@sellable/mcp 0.1.29 → 0.1.30

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.29",
+  "version": "0.1.30",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/research-sender/SKILL.md

@@ -34,18 +34,42 @@ Provide as many as available. Use `"Unknown"` for missing values.
 - `companyDomain` (REQUIRED for WebSearch — derive from email or LinkedIn if absent)
 - `headline` (optional)
 
-## The One Round (Mandatory Parallel Batch)
+## Setup: Pre-Load Deferred Tools (One-Time, Before The Parallel Batch)
 
-Issue ALL of the following in a single tool-call batch (Task subagents,
-`multi_tool_use.parallel`, or whatever batching primitive your host exposes).
-Do NOT issue any of them sequentially — that defeats the protocol.
+Some hosts (Claude Code with deferred-tool fetch) require `WebSearch` and
+some MCP tools to be loaded via `ToolSearch` before they can be invoked. If
+they are not already directly callable, issue this once as the first tool
+call, on its own:
+
+`ToolSearch({ query: "select:WebSearch,mcp__sellable__enrich_sender,mcp__sellable__complete_sender_research", max_results: 5 })`
+
+Skip this turn entirely if the tools are already directly callable.
+
+## The One Round (Parallel Batch)
+
+**HARD RULE:** the four tool calls below MUST be emitted as **four `tool_use`
+content blocks inside a single assistant message** (one turn, parallel
+execution). Do NOT split them across multiple assistant messages.
+
+Concretely, your next assistant message must contain exactly these four
+`tool_use` blocks, in any order, with no leading or trailing prose:
 
 1. `enrich_sender({ linkedinUrl, companyDomain })` — baseline + `clientProspectId`.
-2. `WebSearch`: `site:{companyDomain} ("case study" OR "customer story" OR testimonial OR "success story") "{companyName}"` — proof.
-3. `WebSearch`: `"{companyName}" {companyDomain} {currentYear} (funding OR raised OR seed OR series OR hiring OR launch OR "press release")` — growth/credibility.
-4. `WebSearch` (conditional, include unless you have strong positioning context already): `"{companyName}" about product site:{companyDomain}` — positioning.
+2. `WebSearch({ query: 'site:{companyDomain} ("case study" OR "customer story" OR testimonial OR "success story") "{companyName}"' })` — proof.
+3. `WebSearch({ query: '"{companyName}" {companyDomain} {currentYear} (funding OR raised OR seed OR series OR hiring OR launch OR "press release")' })` — growth/credibility.
+4. `WebSearch({ query: '"{companyName}" about product site:{companyDomain}' })` — positioning.
+
+**Self-check before you reply:** if your reply contains fewer than four
+`tool_use` blocks (after the optional `ToolSearch` setup turn), you are
+violating the protocol. Stop, rewrite the reply with all four.
+
+**Known limitation (`claude -p` headless mode):** Claude often serializes
+these calls one-per-turn even with explicit instructions. That's fine — the
+skill still produces the same output, just with sequential tool execution
+(~30–40s total wall time vs. ~10–15s if truly parallelized). If you can
+batch, do; if not, proceed sequentially without retrying or re-prompting.
 
-That's it. No subagent fan-out. No second round of enrichment polling.
+No subagent fan-out. No second round of enrichment polling.
 
 ## Synthesis (Single Pass After Batch Returns)