Agent Skills: product-strategy
World-class product strategy expertise combining Marty Cagan's outcome-driven product management, Steve Jobs' product intuition, and modern Silicon Valley best practices. This skill answers the fundamental question: "What should we build and why will it win?" This is not about features or roadmaps. It's about discovering what customers desperately need but can't articulate, and building something 10x better than alternatives. Use when "what should we build, product strategy, product vision, product-market fit, pmf, value proposition, competitive advantage, market positioning, customer discovery, jobs to be done, jtbd, problem worth solving, mvp scope, product differentiation, why will this win, product principles, what makes this different, market opportunity, product, strategy, vision, pmf, positioning, discovery, validation, prioritization" mentioned.
Install this agent skill to your local
Skill Files
The files that make up product-strategy.
Loading file tree…
More agent skills
- add-ecosystemAdd a new ecosystem and base model to basemodel.constants.ts. Use when onboarding a new model family from providers like Baidu, ByteDance, Google, etc. Handles ECO constants, BM constants, ecosystem record, family (creates new if needed), license (creates new if needed), and base model record. Optionally triggers add-generation-support at the end.
- deepchemMolecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.
- write-e2e-testsWriting Playwright E2E tests for tldraw. Use when creating browser tests, testing UI interactions, or adding E2E coverage in apps/examples/e2e or apps/dotcom/client/e2e.
- configuration-hardeningReview Talon tool placement and defensive prompts when requested or when adding or changing tools or subagents; apply confirmed changes and verify active capabilities.
- dart-model-upgradeDART Model Upgrade: audit and update DART 6 AI infrastructure for model or coding-agent upgrades, including named models, reasoning modes, migrations, compatibility reviews, and visual simulation-debugging evaluations
- launchLaunch and automate VS Code Insiders with the Copilot Chat extension using agent-browser via Chrome DevTools Protocol. Use when you need to interact with the VS Code UI, automate the chat panel, test the extension UI, or take screenshots. Triggers include 'automate VS Code', 'interact with chat', 'test the UI', 'take a screenshot', 'launch with debugging'.