@sellable/mcp 0.1.62 → 0.1.64

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.62",
+  "version": "0.1.64",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

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

@@ -529,8 +529,8 @@ batch, after buyer, offer/ask, and proof/safety are understood. Frame supplied
 lists as optional, not required. The three visible options are exactly:
 
 1. `Find people for me (recommended if you don't already have your own list)`
-2. `I have a CSV of LinkedIn profiles`
-3. `I have a company/domain list to target`
+2. `I have a CSV of profiles to reach out to`
+3. `I have a CSV of companies/domains I want to target`
 
 Do not expose provider or implementation paths as the user's lead-source
 choices. Never label the structured options as `engagers`, `titles`,
@@ -762,13 +762,26 @@ user-facing lead review. The visible response must include:
 - `Quick numbers` as bullet points, with one provider/source angle per bullet.
   Each bullet must include raw volume, sampled fit rate as `n/N`, estimated
   good-fit range after cleanup, and expected reply-rate range when available.
+- If Signals was searched or considered, `Signal keyword lanes` as a compact
+  table with keyword lane, timeframe, posts found, and finalist posts reviewed.
+- If Signals was searched or considered, `LinkedIn posts sampled` as a compact
+  table with one row per selected or finalist post: post URL/title,
+  author/topic, age, engagers, sampled engagers, good fits as `n/N`, estimated
+  usable prospects per post, and use/discard decision.
 - `Sample leads` with 3-5 representative `Name — Title, Company` rows
 - `Tradeoff`
 - `Open artifact: lead-review.md`
 
-Keep `## Evidence Snapshot`, selected posts, discarded paths, full sample rows,
-and `lead-sample.json` details in artifacts. Do not show raw filesystem paths
-unless links cannot be created or the user asks.
+Do not skip or discard Signals based only on raw post count or vibes. If
+Signals was considered, show the post-level math in chat first so the user can
+see which LinkedIn posts would be scraped, how many engagers each has, how many
+sampled engagers looked like good fits, and roughly how many usable prospects
+each post can produce. If no engagers could be fetched, say that explicitly and
+lower confidence instead of presenting a precise estimate.
+
+Keep discarded paths, full sample rows, and `lead-sample.json` details in
+artifacts. Do not show raw filesystem paths unless links cannot be created or
+the user asks.
 
 For supplied profile CSVs and existing lead lists, `lead-review.md` must not
 describe a generic TAM estimate or pretend the rows came from Sales Nav/Prospeo

package/skills/create-campaign-v2/core/flow.v2.json

@@ -166,8 +166,8 @@
           "question": "How should we get the people for this campaign?",
           "options": [
             "Find people for me (recommended if you don't already have your own list)",
-            "I have a CSV of LinkedIn profiles",
-            "I have a company/domain list to target"
+            "I have a CSV of profiles to reach out to",
+            "I have a CSV of companies/domains I want to target"
           ],
           "forbiddenOptionLabels": [
             "engagers",
@@ -389,6 +389,8 @@
             "Recommendation",
             "Why it won",
             "Quick numbers",
+            "Signal keyword lanes",
+            "LinkedIn posts sampled",
             "Sample leads",
             "Tradeoff"
           ],
@@ -417,12 +419,24 @@
             "expected reply-rate range",
             "confidence note"
           ],
+          "signalsInlineTableRequiredFields": [
+            "keyword lane",
+            "timeframe",
+            "posts found",
+            "finalist posts reviewed",
+            "post URL or title",
+            "engagers or engagement count",
+            "sampled engagers",
+            "good fits as n/N",
+            "estimated usable prospects per post",
+            "use or discard decision"
+          ],
           "forbidPercentOnlyFitRates": true,
           "requiredArtifactLinks": ["lead-review.md"],
           "artifactLinkTiming": "before_next_step_or_revision_question",
           "doNotCompressToSummaryOnly": false,
           "doNotRenderArtifactLinksOnly": true,
-          "chatRenderRule": "Show a slim rendered-Markdown decision summary only, never a fenced code block. Use indexed sections and short bullets: recommendation, why it won, Quick numbers with one provider/source angle per bullet, raw volume, sampled fit rate as n/N, estimated good-fit range after cleanup, expected reply rate range, 3-5 representative sample leads, and one tradeoff. Keep evidence tables, selected posts, discarded paths, full sample rows, and lead-sample.json details in lead-review.md. Do not show plain filesystem paths unless links cannot be created."
+          "chatRenderRule": "Show a slim rendered-Markdown decision summary only, never a fenced code block. Use indexed sections and short bullets: recommendation, why it won, Quick numbers with one provider/source angle per bullet, raw volume, sampled fit rate as n/N, estimated good-fit range after cleanup, expected reply rate range, 3-5 representative sample leads, and one tradeoff. If Signals was searched or considered, include two compact inline Markdown tables before the recommendation is treated as final: Signal keyword lanes with keyword lane, timeframe, posts found, and finalist posts reviewed; and LinkedIn posts sampled with post URL/title, author/topic, age, engagers, sampled engagers, good fits as n/N, estimated usable prospects per post, and use/discard decision. Do not skip or discard Signals based only on raw post count or vibes; show the post-level math first, or explicitly say no engagers could be fetched and lower confidence. Keep discarded paths, full sample rows, and lead-sample.json details in lead-review.md. Do not show plain filesystem paths unless links cannot be created."
         },
         {
           "action": "render_post_lead_parallel_progress",

package/skills/create-campaign-v2/references/lead-validation-preview.md

@@ -97,6 +97,26 @@ Use a compact markdown report with these sections:
 - Likely Reply Rate: {range}
 - Estimate Basis: sample-backed | historical | founder-supplied | directional
 
+## Signal Keyword Lanes
+
+Include this section whenever Signals was searched or considered. This table is
+what lets the user see which keyword lanes produced enough fresh post inventory.
+
+| Keyword lane | Timeframe | Posts found | Finalist posts reviewed |
+| ------------ | --------- | ----------- | ----------------------- |
+| ...          | ...       | ...         | ...                     |
+
+## LinkedIn Posts Sampled
+
+Include this section whenever Signals was searched or considered. Do not skip or
+discard Signals based only on raw post count or vibes; show the post-level math
+first. This table is the evidence for how many posts to scrape, including
+estimated usable prospects per post.
+
+| Post | Author / topic | Age | Engagers | Sampled engagers | Good fits | Estimated usable prospects per post | Use / discard |
+| ---- | -------------- | --- | -------- | ---------------- | --------- | ----------------------------------- | ------------- |
+| ...  | ...            | ... | ...      | ...              | x/y       | ...                                 | ...           |
+
 ## Pros
 
 - ...

package/skills/find-leads/SKILL.md

@@ -284,6 +284,12 @@ Use first when the value is in conversation opportunity, competitor engagers, co
   strategy: Signals = warmer, smaller, higher reply upside; Sales Nav/Prospeo =
   more scalable, usually colder or less signal-rich. Recommend the source you
   believe is better, but keep the viable alternate as a real option.
+- When Signals was searched or considered, do not recommend skipping or
+  discarding it until the user can see the post-level math. Show a compact
+  LinkedIn posts table with the keyword lane, selected/finalist post URL or
+  title, post age, engager count, sampled engagers, good fits as `n/N`,
+  estimated usable prospects per post, and use/discard decision. This table is
+  the evidence for how many posts to scrape; raw post count alone is not enough.
 - If you cannot fetch engagers in the current runtime, say the estimate is inferred and lower confidence.
 - If Signals is too sparse, too noisy, or clearly below campaign scale after the spot check, fall back to `Sales Nav` rather than forcing a weak conversation-led lane.