@sellable/mcp 0.1.149 → 0.1.150

package/skills/create-campaign/references/provider-selection-strategy.md

@@ -53,7 +53,29 @@ Activity Filters (use one or both):
 
 Sales Nav works without these filters too -- just expect lower reply rates.
 
-### 3. Apollo (LAST RESORT FOR VOLUME)
+### 3. Prospeo (HIRING / ACCOUNT / VERIFIED-CONTACT EXPANSION)
+
+Prospeo is the main lane when the user's direction points to database filters
+that LinkedIn sources do not expose.
+
+USE WHEN:
+
+- Hiring-led targeting: companies actively hiring specific roles
+- Named-account or domain-list targeting
+- Broad persona expansion where verified contact coverage matters
+- You need `company_job_posting_hiring_for`,
+  `company_job_posting_quantity`, funding, headcount, or domain filters
+
+SKIP WHEN:
+
+- The campaign is mainly about fresh LinkedIn activity or engagement warmth
+- Signal Discovery can clearly produce enough ICP-fit engagers
+
+WHY: Prospeo is the only current provider with company job-posting filters by
+role. Sales Nav is stronger for recent LinkedIn activity, but not for
+hiring-by-role filtering.
+
+### 4. Apollo (LAST RESORT FOR VOLUME)
 
 Large database but leads may not be active on LinkedIn.
 
@@ -74,25 +96,30 @@ Is your ICP LinkedIn-active (founders, sales, marketing, GTM, engineers)?
     NO  -> Sales Navigator + POSTED_ON_LINKEDIN (4x reply rates)
   NO  -> Sales Navigator (with or without POSTED_ON_LINKEDIN)
 
+Need hiring-by-role filters? -> Prospeo (has company job-posting filters)
 Need tech stack targeting? -> Apollo (has technology filters)
-Have specific company names? -> Sales Navigator or Apollo with domains
+Have specific company names/domains? -> Sales Navigator for small lists or Prospeo with domainFilterId
 ```
 
 ## ICP-to-Provider Quick Reference
 
-| ICP Type                  | Recommended      | Why                                                  |
-| ------------------------- | ---------------- | ---------------------------------------------------- |
-| Founders, CEOs            | Signal Discovery | Highly active on LinkedIn, lots of founder content   |
-| Sales/GTM leaders         | Signal Discovery | Very active, tons of sales content                   |
-| Marketing leaders         | Signal Discovery | Active, lots of marketing content                    |
-| Engineers/DevOps          | Signal Discovery | Active on tech discussions, open source              |
-| Enterprise CTOs           | Sales Navigator  | Less public engagement, use POSTED_ON_LINKEDIN       |
-| Procurement/Ops           | Sales Navigator  | Rarely engage publicly                               |
-| Few specific companies    | Sales Navigator  | Use CURRENT_COMPANY filter (lookup each company)     |
-| Company domain list (ABM) | Apollo           | Has `q_organization_domains_list` for bulk targeting |
-| Tech stack users          | Apollo           | Has technology filters                               |
-
-**Default:** Try Signal Discovery first. Fall back to Sales Navigator if ICP is too niche.
+| ICP Type                  | Recommended      | Why                                                |
+| ------------------------- | ---------------- | -------------------------------------------------- |
+| Founders, CEOs            | Signal Discovery | Highly active on LinkedIn, lots of founder content |
+| Sales/GTM leaders         | Signal Discovery | Very active, tons of sales content                 |
+| Marketing leaders         | Signal Discovery | Active, lots of marketing content                  |
+| Engineers/DevOps          | Signal Discovery | Active on tech discussions, open source            |
+| Enterprise CTOs           | Sales Navigator  | Less public engagement, use POSTED_ON_LINKEDIN     |
+| Procurement/Ops           | Sales Navigator  | Rarely engage publicly                             |
+| Few specific companies    | Sales Navigator  | Use CURRENT_COMPANY filter (lookup each company)   |
+| Hiring-led targeting      | Prospeo          | Has company job-posting filters by role            |
+| Company domain list (ABM) | Prospeo          | Uses `domainFilterId` for domain targeting         |
+| Tech stack users          | Apollo           | Has technology filters                             |
+
+**Default:** Try Signal Discovery first only when there is no stronger source
+direction and the ICP is plausibly active in public LinkedIn conversations. Fall
+back to Sales Navigator if ICP is too niche. Use Prospeo first when the ask is
+hiring-led, account/domain-led, or broad verified-contact expansion.
 
 ## ABM / Account-Based Targeting
 
@@ -103,10 +130,10 @@ When user has a list of target companies:
   - Requires looking up each company individually
   - Can combine with POSTED_ON_LINKEDIN for active users
 
-- **Many companies (domain list):** Use Apollo with `q_organization_domains_list`
-  - Supports bulk domain upload (up to 190 per search)
-  - Example: `filters: { q_organization_domains_list: ["stripe.com", "notion.so", "figma.com"] }`
-  - Trade-off: No POSTED_ON_LINKEDIN equivalent, so reply rates may be lower
+- **Many companies (domain list):** Use Prospeo with `domainFilterId`
+  - Supports large domain filters through `load_csv_domains` or `save_domain_filters`
+  - Example: create a domain filter for `stripe.com`, `notion.so`, and `figma.com`, then pass `domainFilterId` into `search_prospeo`
+  - Trade-off: No POSTED_ON_LINKEDIN equivalent, so LinkedIn activity warmth may be lower
 
 ## Recommendation Templates
 
@@ -141,6 +168,19 @@ Here's why:
 Should I search for active {icp} on Sales Navigator?
 ```
 
+**Prospeo (hiring-led ICP):**
+
+```
+Since this campaign depends on companies actively hiring for **{roleThemes}**, I'd recommend **Prospeo** first.
+
+Here's why:
+- Prospeo can filter companies by open-role themes using job-posting filters
+- We can pair those hiring signals with founder, GTM, recruiting, or revenue-owner contacts
+- Sales Nav is useful for LinkedIn activity and referrals, but it cannot filter companies by hiring role
+
+Should I search Prospeo for companies hiring {roleThemes} and the right hiring-owner contacts?
+```
+
 **Apollo (tech stack targeting):**
 
 ```
@@ -154,17 +194,17 @@ Here's why:
 Should I search Apollo for {techStack} users?
 ```
 
-**Apollo ABM (company domains):**
+**Prospeo ABM (company domains):**
 
 ```
-Since you have a **list of target companies**, I'd recommend **Apollo** with domain targeting.
+Since you have a **list of target company domains**, I'd recommend **Prospeo** with a domain filter.
 
 Here's why:
-- Apollo supports bulk domain lists (up to 190 companies per search)
+- Prospeo is the campaign-default path for supplied company-domain lists
+- We'll create a `domainFilterId` from the CSV or pasted domains before searching
 - We can find decision-makers at your exact target accounts
-- Just share the domains (e.g., stripe.com, notion.so) and I'll find your ICP at those companies
 
-Note: Reply rates may be lower than Signal Discovery or Sales Nav with POSTED_ON_LINKEDIN, since we can't filter for LinkedIn activity. Consider combining with a strong personalized message.
+Note: LinkedIn activity warmth may be lower than Signal Discovery or Sales Nav with POSTED_ON_LINKEDIN, so we should inspect the first review batch before scaling.
 
 Can you share your target company domains?
 ```
@@ -179,7 +219,8 @@ Do not hardcode provider options. Build them from the framework:
    - If user already has some other list shape that does not fit those CSV paths -> proceed with provider selection
    - If the user specifies a provider or research plan -> treat that as a hard override
    - Else if `providerPreference` override exists -> recommend that provider
-   - Else use the decision hierarchy above (Signal Discovery -> Sales Nav -> Apollo)
+   - Else use the decision hierarchy above only when there is no stronger source
+     direction (Signal Discovery -> Sales Nav -> Prospeo -> Apollo)
 2. Build options from `providerOrder` and `framework.providers[providerId].askOption`
 3. Mark the recommended option by appending " (Recommended)" if needed
 

