@sellable/mcp 0.1.305 → 0.1.306

package/dist/tools/leads.js

@@ -1143,16 +1143,17 @@ function buildSignalDiscoverySourceRecommendation({ selectedPosts, targetEngager
     const recommendedCount = recommendedPosts.length;
     const totalVisibleEngagement = normalizedSelectedPosts.reduce((sum, post) => sum + post.likes + post.comments, 0);
     const recommendedVisibleEngagement = recommendedPosts.reduce((sum, post) => sum + post.likes + post.comments, 0);
+    const fitRateForEstimate = targetEngagerCount && effectiveTargetEngagerCount > 0
+        ? Math.min(1, targetGoodFitLeads / effectiveTargetEngagerCount)
+        : defaultFitRate;
+    const estimatedGoodFit = scrapePlan.estimatedEngagers * fitRateForEstimate;
     const tableRows = recommendedPosts
         .map((post) => {
         const engagement = post.likes + post.comments;
-        return `| ${escapeMarkdownTableCell(post.authorName)} | ${escapeMarkdownTableCell(post.reason)} | ${formatApproxInteger(engagement)} | ${formatApproxInteger(estimateScrapableSignalEngagers(post))} |`;
+        const estimatedPostGoodFit = estimateScrapableSignalEngagers(post) * fitRateForEstimate;
+        return `| ${escapeMarkdownTableCell(post.authorName)} | ${escapeMarkdownTableCell(post.reason)} | ${formatApproxInteger(engagement)} | ${formatApproxInteger(estimatedPostGoodFit)} |`;
     })
         .join("\n");
-    const fitRateForEstimate = targetEngagerCount && effectiveTargetEngagerCount > 0
-        ? Math.min(1, targetGoodFitLeads / effectiveTargetEngagerCount)
-        : defaultFitRate;
-    const estimatedGoodFit = scrapePlan.estimatedEngagers * fitRateForEstimate;
     const fitRateLabel = targetEngagerCount && effectiveTargetEngagerCount > 0
         ? "the approved buyer-search target"
         : `the ${Math.round(defaultFitRate * 100)}% starting estimate`;
@@ -1172,7 +1173,7 @@ I found ${recommendedCount.toLocaleString("en-US")} recommended LinkedIn post${r
 
 ### Recommended posts
 
-| Post | Why this post | Public activity | People we can check |
+| Post | Why this post | Public activity | Est. likely prospects |
 |---|---|---:|---:|
 ${tableRows || "| Recommended posts | Campaign-matched public activity | - | - |"}
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.305",
+  "version": "0.1.306",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/create-campaign/SKILL.md

@@ -406,8 +406,11 @@ summary should be a compact `## Source Recommendation` block with:
 - first review: after the source list exists, add confirmed source rows to the
   campaign and review the first 15 leads before scaling
 - a selected-post table with post author/topic, why it fits, public activity,
-  and people we can check
-- total public activity and likely prospect pool
+  and estimated likely prospects. Calculate each row's estimated likely
+  prospects from the sampled fit rate when available, otherwise from the stated
+  starting estimate; never duplicate public activity or people-to-check counts in
+  this column.
+- total public activity, people to check, and likely prospect pool
 - next step: build the source list, add it to the campaign, and review the
   first 15 leads before scaling
 - fallback: switch to active LinkedIn profiles if the first sample is too noisy

package/skills/create-campaign-v2/SKILL.md

@@ -252,9 +252,10 @@ After `import_leads`, poll `wait_for_lead_list_ready` until ready, failed, or
 cancelled. Rows appearing is not enough for `confirm_lead_list`; use
 `allowPartialSourceList: true` only when the user explicitly asks to continue early.
 
-For LinkedIn engagement, the Start Import approval uses `## Source
-Recommendation`, plain language, selected posts, people to check, likely
-prospects, cleanup risk, fallback, and the first 15-lead review.
+For LinkedIn engagement, Start Import uses `## Source Recommendation`: selected
+posts, people to check, likely prospects, cleanup risk, fallback, first 15-lead
+review. Tables show public activity + est. likely prospects, not duplicate
+people-to-check; rows = fit rate * checkable people.
 
 A source recommendation must show source path, filters/recipe, raw volume,
 sample size, sampled fits as n/N plus percentage/range, estimated usable

package/skills/create-campaign-v2/SOUL.md

@@ -267,6 +267,10 @@ For LinkedIn engagement, the second gate is not "approve source" in the abstract
 It is a concrete scrape approval: show a compact `## Source Recommendation`
 with the ~300 likely-prospect goal, people-to-check count, selected-post table,
 total public activity, likely prospect pool, first-review checkpoint, and fallback.
+In the selected-post table, show public activity beside estimated likely
+prospects. Do not duplicate the people-to-check/raw public-activity number in the
+second numeric column; calculate row-level likely prospects from sampled fit rate
+when available or the stated starting estimate.
 Keep the 10% planning floor as plain "at least 10% of the first sample should
 look like real prospects." The approval question should be
 "Approve scraping N recommended LinkedIn posts?" where N comes from the