Claude Skills for a Product Manager — Page 6
TAO OneFormer Universal Segmentation
Train and deploy one task-conditioned model for panoptic, instance, and semantic image segmentation.
Ten-Principle Thinking Loop
A structured ten-stage loop that helps Claude analyze complex problems, challenge assumptions, and produce actionable conclusions.
Google Ads Account Diagnostics
Find the causes of conversion loss, low lead flow, and lost ad opportunities.
Processize — Manual-First Delivery
Turn a product idea into a manual process you can deliver today, before writing a single line of code.
Trackio Experiment Tracking Skill
Log metrics during model training, retrieve and analyze them afterward, and sync dashboards to Hugging Face Spaces for real-time monitoring.
PPT Agent
Generate professional presentations like software engineering: a multi-subagent pipeline with pixel-level visual QA that turns one sentence into a deliverable PPTX.
Reveal.js Presentation Skill
Turns a coding agent into a slide generator that produces polished reveal.js HTML decks you can open directly in a browser — no build step.
Paper-to-Presentation Pipeline
Turns a batch of academic papers into a rigorous, fully traceable course slide deck you can actually present.
Claude Ecom — Ecommerce Business Review
Turn an orders CSV into a consultant-grade business review in one command: KPI decomposition, ~30 health checks, prioritized findings, and next actions.
Apple Bridges: Native Apple App Access for Claude Code
Swift CLI bridges that give Claude Code direct read/write access to macOS Reminders, Calendar, Contacts, Notes, Mail, Messages, and tmux sessions.
MBB Decks
Generate real consulting-grade .pptx files from Claude, with action-title storylines, MECE bullets, and company logos as bullet markers.
Factory Floor — Startup Coach
Turns Claude into a startup coach that finds your bottleneck, forces prioritization, and decides what to build next — by asking the questions you're avoiding.
Headless PowerPoint Author
Generate a deliverable PowerPoint file in managed-agent environments without an open Office application.
Obsidian JSON Canvas Assistant
Create, edit, and validate Obsidian Canvas files with an agent.
Data Designer Synthetic Data Skill
Build synthetic datasets and data-generation pipelines from a natural-language specification.
DICOM Metadata Extractor
Extract selected metadata from one DICOM file and flag PHI in standard tags.
Clinical ASR Benchmark Builder
Build pronunciation-aware NeMo evaluation benchmarks for clinical speech recognition.
TAO Image Grounding
Convert image-caption pairs into phrase-grounded annotations with pixel-space bounding boxes.
TAO FoundationStereo Stereo Depth
Generate disparity maps from stereo images and manage FoundationStereo training, evaluation, and deployment for 3D reconstruction.
TAO PointPillars 3D Detection
Guides TAO workflows for training, evaluating, and deploying LiDAR-based PointPillars detectors.
TAO SegFormer Semantic Segmentation
Guidance for training, evaluating, exporting, and deploying TAO SegFormer models.
TAO Standard Training Workflow
Run a controlled TAO train, evaluate, and export workflow on labeled data.
VSS Video Q&A
Answers visual questions by having an agent inspect a recorded video clip.
Autonomous Research Filing
Turn a research topic into traceable Obsidian knowledge-base pages.