v0.0.68 - Update SKILLS.md with seed determinism fields and private kind 31124 NIP-44 encrypted payload spec

docs/SKILLS.md

@@ -36,6 +36,7 @@ The skill event's `content` field is a JSON object that defines the complete exe
     "tools": false,
     "max_tokens": 2000,
     "temperature": 0.1,
+    "seed": 42,
     "template": "system:\nYou are a spelling and grammar checker.\n\nRules:\n- Fix spelling errors\n- Fix grammar errors\n- Preserve original formatting\n- Ignore: API, JSON, HTTP, nostr, pubkey, npub, nsec, NIP\n- Canadian English preferred\n- Return ONLY the corrected text, no explanations\n\nuser:\n{{message}}"
   },
   "tags": [
@@ -58,9 +59,61 @@ The skill event's `content` field is a JSON object that defines the complete exe
 | `soul` | bool | `true` | Whether to include the agent's soul in context |
 | `max_tokens` | int | — | Override max tokens for this skill |
 | `temperature` | float | — | Override temperature for this skill |
+| `seed` | int | — | Optional deterministic seed (effective only on providers/engines that support seeded sampling) |
+
+### Determinism Controls
+
+For reproducible outputs, set `temperature` low (typically `0`) and also set `seed` when the selected model backend supports it. If a provider ignores seeds, `temperature` still applies but deterministic replay is not guaranteed.
 
 ---
 
+## Private Skill Encoding (`31124`)
+
+Private skills use NIP-44 encryption on the event `content` field.
+
+Rules for kind `31124`:
+
+- Keep `d` tag exposed so the event remains addressable/replaceable.
+- Move all other skill metadata (including non-`d` tags) into the plaintext payload before encryption.
+- Encrypt the full payload with NIP-44 and store the ciphertext in event `content`.
+- On receive: resolve by `d`, decrypt `content`, then read both content variables and tag values from decrypted payload.
+
+### Private Skill Event (on relay)
+
+```json
+{
+  "kind": 31124,
+  "content": "<nip44-ciphertext>",
+  "tags": [
+    ["d", "mention-monitor"]
+  ]
+}
+```
+
+### Decrypted Private Payload (application-level JSON)
+
+```json
+{
+  "content": {
+    "description": "Monitor mentions and DM summaries",
+    "context_mode": "inject",
+    "llm": "openai/gpt-4o-mini, fast",
+    "tools": ["nostr_query", "nostr_dm"],
+    "temperature": 0,
+    "seed": 42,
+    "template": "When {{triggering_event}} includes Bitcoin or Lightning, summarize and DM admin."
+  },
+  "private_tags": [
+    ["scope", "private"],
+    ["trigger", "nostr-subscription"],
+    ["filter", "{\"#p\":[\"<admin_pubkey>\"],\"kinds\":[1]}"],
+    ["enabled", "true"]
+  ]
+}
+```
+
+This mirrors the DM-style encrypted payload pattern (historically associated with NIP-04), but private skills should use NIP-44 ciphertext encoding.
+
 ## Context Modes
 
 Skills control how the LLM context window is assembled using the `context_mode` field:
@@ -182,7 +235,7 @@ This is the same execution model as DM-invoked skills — the only difference is
 
 ```json
 {
-  "kind": 31124,
+  "kind": 31123,
   "content": "You monitor Nostr mentions. When the triggering event mentions Bitcoin or Lightning, summarize it and DM the admin. Otherwise, ignore silently.",
   "tags": [
     ["d", "mention-monitor"],
@@ -197,7 +250,7 @@ A cron-triggered skill:
 
 ```json
 {
-  "kind": 31124,
+  "kind": 31123,
   "content": "DM the admin a short heartbeat status message with the current time.",
   "tags": [
     ["d", "heartbeat"],