@sellable/mcp 0.1.48 → 0.1.50

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sellable/mcp",
-  "version": "0.1.48",
+  "version": "0.1.50",
   "type": "module",
   "description": "Sellable MCP server for Claude Code and Codex campaign workflows",
   "main": "dist/index.js",

package/skills/create-campaign/SKILL.md

@@ -92,14 +92,17 @@ clear business decisions, tradeoffs, and approval gates. Use product language:
 When explaining lead-source decisions, show the concrete counts behind the
 logic: lanes searched, timeframe, raw result counts, finalist posts or preview
 rows, sampled people, sampled fits as n/N (%), estimated usable people, and the
-confidence basis. Never show a percent like "73% match" without the numerator,
-denominator, and sample basis.
+confidence basis. Break estimates out by provider/source angle in bullet form
+instead of showing only one raw total. Each angle should show raw pool, sampled
+fits as n/N, estimated good-fit range after cleanup, expected reply-rate range,
+and confidence basis. Never show a percent like "73% match" without the
+numerator, denominator, and sample basis.
 
 Every approval gate must include artifact access after the readable inline
 content. Show an `Open artifact:` line with the one key clickable markdown link
 for that stage. Do not show raw filesystem paths unless links cannot be created
 or the user asks. Do this for brief approval, lead-source approval/review,
-lead-filter review, message review, sequence/settings, and final approval
+lead-filter review, message review, and final approval
 packet. The link is for deeper inspection; never use it as a substitute for
 showing the decision in chat.
 

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

@@ -56,7 +56,6 @@ Validated draft directory:
   lead-review.md
   lead-sample.json
   lead-filter.md
-  sequence-settings.md
   message-prep.md   # optional speed artifact
   message-candidate-drafts.md   # optional provisional message artifact
   message-validation.md
@@ -139,9 +138,9 @@ Validated draft directory:
   content. Show a short `Open artifact:` line with the one key clickable
   markdown link for that stage. Do not show raw filesystem paths unless links
   cannot be created or the user asks. Do this for brief approval, lead-source
-  approval/review, lead-filter review, message review, sequence/settings, and
-  final approval packet. Do not use the link as a substitute for rendering the
-  decision in chat; links are for deeper inspection.
+  approval/review, lead-filter review, message review, and final approval
+  packet. Do not use the link as a substitute for rendering the decision in
+  chat; links are for deeper inspection.
 - Do not treat the active Sellable workspace as the campaign subject. The
   workspace only tells you where the campaign will be saved. Before buyer, CTA,
   proof, or source questions, identify two things:
@@ -329,7 +328,7 @@ me`, `I’ll paste a different sender profile`, and `Other / custom`.
   Campaign brief
 
   Target:
-  ...
+  ... (include concrete role/title names, not just a broad persona)
 
   Core pain:
   ...
@@ -423,10 +422,6 @@ should test for this campaign. Those can run in parallel and usually take
 - `lead-review.md` and `lead-sample.json` are the required outputs of `find leads`.
 - `lead-filter.md` is the primary output of `filter leads`.
 - `rubric.json` is optional and secondary to `lead-filter.md`.
-- `sequence-settings.md` is a cheap pre-mint preview artifact. It summarizes
-  recommended sequence/settings for the user's approval packet. It must not call
-  sequence tools or rerun research; actual sequence attachment still happens
-  after campaign creation via `attach_recommended_sequence`.
 - `message-prep.md` is an optional speed artifact produced by the explicit
   message path after find-leads. It can prepare proof inventory, buyer
   objections, CTA options, gold-standard strategy maps, and candidate angles
@@ -696,12 +691,17 @@ table with one row per selected or finalist post:
 `## Evidence Snapshot` must include a compact numbers-first table:
 
 - source lane / keyword or filter
+- provider/source angle label, e.g. `Signals / AI outbound posts`,
+  `Sales Nav / active SaaS founders + GTM leaders`, or
+  `Prospeo / domain-filtered agencies`
 - timeframe searched
 - raw results found
 - finalist posts or preview rows reviewed
 - sampled people
 - sampled fits, shown as `n/N (%)`
 - estimated usable people
+- estimated good-fit range after cleanup
+- expected reply-rate range
 - confidence note (`sample-backed`, `directional`, or `needs more sample`)
 
 For Signals-first campaigns, `## Sample Leads` must group representative sample
@@ -719,8 +719,9 @@ chat, not the full evidence table. The visible response must include:
 - `Lead source decision`
 - `Chosen source`
 - `Why it won`
-- `Key numbers` with raw volume, sampled fit rate as `n/N`, estimated usable
-  leads, expected connection acceptance range, and expected reply rate range
+- `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.
 - `Sample leads` with 3-5 representative `Name — Title, Company` rows
 - `Tradeoff`
 - `Open artifact: lead-review.md`
@@ -729,6 +730,20 @@ 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.
 
