Add building-nostr to ref, flesh out summary

.agents/skills/research-chapter/SKILL.md

@@ -14,10 +14,21 @@ Before doing any research, ask the user to provide a brief summary of what this
 should cover. What concepts, data structures, protocols, or functionality should the
 research focus on? Wait for their response before proceeding.
 
-## Step 2: Research Reference Implementations
+## Step 2: Research References
 
-Once you have the topic summary, spawn **one sub-agent per reference implementation** in
-`./ref/` to analyze them in parallel. Each sub-agent should:
+Once you have the topic summary, research the references in `./ref/` in parallel.
+
+### Philosophy Reference
+
+Spawn a sub-agent to read `ref/building-nostr` for content relevant to the chapter topic.
+This is not code — it's high-level ideas about what nostr is and how to work with it.
+Extract any philosophical framing, design principles, or conceptual guidance that should
+inform the chapter's narrative and approach.
+
+### Code References
+
+Spawn **one sub-agent per code reference implementation** to analyze them in parallel.
+Each sub-agent should:
 
 1. Search the reference implementation for code relevant to the chapter topic
 2. Analyze in depth:
@@ -29,7 +40,7 @@ Once you have the topic summary, spawn **one sub-agent per reference implementat
 3. Return a detailed summary focusing **only on functionality relevant to the chapter topic**
    — ignore unrelated parts of the library
 
-The six reference implementations to analyze:
+The six code reference implementations to analyze:
 - `ref/applesauce` (TypeScript — noStrudel ecosystem)
 - `ref/ndk` (TypeScript — Nostr Development Kit)
 - `ref/nostr-gadgets` (TypeScript — high-level utilities, JSR)
@@ -51,6 +62,10 @@ The research file should have this structure:
 
 <The topic summary provided by the user in Step 1>
 
+## Philosophy
+
+<Relevant ideas, principles, and framing from ref/building-nostr>
+
 ## Reference Implementation Analysis
 
 ### applesauce