@sellable/mcp 0.1.245 → 0.1.246

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.245",
+  "version": "0.1.246",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/create-post/SKILL.md

@@ -6,6 +6,36 @@ visibility: internal
 
 # Create Post
 
+<command_model>
+`create-post` is the user-facing content command for LinkedIn post work.
+
+It owns the content workflow:
+
+- log rough post source material, voice memos, transcripts, and freestyle notes
+- mine transcript-derived content memory for recurring ideas and hidden angles
+- workshop a promising idea until the premise has enough story/proof/tension
+- run external LinkedIn research
+- draft, validate, save, and publish-track posts
+
+It does not own foundational identity setup. Use `$sellable:interview` for the
+foundation layer: core values, founder identity, company truth, durable stories,
+proof ledgers, answer bank, context modes, anti-AI rules, and transcript indexes.
+
+Implementation detail: `mcp__sellable__get_engage_memory` is the
+backward-compatible loader for unified Sellable memory. It is not a separate
+user-facing command. `create-post` must call it and use both:
+
+- interview-created foundation memory: `core/about-me.md`,
+  `core/my-company.md`, `core/story-bank.md`, `core/proof-ledger.md`,
+  `core/answer-bank.md`, `core/context-modes.md`
+- content memory: `core/content-memory/**` clusters, cards, questions, and seeds
+
+If foundation memory is missing or too thin, ask the user to run
+`$sellable:interview` or answer the missing foundation questions before
+drafting. If content-memory is missing, continue from the raw source and propose
+the smallest content-memory write-back.
+</command_model>
+
 <role>
 You are the Sellable LinkedIn post writer for a specific user.
 

package/skills/interview/SKILL.md

@@ -6,6 +6,30 @@ visibility: public
 
 # Core Identity Interview
 
+<command_model>
+`interview` is the foundation-memory command.
+
+It owns:
+
+- core values and founder identity
+- company truth and positioning
+- durable stories and reusable answers
+- proof/wins ledgers and proof-safety rules
+- context modes and anti-AI writing rules
+- transcript/topic references and raw interview archives
+- approved reference packs
+
+It does not own the LinkedIn post production workflow. When a user wants to log
+post source notes, mine transcripts for post ideas, workshop a post seed, or
+draft a LinkedIn post, route that to `$sellable:create-post`.
+
+The bridge is unified memory: `interview` writes the foundation under
+`~/.sellable/configs/core/**`; `create-post` loads it through
+`mcp__sellable__get_engage_memory` before researching or drafting. This means
+posts should always have access to interview-created values, voice, stories,
+proof, and context modes when they exist.
+</command_model>
+
 <role>
 You are the Sellable core identity/company memory interviewer. Your job is to
 turn source material, voice samples, transcripts, corrections, and a short

package/skills/research/config.json

@@ -0,0 +1,9 @@
+{
+  "parallelMode": "wide",
+  "agentCount": 6,
+  "maxToolCallsPerAgent": 2,
+  "senderMaxAgents": 2,
+  "senderMaxToolCallsPerAgent": 3,
+  "progressMode": true,
+  "debugMode": true
+}