+Use this chat shape for the quick-number bullets:
+
+```text
+Quick numbers:
+- Signals / AI outbound posts: 249 posts found. Sampled 40 engagers; 18/40
+  looked usable. Estimate: 100-250 good warm fits. Expected reply: 6-12%.
+- Sales Nav / active SaaS founders + GTM leaders: 27,454 active profiles before
+  filtering. First 25 had 12 strong/probable fits. Estimate: 300-800 good fits
+  after title/company cleanup. Expected reply: 4-9%.
+- Prospeo / domain-filtered agencies: 1,000+ likely contacts if we need scale,
+  but weaker LinkedIn activity. Estimate: 500-1,000 contacts. Expected reply:
+  2-5%.
+```
+
 After the lead source is set, use this progress copy before the parallel
 filter/message work:
 
@@ -890,52 +905,25 @@ Keep tokenized templates, token fill basis, rendered examples, good/bad token
 fill examples, validation notes, and `message-validation.md` details in
 artifacts.
 
-## Step 4: Sequence + Settings Preview
-
-Before the final approval packet, write a cheap `sequence-settings.md` preview.
-This is a planning artifact only. Do not call `attach_sequence` or
-`attach_recommended_sequence` here, and do not rerun research or message
-generation. Actual sequence attachment happens after campaign creation at
-`awaiting-user-greenlight`.
-
-Show this slim chat summary:
-
-```text
-Sequence + settings
-
-Recommended sequence:
-Recommended LinkedIn sequence based on the connected sender’s tier and limits.
-
-Review batch:
-First review batch only.
-
-Launch state:
-Paused / review-gated. Nothing sends live until final greenlight.
-
-Safety checks:
-Sender and workspace will be checked again before start.
-
-Open artifact: sequence-settings.md
-```
-
-## Step 5: Final Approval Packet
+## Step 4: Final Approval Packet
 
 When showing the final approval packet, render a slim "ready to create" summary
 in chat. The visible response must include:
 
 - `Ready to create campaign`
 - `Campaign`
-- `Target`
+- `Target` with concrete role/title names
 - `Lead source` with one key metric
 - `Filter`
 - `Sample message` with one fully filled sample and no `{{tokens}}`
-- `Sequence/settings`
 - `What approval creates`
 - `Safety`
 - `Open artifact: approval-packet.md`
 
 Keep tokenized templates, evidence tables, rubrics, validation notes, and long
-implementation details in `approval-packet.md`.
+implementation details in `approval-packet.md`. Do not include
+sequence/settings in the final approval packet; sequence attachment and launch
+settings happen after campaign creation and before the later greenlight.
 
 ## Tail (MANDATORY TOOL ORDER + Steps 13-16 + Threshold Trips + Hard Rules)
 

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

@@ -122,17 +122,32 @@ sampled engagers; 31 looked like real ICP fits, so I’d treat this as direction
 usable people if the remaining engagers behave similarly.
 ```
 
-Lead review chat should be short and numeric: chosen source, why it won, raw
-volume, sampled fit rate as `n/N`, estimated good fits, expected connection
-acceptance, expected reply rate, 3-5 sample leads, and one tradeoff. Full tables
-belong in `lead-review.md`.
+Lead review chat should be short and numeric. It must include bullet-pointed
+provider/source-angle estimates, one bullet per angle, so the sourcing logic is
+easy to scan:
+
+```text
+Quick numbers:
+- Signals / AI outbound posts: 249 posts found. Sampled 40 engagers; 18/40
+  looked usable. Estimate: 100-250 good warm fits.
+- Sales Nav / active SaaS founders + GTM leaders: 27,454 active profiles before
+  filtering. First 25 had 12 strong/probable fits. Estimate: 300-800 good fits.
+- Sales Nav / agencies + GTM consultants: smaller but higher intent. Estimate:
+  150-400 good fits.
+```
+
+Then show chosen source, why it won, expected connection acceptance, expected
+reply rate, 3-5 sample leads, and one tradeoff. Full tables belong in
+`lead-review.md`.
 
 Lead filter chat should always show what changed: keep, exclude, why, expected
 impact, and `Open artifact: lead-filter.md`.
 
-Final approval chat should be a ready-to-create summary: campaign, target, lead
-source, filter, sequence/settings, one filled sample message, what approval
-creates, and the safety note that nothing sends live until greenlight.
+Final approval chat should be a ready-to-create summary: campaign, target with
+concrete role/title names, lead source, filter, one filled sample message, what
+approval creates, and the safety note that nothing sends live until greenlight.
+Do not include sequence/settings in final approval; that belongs after campaign
+creation.
 
 Avoid:
 

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

@@ -385,6 +385,7 @@
             "why use or discard"
           ],
           "evidenceSnapshotRequiredFields": [
+            "provider/source angle label",
             "source lane or keyword",
             "timeframe searched",
             "raw results found",
@@ -392,12 +393,14 @@
             "sampled people",
             "sampled fits as n/N (%)",
             "estimated usable people",
+            "estimated good-fit range after cleanup",
+            "expected reply-rate range",
             "confidence note"
           ],
           "forbidPercentOnlyFitRates": true,
           "requiredArtifactLinks": ["lead-review.md"],
           "artifactLinkTiming": "before_next_step_or_revision_question",
-          "chatRenderRule": "Show a slim decision summary only: chosen source, why it won, raw volume, sampled fit rate as n/N, estimated usable leads, expected connection acceptance range, 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 decision summary only: chosen source, why it won, bullet-pointed Quick numbers with one provider/source angle per bullet, raw volume, sampled fit rate as n/N, estimated good-fit range after cleanup, expected connection acceptance range, 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."
         },
         {
           "action": "render_post_lead_parallel_progress",
@@ -727,60 +730,11 @@
       "watchRequired": false,
       "waitFor": ["message_approved", "revise_messaging"],
       "transitions": {
-        "message_approved": "sequence-settings-preview",
+        "message_approved": "approval-packet",
         "revise_messaging": "message-generation"
       },
       "interruptOnly": true
     },
-    {
-      "id": "sequence-settings-preview",
-      "label": "Sequence and settings preview",
-      "normalFlow": true,
-      "resumeOnly": false,
-      "onEnter": [
-        {
-          "action": "write_sequence_settings_preview",
-          "artifact": "sequence-settings.md",
-          "requiredInlineMarker": "Status: sequence-settings-preview",
-          "inputs": ["brief.md", "lead-review.md", "lead-filter.md", "message-review.md"],
-          "mustBeFast": true,
-          "doNotCallTailTools": true,
-          "requiredSections": [
-            "Recommended sequence",
-            "Review batch",
-            "Launch state",
-            "Safety checks"
-          ],
-          "chatRenderRule": "Show a slim sequence/settings summary: recommended LinkedIn sequence based on connected sender tier and limits, first review batch only, paused/review-gated launch state, nothing sends live until final greenlight, and sender/workspace checked again before start. Keep any details in sequence-settings.md. Do not show plain filesystem paths unless links cannot be created."
-        }
-      ],
-      "requiredArtifacts": [
-        "brief.md",
-        "lead-review.md",
-        "lead-filter.md",
-        "message-review.md",
-        "message-review-decision.md"
-      ],
-      "producesArtifacts": ["sequence-settings.md"],
-      "allowedTools": ["AskUserQuestion", "request_user_input"],
-      "doNotAllow": [
-        "attach_sequence",
-        "attach_recommended_sequence",
-        "create_campaign",
-        "save_rubrics",
-        "import_leads",
-        "confirm_lead_list",
-        "update_campaign",
-        "queue_cells",
-        "start_campaign"
-      ],
-      "watchRequired": false,
-      "waitFor": "sequence_settings_ready",
-      "transitions": {
-        "sequence_settings_ready": "approval-packet"
-      },
-      "interruptOnly": true
-    },
     {
       "id": "approval-packet",
       "label": "Approval packet",
@@ -796,8 +750,7 @@
             "lead-filter.md",
             "message-validation.md",
             "message-review.md",
-            "message-review-decision.md",
-            "sequence-settings.md"
+            "message-review-decision.md"
           ],
           "optionalFiles": ["rubric.json"]
         },
@@ -816,14 +769,13 @@
             "campaign direction",
             "lead source",
             "filter",
-            "sequence and settings",
             "sample message",
             "what approval creates"
           ],
           "minimumVisibleDetail": "slim_final_approval_summary",
           "requiredArtifactLinks": ["approval-packet.md"],
           "artifactLinkTiming": "before_commit_gate_question",
-          "chatRenderRule": "Show a slim final approval packet only. Include target, lead source with one key metric, filter summary, sequence/settings summary, one fully filled sample message with no {{tokens}}, what approval creates, and safety note that nothing sends live until the review/greenlight step. Keep tokenized templates, evidence tables, rubrics, and validation details in approval-packet.md. Do not show plain filesystem paths unless links cannot be created.",
+          "chatRenderRule": "Show a slim final approval packet only. Include target with concrete role/title names, lead source with one key metric, filter summary, one fully filled sample message with no {{tokens}}, what approval creates, and safety note that nothing sends live until the review/greenlight step. Keep tokenized templates, evidence tables, rubrics, and validation details in approval-packet.md. Do not show sequence/settings in final approval; that comes after campaign creation. Do not show plain filesystem paths unless links cannot be created.",
           "userFacing": true,
           "doNotUseWords": ["anchor", "validation anchor", "lane"]
         },
@@ -841,8 +793,7 @@
         "lead-filter.md",
         "message-validation.md",
         "message-review.md",
-        "message-review-decision.md",
-        "sequence-settings.md"
+        "message-review-decision.md"
       ],
       "producesArtifacts": ["approval-packet.md"],
       "optionalProducesArtifacts": ["customer-roleplay.md"],
@@ -919,12 +870,11 @@
             "campaign direction",
             "lead source",
             "filter",
-            "sequence and settings",
             "sample message",
             "what approval creates"
           ],
           "requiredArtifactLinks": ["approval-packet.md"],
-          "chatRenderRule": "Same slim approval packet as approval-packet. Include one fully filled sample message without tokens. Do not repeat tokenized template or long evidence tables in chat.",
+          "chatRenderRule": "Same slim approval packet as approval-packet. Include target with concrete role/title names and one fully filled sample message without tokens. Do not include sequence/settings. Do not repeat tokenized template or long evidence tables in chat.",
           "artifactLinkTiming": "same_turn_before_commit_question"
         },
         {

package/skills/create-campaign-v2/core/policy.md

@@ -61,7 +61,6 @@ message-candidate-drafts.md (optional, generated from find-leads basis rows)
 message-validation.md
 message-review.md
 message-review-decision.md
-sequence-settings.md
 approval-packet.md
 commit-gate-decision.md
 ```

package/skills/create-campaign-v2/references/approval-gate-framing.md

@@ -126,19 +126,20 @@ decision, not an internal validation report. Chat should show a slim approval
 surface only:
 
 1. **campaign** — company + sender
-2. **target** — concise ICP summary from `brief.md`
+2. **target** — concise ICP summary from `brief.md`, including concrete
+   role/title names so the user can verify we are aiming at the right buyers
 3. **lead source** — selected source plus one key metric from `lead-review.md`
    (for example `17/25 sampled fits`, `520 active profiles`, or estimated usable
    leads). Put the full evidence table in `lead-review.md`, not chat.
 4. **filter** — one-line keep/exclude summary from `lead-filter.md`
-5. **sequence/settings** — conservative defaults from `sequence-settings.md`:
-   recommended sequence, first review batch, paused/review-gated launch state,
-   nothing sends live until greenlight, sender/workspace checked again before
-   start
-6. **sample message** — one fully filled sample message with no `{{tokens}}`
-7. **what approval creates** — campaign draft + review batch preparation, not
+5. **sample message** — one fully filled sample message with no `{{tokens}}`
+6. **what approval creates** — campaign draft + review batch preparation, not
    live sending
 
+Do not include sequence/settings in the pre-mint final approval packet. Sequence
+attachment and launch settings happen after campaign creation and before the
+later greenlight.
+
 Keep implementation details, tokenized templates, lead tables, rubric JSON, and
 validation notes available in `approval-packet.md` and the supporting artifacts.
 Do not show raw filesystem paths unless links cannot be created or the user asks.

package/skills/create-campaign-v2/references/validation-criteria.md

@@ -131,6 +131,18 @@ usable leads after filtering, likely connection acceptance range, likely reply
 range, and estimate basis. If exact performance data is unavailable, use a
 directional range and label it `directional`, not definitive.
 
+`## Evidence Snapshot` and the visible lead-review chat must break estimates out
+by provider/source angle. Do not collapse everything into one raw count. Use
+one row or bullet per angle, for example:
+
+- `Signals / AI outbound posts`
+- `Sales Nav / active SaaS founders + GTM leaders`
+- `Sales Nav / agencies + GTM consultants`
+- `Prospeo / domain-filtered agencies`
+
+Each angle must show raw pool, sampled fits as `n/N`, estimated good-fit range
+after cleanup, expected reply-rate range, and confidence basis.
+
 `lead-sample.json` must include enough structured lead data for downstream
 filtering: