mweinbach

Build a source-linked, driver-based diligence model with assumptions, scenarios, sensitivities, checks, and evidence provenance. Use for market sizing, revenue builds, unit economics, capacity models, margin or EPS bridges, operating models, valuation inputs, or any spreadsheet/model request grounded in Diligence Stack research.

Build a source-linked company or vendor diligence packet using Diligence Stack reports, vendor notes, and optionally entitled equity research. Use for company briefs, competitive positioning, thesis updates, catalysts, risks, monitoring dashboards, or investment research.

Apply The Diligence Stack visual identity, source attribution, citation format, and canonical-link policy to user-facing content created from Diligence Stack research. Use whenever this plugin creates or edits prose, documents, decks, spreadsheets, charts, dashboards, web pages, images, exports, or other deliverables; use the visual defaults unless the user explicitly requests different styling.

Scope and plan a diligence project before research begins. Use for investment, vendor, product, partner, acquisition, or strategic diligence when the user needs questions, workstreams, evidence requirements, priorities, or a research plan.

Search and retrieve source-linked evidence from the Diligence Stack MCP knowledge bases. Use for any company, market, product, vendor, technology, or investment question that should be grounded in Diligence Stack reports or entitled equity research.

Synthesize diligence evidence into a decision-ready memo, scorecard, risk register, or recommendation. Use when the user has research, interviews, analyses, or data-room findings and needs conclusions with confidence, red flags, and next actions.

Synthesize separately entitled private equity research alongside the Diligence Stack house view. Use for ticker briefs, consensus and disagreement maps, catalysts, earnings preparation, valuation debates, or analyst-view comparisons when the equity-research corpus is authorized.

Audit the quality, traceability, freshness, and decision usefulness of a diligence thesis or report using Diligence Stack evidence. Use when checking claims, citations, confidence, source classes, estimates, charts, customer proof, or whether a conclusion outruns its evidence.

Use when the user asks to create, publish, deploy, update, or maintain a Cowork marketplace - a public GitHub repo with a .agents/plugins/marketplace.json catalog that distributes plugins and standalone skills, versioned by per-entry sourceHash fingerprints. Triggers on: 'create a marketplace', 'publish a marketplace', 'deploy a marketplace', 'set up a marketplace repo', 'add a plugin to my marketplace', 'add a skill to my marketplace', 'update marketplace hashes', 'marketplace source hash mismatch'.

Create, edit, redline, and comment on `.docx` files inside the container, with a strict render-and-verify workflow. Use `render_docx.py` to generate page PNGs (and optional PDF) for visual QA, then iterate until layout is flawless before delivering the final DOCX.

Read, create, inspect, render, and verify PDF files where visual layout matters. Use Poppler rendering plus Python tools such as reportlab, pdfplumber, and pypdf for generation and extraction.

Build premium editorial analytics PPTX decks with artifact-tool presentation JSX, using ruthless narrative editing, chart-first storytelling, rendered critique, and iteration until the output beats the reference deck.

Use when the user asks to create, author, scaffold, package, edit, or update a plugin — a bundle with a .cowork-plugin/plugin.json manifest that groups one or more skills and, optionally, MCP servers and app integrations. Triggers on: 'create a plugin', 'new plugin', 'author a plugin', 'edit a plugin', 'update a plugin', 'add a skill to a plugin', 'bundle these skills into a plugin', 'make a plugin.json', 'add an MCP server to a plugin'.

Use when the user asks to create, author, scaffold, write, or improve a skill — a SKILL.md package that gives an agent specialized, on-demand instructions plus optional bundled resources. Triggers on: 'create a skill', 'new skill', 'write a skill', 'author a skill', 'add a skill', 'scaffold a skill', 'make a SKILL.md', 'improve this skill', 'fix my skill description'.

Transcribe local audio files on macOS 26 or newer with the `apple-native-transcribe` CLI. Use when a task needs Apple's on-device SpeechAnalyzer and SpeechTranscriber workflow for `.mp3`, `.m4a`, `.wav`, or similar local audio, and the CLI may need to be verified or installed with `brew install mweinbach/max-skills/apple-native-transcribe`. Do not use this skill on Linux, Windows, or macOS versions earlier than 26.

Use this skill when a user requests to create, modify, analyze, visualize, or work with spreadsheet files (`.xlsx`, `.xls`, `.csv`, `.tsv`) with formulas, formatting, charts, tables, and recalculation.

Use when building JavaScript/TypeScript applications, running scripts, managing dependencies, bundling code, or testing. Bun is a drop-in replacement for Node.js with integrated package manager, bundler, and test runner.

Promote substantial, multi-step work from ordinary chat into durable task mode. Use when the user explicitly invokes /task or asks to create/start a task, or when an objective needs a persistent plan, progress tracking, artifacts, decisions, review, or work that may span sessions. Do not use for quick answers, simple one-step edits, or work that can be completed naturally in the current chat.

Use when the user asks to view, list, inspect, add, create, edit, correct, update, or manage long-term memories for the current chat or workspace.

Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs.

Integrate Expo and React Native into an existing native iOS or Android app. Use when the user mentions brownfield, embedding React Native in a native app, AAR/XCFramework, or adding Expo to an existing Kotlin/Swift project. Covers both the isolated approach and the integrated approach.

Guide for creating and writing Expo native modules and views using the Expo Modules API (Swift, Kotlin, TypeScript). Covers module definition DSL, native views, shared objects, config plugins, lifecycle hooks, autolinking, and type system. Use when building or modifying native modules for Expo.

End-to-end release workflows for TestFlight and App Store using asc publish, builds, versions, and submit commands. Use when asked to upload a build, distribute to TestFlight, or submit to App Store.

Set up bundle IDs, capabilities, signing certificates, and provisioning profiles with the asc CLI. Use when onboarding a new app or rotating signing assets.

Orchestrate TestFlight distribution, groups, testers, and What to Test notes using asc. Use when rolling out betas.

Build, archive, and export iOS/macOS apps with xcodebuild before uploading to App Store Connect. Use when you need to create an IPA or PKG for upload.

Transcribe local audio files with Apple's native SpeechAnalyzer and SpeechTranscriber APIs using the installed apple-native-transcribe CLI. Use when a task needs on-device speech-to-text for local audio on macOS 26 or newer. Prefer installing with brew install mweinbach/max-skills/apple-native-transcribe. Do not use on Linux, Windows, or macOS versions earlier than 26.

Transcribe local audio files on macOS 26 or newer with the `apple-native-transcribe` CLI. Use when a task needs Apple's on-device SpeechAnalyzer and SpeechTranscriber workflow for `.mp3`, `.m4a`, `.wav`, or similar local audio, and the CLI may need to be verified or installed with `brew install mweinbach/max-skills/apple-native-transcribe`. Do not use this skill on Linux, Windows, or macOS versions earlier than 26.

Use when conducting research on AI infrastructure, semiconductors, memory/storage, datacenters, or hyperscalers using the Diligence Stack MCP server. Triggers on: 'search Diligence Stack', 'query Diligence Stack', 'fetch Diligence Stack evidence', 'find Diligence Stack reports', 'look up semiconductor / AI research'.

A tiny demonstration skill from a custom test marketplace. Use when the user asks to say hello from the test marketplace.