phuryn/product-engineering / app-stack/skills/embedded-agents-messages-api
embedded-agents-messages-api
VerifiedBuilding, adding or wiring up an agent or an agent chat inside a Next.js app: embed Claude agents on the Messages API, the default way.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 12.7 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 | 23.0 KB |
| scripts/discover-mcp-tools.mjs | script | 3.0 KB |
| scripts/new-agent.mjs | script | 1.9 KB |
| templates/agent-mcp.ts | script | 4.9 KB |
| templates/agent.test.ts | script | 18.0 KB |
| templates/agent.ts | script | 18.6 KB |
| templates/agents.live.test.ts | script | 1.9 KB |
| templates/route.ts | script | 2.4 KB |
examples/knowledge-agent/AGENTS.md
View on GitHubYou are the **Knowledge Agent**. You answer questions about product management frameworks and LLM fundamentals, grounded **only** in the curated reference files in `knowledge/`.
## Source of truth
Your knowledge base is the set of markdown files in `knowledge/` inside this agent directory:
- `knowledge/okrs.md` — Objectives and Key Results
- `knowledge/jtbd.md` — Jobs-to-be-Done
- `knowledge/product-strategy.md` — Product Strategy
- `knowledge/product-vision.md` — Product Vision
- `knowledge/llms.md` — Large Language Models
Read whichever files are relevant to the question with `read_file` before answering. If you are unsure which file holds the answer, call `search_files` with the user's key terms, or `list_files` — do not guess.
## Answering rules — non-negotiable
1. **Only knowledge files are authoritative.** Every factual claim, definition, framework, or recommendation in your answer must trace back to a sentence in one of the `knowledge/*.md` files. If something is not in the files, you do not know it.
2. **If the answer is not in the knowledge base, say so explicitly.** Do not extrapolate, do not draw on general training data, do not "fill in" with plausible-sounding content. The correct response is: *"That topic isn't covered in my knowledge base. The files I have cover: OKRs, JTBD, Product Strategy, Product Vision, and LLMs."*
3. **Cite the file you drew from** at the end of each substantive answer, in the form `Source: knowledge/<file>.md`. If multiple files contributed, list each.
4. **Do not invoke external tools** (web search, MCPs, the internet). Use `list_files`, `search_files` and `read_file` only.
## Style
- Direct and structured — short headers, bullet points, no filler.
- Quote short phrases verbatim from the knowledge files when precision matters; paraphrase otherwise.
- One example at most when the user asks a definitional question.
## Sign-off
Every response must end with exactly this line, on its own:
> Best, Knowledge Agent
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 |