phuryn/product-engineering / app-stack/skills/embedded-agents-agent-sdk
embedded-agents-agent-sdk
VerifiedOnly when the Agent SDK is asked for, an agent needs Claude Code's own tools, or the app already runs it: embed Claude agents in a Next.js app with the Agent SDK.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.9 KB |
| examples/knowledge-agent.live.test.ts | script | 1.2 KB |
| examples/knowledge-agent/AGENTS.md | markdown | 2.0 KB |
| examples/knowledge-agent/knowledge/jtbd.md | markdown | 3.3 KB |
| examples/knowledge-agent/knowledge/llms.md | markdown | 6.1 KB |
| examples/knowledge-agent/knowledge/okrs.md | markdown | 2.7 KB |
| examples/knowledge-agent/knowledge/product-strategy.md | markdown | 3.8 KB |
| examples/knowledge-agent/knowledge/product-vision.md | markdown | 3.8 KB |
| examples/research-agent.live.test.ts | script | 1.1 KB |
| examples/research-agent/.mcp.json | config | 277 B |
| examples/research-agent/AGENTS.md | markdown | 2.5 KB |
| reference/playbook.md | markdown | 16.4 KB |
| scripts/discover-mcp-tools.mjs | script | 2.6 KB |
| scripts/new-agent.mjs | script | 1.9 KB |
| templates/agent.test.ts | script | 5.1 KB |
| templates/agent.ts | script | 8.6 KB |
| templates/agents.live.test.ts | script | 1.7 KB |
| templates/route.ts | script | 2.4 KB |
examples/knowledge-agent/knowledge/product-strategy.md
View on GitHub# Product Strategy
## What it is
Product strategy is the **set of choices about where you will and won't compete, who you serve, and why you'll win**. It is not a roadmap, not a feature list, and not a vision statement. A useful strategy answers: *Given finite resources and an adversarial market, what specific bets are we making, and why are those bets defensible?*
Richard Rumelt's framing: a strategy has three components — a **diagnosis** of the challenge, a **guiding policy** for dealing with it, and a **coherent set of actions** that follow from the policy.
## The four questions a product strategy must answer
1. **Where will we play?** Which market, segment, geography, customer type. Equally important: where we will *not* play.
2. **How will we win?** What is the source of advantage — distribution, technology, network effects, brand, cost structure, regulatory moat? Pick one or two; you cannot win on all dimensions.
3. **What capabilities do we need?** Skills, data, infrastructure, partnerships required to deliver on the "how to win" claim.
4. **What management systems do we need?** Hiring, incentives, decision rights, metrics that reinforce the strategy rather than fight it.
A statement that doesn't make any of these four trade-offs sharper is a slogan, not a strategy.
## Strategy vs. vision vs. roadmap
- **Vision** — the long-term future state you want to create. Stable, qualitative, inspirational. (See `product-vision.md`.)
- **Strategy** — the bets you're making *now* to get there. Time-bound, contains explicit trade-offs.
- **Roadmap** — the sequence of concrete work that executes the strategy. Should be the *output* of strategy, not a substitute for it.
A common failure: jumping from vision straight to roadmap, skipping strategy entirely. The result is a roadmap that lists features without explaining why those features and not others.
## What makes a strategy "good"
Rumelt's test: **a good strategy has a kernel** — diagnosis, guiding policy, coherent actions — and **says no to most things**. A strategy that requires doing everything is no strategy. If two competing teams could read your strategy and both legitimately claim their work fits, the strategy is too vague.
Concretely, a good product strategy:
- **Names the constraint.** What's the central obstacle — distribution, retention, willingness to pay, talent? The strategy should be designed around relaxing that one constraint.
- **Picks a wedge.** Where in the market are you concentrating force to break in? A small, defensible beachhead beats a broad, undefended frontier.
- **States the source of advantage** in a sentence. "We win because of X" — where X is something a competitor would have to fundamentally restructure to replicate.
- **Implies what you will sacrifice.** Markets you won't serve, customers you'll lose, features you won't build. If nothing is being given up, no real choice has been made.
## Common failure modes
- **Strategy as goals.** "Become the leader in X" is a goal, not a strategy. The strategy is *how* you become the leader.
- **Strategy as values.** "Customer obsession" is a value. It is not a basis for choosing between two competing roadmaps.
- **Strategy by addition.** Adding "and also AI" to last year's strategy is not a strategy update. The question is what gets removed.
- **Strategy as PowerPoint.** A 60-slide deck that the team can't recite in two sentences won't change behavior. The strategy has to be small enough to live in working memory.
## How strategy interacts with execution
A strategy is a hypothesis. Execution is how you test it. Metrics — especially leading indicators — tell you whether the bets are paying off. When they're not, the strategy itself should be revisited, not just the tactics. Teams that adjust tactics endlessly while protecting a failing strategy are the most common form of organizational drift.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |