreg + iplot for figures). **Also covers two parallel domain modes that share the same 8-step scaffolding** — **Mode A — Epidemiology / public health** (target-trial emulation, IPTW + g-formula + TMLE doubly-robust triplet via `WeightIt` / `gfoRmula` / `tmle` / `ltmle`, Mendelian randomization via `MendelianRandomization` / `TwoSampleMR` / `MRPRESSO`, KM / Cox / AFT / RMST survival via `survival` / `survminer` / `flexsurv`, E-value sensitivity via `EValue`, principal stratification — STROBE / TRIPOD reporting), and **Mode B — ML causal inference** (DML via `DoubleML`, S/T/X/R/DR meta-learners via `causalweight` / `grf`, causal forest via `grf::causal_forest`, BART/BCF via `bartCause` / `bcf`, matrix completion via `MCPanel`, CATE distribution + policy tree via `policytree`, off-policy evaluation, conformal causal via `conformalInference` / `cfcausal`, fairness audit via `fairmodels`, DAG learning via `pcalg` / `bnlearn` / LLM-assisted). Use when the user asks for a complete R empirical analysis, wants a tidyverse-style reproducible R script / Quarto workflow, prefers fixest over reghdfe, needs the R counterpart to StatsPAI / 00.1 / 00.2, or names a specific R step in isolation ("feols with cluster", "MatchIt nearest neighbor", "bacondecomp in R", "gtsummary table 1", "modelsummary to Word"). Mode A triggers on "target trial emulation R", "tmle ltmle", "MendelianRandomization", "TwoSampleMR", "MRPRESSO", "survival cox AFT", "STROBE R", "EValue R", "公共健康 R", "流行病学 R". Mode B triggers on "DoubleML R", "grf causal forest", "policytree", "bartCause bcf", "conformal causal R", "fairmodels", "pcalg NOTEARS", "因果机器学习 R".

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

Apple オンデバイス機械学習フレームワークリファレンス。 Core AI (.aimodel) / Core ML / Create ML / Vision / Natural Language / Speech / Media Intelligence / Music Understanding。 AIModel, InferenceFunction, MLModel, MLModelConfiguration, MLMultiArray, MLTensor, MLComputeUnits, MLImageClassifier, MLTextClassifier, MLDataTable, VNCoreMLRequest, VNImageRequestHandler, VNRecognizeTextRequest, RecognizeTextRequest, NLTagger, NLEmbedding, NLLanguageRecognizer, SpeechAnalyzer, SpeechTranscriber, SFSpeechRecognizer, SFSpeechAudioBufferRecognitionRequest, SFTranscription, FaceGroupAnalyzer, MusicUnderstandingSession。

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

Manage Apple Notes on macOS through memo, a command-line tool. Create, browse, search, edit, delete, and move notes between folders, or export selected notes to HTML or Markdown for use outside the app.

• Creating notes with titles
• Finding notes by folder or approximate search
• Editing notes and organizing them into folders

Explain concepts through detailed, interactive machines drawn from an angled view. The skill produces standalone HTML, SVG, or React components, with moving parts and numerical readouts driven by the same model so readers can explore how the idea works.

• Explain an abstract concept through a moving machine
• Add an interactive figure to a technical article
• Create a standalone HTML explainer

Create full-screen animated visuals with WebGL, a browser technology for GPU rendering. Combine shaders, 3D scenes, or particles with a text overlay, and deliver the result as one self-contained HTML file without external requests.

• Create a website hero animation
• Build generative art with a headline
• Prototype a 3D scene or particle field

Create a 16:9 animated hero composition with rotating rings, a globe or other focal graphic, and expressive typography. Deliver a single HTML document with CSS animations that a frame-capture exporter such as HyperFrames can turn into video.

• Create an animated hero for a marketing page
• Design a title card with moving typography
• Build a looping poster with rotating rings and a globe

Create HTML slides about choosing and connecting AI models in OpenDesign using your own API key. Use a terminal-style template to explain costs, quality, and model routing decisions, with speaker notes and presentation controls.

• Explaining model choices to engineers and IT teams
• Comparing model costs, quality, and routing decisions in slides
• Preparing a terminal-style presentation with speaker notes

Build an HTML sales presentation for a design team's product rollout decision. Use the product-launch template to organize the proposal, develop slide content, and prepare speaker notes for internal sharing and presentation.

• Propose a product rollout to a design team
• Prepare slides for design leads and IT stakeholders
• Create a proposal that an internal champion can forward

Build HTML slides for an OpenDesign live demo, showing how a short prompt becomes a runnable design. Organize the presentation, visual direction, speaker notes, and animations using the supplied deck template.

• Preparing an OpenDesign live demo for developers
• Explaining an AI workflow to prospective customers
• Building HTML slides with speaker notes

Review HTML to find important fonts, images, and scripts discovered late during loading. Suggest resource hints, instructions that start fetching or connecting earlier, and check the final markup delivered to the browser.

• Reviewing preload hints for important fonts and images
• Checking early connections to third-party domains
• Auditing resource hints in rendered HTML

Review how a web page loads scripts and identify tags that interrupt HTML parsing. Get guidance on choosing defer, async, or type=module, with checks focused on the HTML actually delivered to the browser.

• Checking script tags that delay page rendering
• Choosing between defer, async, and type=module
• Reviewing HTML generated by shared components

Review the HTML delivered to browsers for a correct UTF-8 character encoding declaration. Find missing or misplaced charset tags in templates and rendered pages, then position the declaration early to help prevent garbled multilingual text.

• Investigating garbled Japanese or special characters
• Checking character encoding declarations before release
• Reviewing HTML output from shared templates

Turn stored knowledge pages into self-contained HTML files for sharing research, briefings, or travel plans. The workflow removes internal metadata and links, applies password protection by default, and offers optional cloud upload and expiring access links.

• Sharing research with external recipients
• Preparing a deal memo for sharing
• Sending a briefing about a person

Create charts, dashboards, scorecards, and styled summaries as standalone HTML reports for the screenpipe viewer. Keep styles, scripts, and images inside the file so the report renders in a sandbox with no network access.

• Create a visual report of daily work time
• Present key metrics in a dashboard
• Summarize results with charts and scorecards

Manage machine learning experiments with MLflow by recording settings, metrics, files, and trained models. Covers experiment comparison, model version management, reproducible project configurations, and deployment workflows across local and cloud environments.

• Recording experiment settings and evaluation results
• Comparing model performance across experiments
• Managing model versions for production use