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

@@ -49,9 +49,10 @@ for debug output.
 12. Sync the approved template into the campaign brief.
 13. After message approval, keep the watched app on Filter Leads while the
     bounded enrichment/filter cascade starts.
-14. Move to Messages only after at least one review row passes, generate and
-    review bounded messages, then hand off to Settings, sender, sequence, and
-    explicit launch greenlight.
+14. Move to Messages only after at least one review row passes and one generated
+    message is ready for review. Do not wait for a stronger sample once that
+    first passing message exists; review it, then hand off to Settings, sender,
+    sequence, and explicit launch greenlight.
 
 There is no normal approval-packet, commit-gate, atomic-mint, or local
 artifact-validation step. Those belong only to legacy validation/rehearsal
@@ -125,6 +126,16 @@ Default source order when the user has not supplied a source:
 3. broader Sales Nav role/title filters
 4. Prospeo account/contact expansion
 
+Use that order only when the brief has no stronger sourcing constraint. If the
+campaign is hiring-led, asks for companies actively hiring specific roles, asks
+for open-role/job-posting signals, or needs verified contacts at companies with
+those hiring signals, start with Prospeo. Prospeo supports
+`company_job_posting_hiring_for` and `company_job_posting_quantity`; Sales Nav
+does not provide hiring-by-role filters. For those campaigns, Signal Discovery
+can be a conversation-signal check if relevant hiring posts are likely, and
+Sales Nav is a LinkedIn activity/referral fallback rather than the main hiring
+filter.
+
 Before any provider prompt, search, source scout, or signal-discovery call,
 show a short source-plan gate and ask for approval. This first approval
 authorizes source scouting/search only. The gate must say, in plain language:
@@ -161,14 +172,30 @@ the target engager/source-candidate volume, the bounded campaign review-batch
 size, the cleanup risk, and the fallback if the selected posts look wrong. The
 approval label must describe the action with the count, such as "Approve
 scraping 3 Signal Discovery posts?" For Sales Nav or Prospeo, the label should
-name the specific search/import lane. Do not call `import_leads` or
-`confirm_lead_list` until this second source-action approval is granted.
+name the specific search/import lane and source lead count. Do not call
+`import_leads` or `confirm_lead_list` until this second source-action approval
+is granted.
+
+For Sales Nav and Prospeo, do not ask to import only the 25-row review batch at
+the source-action gate. First-page samples are for source math: compute sampled
+fit after conservative cleanup, project how many good-fit prospects the raw
+pool can yield, and keep refining filters while the projected good-fit pool is
+below the campaign target (normally about 150+ usable prospects unless the
+campaign/source defaults say otherwise). Once the lane clears the target, ask
+approval to materialize the source list with
+`targetLeadCount = min(rawResultCount, providerMax, ceil(targetGoodFitLeads /
+projectedFitRateAfterCleanup))`. After that source list is ready,
+`confirm_lead_list` imports only the bounded review batch into the campaign
+table for fit and message review.
+
 After the user approves this concrete source-action gate, do not show the
 Source Recommendation again and do not ask another source approval question.
 Acknowledge once, then call `import_leads` immediately with the approved source
-math. For Signal Discovery, pass `provider: "signal-discovery"`,
-`targetEngagerCount`, `maxPostsToScrape`, and `confirmed: true`; the tool owns
-moving the watch UI to source-list progress after a lead-list/job id exists.
+math. For Sales Nav/Prospeo, pass `targetLeadCount` as the approved source-list
+export count, not the review-batch size. For Signal Discovery, pass
+`provider: "signal-discovery"`, `targetEngagerCount`, `maxPostsToScrape`, and
+`confirmed: true`; the tool owns moving the watch UI to source-list progress
+after a lead-list/job id exists.
 
 For Signal Discovery, use this compact source-action approval shape after
 selected posts exist:
@@ -181,7 +208,7 @@ Use Signal Discovery first.
 **Good-fit target:** ~150 prospects after cleanup, enrichment, and filters<br>
 **Source-candidate plan:** scrape ~1,000 raw engagers using a conservative 15% fit-rate assumption<br>
 **Planning floor:** continue only when sampled/projected fit is at least 10% after cleanup; below that, switch to Sales Nav recent activity<br>
-**Review checkpoint:** import the first 25 leads into the campaign for fit and message review before scaling<br>
+**Review checkpoint:** after the source list exists, clone only the bounded review batch into the campaign for fit and message review<br>
 
 ### Selected posts
 
@@ -202,8 +229,9 @@ This gives enough volume to work toward ~150 good-fit prospects, while
 keeping the source tied to people already engaging with Claude Code outbound /
 AI-native sales workflows.
 
-**First pass:** build the source list, then import only the 25-lead review
-batch so we can inspect fit and messages before scaling.
+**First pass:** build the source list at the approved source-candidate target,
+then clone only the bounded review batch into the campaign so we can inspect
+fit and messages before sending.
 
 **Fallback:** if sampled/projected fit falls below 10%, or if the review batch
 is too vendor-heavy, agency-heavy, or off-ICP, switch to Sales Nav recent
@@ -213,7 +241,11 @@ activity.
 A source recommendation must show concrete evidence: source lane, filters or
 recipe, raw volume, sample size, sampled fits as n/N plus percentage/range,
 estimated usable prospects, cleanup risk, runner-up, and what approval
-authorizes.
+authorizes. For Sales Nav/Prospeo it must also show source export math:
+`rawResultCount`, `sampledFitRate`, conservative projected fit rate,
+`targetLeadCount` for the source list, and projected good-fit count from that
+export. If projected good-fit count is below target, the recommendation is to
+refine or broaden filters, not to import a 25-row batch.
 
 Supplied profile CSVs, company/domain CSVs, pasted domains, and existing
 Sellable lead lists are supported, but keep provider mechanics out of the first
@@ -222,24 +254,28 @@ customer-facing source-choice labels.
 ## Post-Lead Workstreams
 
 After `confirm_lead_list` imports a non-empty bounded review batch and
-`get_rows_minimal({ tableId: workflowTableId })` proves rows exist, call
-`get_post_find_leads_scout_registry` and start the Message Draft Builder branch
-immediately when the current host exposes that returned agent. Do this before
-asking the filter-choice question. If no real background branch can start, say
-the real sequence and do not claim background drafting is running.
-
-The message branch uses live CampaignOffer/source/table state as the source of
-truth and may draft while the user is choosing filters. It does not write
-message cells, enrich rows, attach sequences, or unlock Settings. The Lead Fit
-Builder branch starts only after the user chooses filters. Debug markdown/json
-artifacts are optional only.
+`get_rows_minimal({ tableId: workflowTableId })` proves rows exist, ask the
+filter-choice question immediately. Do not call
+`get_post_find_leads_scout_registry`, load filter/message subskill prompts, or
+spawn post-lead workers before that question. The only customer-facing work
+before the question should be a short review-batch summary and the choice:
+add filters, skip filters, or revise source.
+
+If the user chooses filters, then load the post-lead registry/reference needed
+for filtering and start the Lead Fit Builder. Also start the Message Draft
+Builder in the background from the same campaign/table basis as soon as the
+filter-choice answer is known. If the user skips filters, move the watched app to
+Messages and run the Message Draft Builder there. Debug markdown/json artifacts
+are optional only.
 
 When the user chooses filters, immediately call
 `update_campaign({ campaignId, enableICPFilters: true, currentStep: "create-icp-rubric", watchNarration })`
 before rubric thinking or branch work. The watched app should move to Filter
 Rules quickly. After `save_rubrics`, the watched app should move to
 `apply-icp-rubric` / Filter Leads so the user can see the saved filters are
-ready before message approval unlocks any enrichment or filtering.
+ready and wait there for the background message agent. Tell the user explicitly
+that a message agent is drafting the first-message template while enrichment,
+filtering, and Generate Message cells remain blocked.
 
 Lead Fit Builder persists production rubrics with `save_rubrics` when filters
 are enabled. It must not require `brief.md`, `lead-review.md`, or

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

@@ -274,14 +274,18 @@ keep the output numeric but do not claim the source scout was parallel or
 surface install status to the customer.
 
 For post-lead work, call `get_post_find_leads_scout_registry` after
+the user chooses filters, not before the filter-choice question. After
 `confirm_lead_list` imports a non-empty bounded review batch and
-`get_rows_minimal` proves rows exist. Start `post-find-leads-message-scout`
-immediately when real subagents are available, before asking the filter-choice
-question. Start `post-find-leads-filter-scout` only after the user chooses
-filters. This is the same registry pattern as source scouting, but the trigger
-for message drafting is review-batch import, not filter approval. The join gate
-is live branch readiness: saved rubrics or a resolved skip-filter choice, plus a
-message recommendation grounded in the same campaign/table basis.
+`get_rows_minimal` proves rows exist, ask add-filters vs skip-filters
+immediately. Once the user answers, start `post-find-leads-message-scout` /
+message generation from the same campaign/table basis. If the user chooses
+filters, also start `post-find-leads-filter-scout`, move the browser to Filter
+Rules, save rubrics, then keep the browser on Filter Leads while the message
+recommendation is reviewed. If the user skips filters, move the browser to
+Messages/message review. The join gate is live branch readiness: saved rubrics
+or a resolved skip-filter choice, plus a message recommendation grounded in the
+same campaign/table basis. Enrichment, filtering, and product Generate Message
+cells still wait for template approval.
 
 Only promise parallel post-lead work when parallel work actually started. If the
 host cannot or should not launch background branches, say the real sequence:

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

@@ -588,20 +588,9 @@
           ]
         },
         {
-          "action": "launch_message_draft_builder_after_review_batch_import",
-          "tool": "get_post_find_leads_scout_registry",
-          "target": "post-find-leads-message-scout",
-          "requiresNonEmptyRows": true,
-          "mustRunBefore": [
-            "filter-choice question",
-            "filter approval",
-            "save_rubrics"
-          ],
-          "mode": "background_when_host_supports_subagents",
-          "fallback": "if no real background branch can start, say the real sequence and do not claim background drafting is running",
-          "toolCallRequiredInBranch": "get_subskill_prompt({ subskillName: \"generate-messages\", offset, limit }) until hasMore=false",
-          "runtimeProofTransport": "CampaignOffer.watchNarration.workerDetails.messageDraftBuilder",
-          "purpose": "start the provisional message draft from the imported review batch immediately; do not defer this to filter approval"
+          "action": "summarize_review_batch_and_advance_to_filter_choice",
+          "purpose": "ask filter choice immediately; no post-lead registries, filter refs, or message prompts first",
+          "maxCustomerCopyLines": 4
         }
       ],
       "requiredCampaignState": [
@@ -611,8 +600,6 @@
       ],
       "allowedTools": [
         "get_subskill_prompt",
-        "get_subskill_asset",
-        "get_post_find_leads_scout_registry",
         "import_leads",
         "wait_for_lead_list_ready",
         "confirm_lead_list",
@@ -620,16 +607,18 @@
         "get_rows_minimal",
         "update_campaign",
         "AskUserQuestion",
-        "request_user_input",
-        "Task",
-        "spawn_agent"
+        "request_user_input"
       ],
       "doNotAllow": [
+        "get_post_find_leads_scout_registry",
+        "Task",
+        "spawn_agent",
         "list_senders",
         "queue_cells",
         "start_campaign",
         "enrich_with_prospeo",
-        "bulk_enrich_with_prospeo"
+        "bulk_enrich_with_prospeo",
+        "save_rubrics"
       ],
       "waitFor": "review_batch_imported",
       "transitions": {
@@ -659,6 +648,13 @@
           ]
         }
       ],
+      "hardRules": [
+        "ask_filter_choice_immediately_after_review_batch_import",
+        "do_not_call_get_subskill_prompt_before_filter_choice",
+        "do_not_call_get_subskill_asset_before_filter_choice",
+        "do_not_call_get_post_find_leads_scout_registry_before_filter_choice",
+        "do_not_spawn_post_lead_agents_before_filter_choice"
+      ],
       "requiredCampaignState": [
         "campaignId",
         "campaignBrief",
@@ -672,6 +668,11 @@
         "get_campaign_navigation_state"
       ],
       "doNotAllow": [
+        "get_subskill_prompt",
+        "get_subskill_asset",
+        "get_post_find_leads_scout_registry",
+        "Task",
+        "spawn_agent",
         "create_campaign",
         "list_senders",
         "import_leads",
@@ -693,7 +694,7 @@
     },
     {
       "id": "post-lead-workstreams",
-      "label": "Filter and message workstreams",
+      "label": "Filter workstream",
       "onEnter": [
         {
           "action": "persist_add_filters_approval",
@@ -715,17 +716,18 @@
           },
           "mustRunBefore": [
             "get_post_find_leads_scout_registry",
-            "launch_or_reuse_post_lead_workstreams",
+            "launch_lead_fit_builder_after_filter_choice",
             "save_rubrics"
           ]
         },
         {
           "tool": "get_post_find_leads_scout_registry",
-          "purpose": "load canonical post-lead worker names"
+          "purpose": "load canonical post-lead worker names only after the user has chosen filters"
         },
         {
-          "action": "launch_or_reuse_lead_fit_builder_and_existing_message_draft",
+          "action": "launch_lead_fit_builder_after_filter_choice",
           "mode": "parallel_when_host_supports_subagents",
+          "target": "post-find-leads-filter-scout",
           "inputs": [
             "campaignId",
             "campaignBrief",
@@ -734,9 +736,16 @@
             "reviewBatchRowIds/hash",
             "filterChoice"
           ],
-          "stateSource": "CampaignOffer and workflow table rows",
-          "debugFilesOptionalOnly": true,
-          "messageDraftRule": "reuse or join the Message Draft Builder branch that started immediately after confirm_lead_list; do not start first-time message drafting here unless the earlier branch failed to start"
+          "stateSource": "live campaign/table",
+          "debugFilesOptionalOnly": true
+        },
+        {
+          "action": "launch_message_draft_builder_after_filter_decision",
+          "mode": "parallel_when_host_supports_subagents",
+          "target": "post-find-leads-message-scout",
+          "when": "filters_enabled",
+          "doesNotQueueCells": true,
+          "customerNarration": "Say message agent is drafting."
         },
         {
           "action": "save_filter_rubrics_to_campaign",
@@ -793,10 +802,13 @@
       "hardRules": [
         "after_save_rubrics_currentStep_must_be_apply-icp-rubric",
         "do_not_move_browser_to_messages_until_filter_leads_step_is_current_or_filters_are_explicitly_skipped",
-        "message_draft_builder_start_is_not_deferred_until_filters"
+        "no_post_lead_worker_or_deep_prompt_before_filter_choice",
+        "lead_fit_builder_starts_only_after_filters_enabled",
+        "msg_draft_after_filter_choice",
+        "msg_draft_no_cells"
       ],
       "transitions": {
-        "post_lead_workstreams_ready": "message-review",
+        "post_lead_workstreams_ready": "message-generation",
         "revise_leads": "find-leads",
         "revise_rubric": "filter-rubric",
         "revise_messaging": "message-generation",
@@ -865,14 +877,23 @@
       "id": "message-generation",
       "label": "Message generation",
       "onEnter": [
+        {
+          "action": "set_message_review_visible_step_by_filter_choice",
+          "tool": "update_campaign",
+          "branchRules": [
+            "yes: currentStep=apply-icp-rubric; wait on Filter Leads",
+            "no: currentStep=messages; message review"
+          ],
+          "watchNarration.stage": "fit-message"
+        },
         {
           "action": "run_or_reconcile_message_draft_builder",
           "target": "post-find-leads-message-scout",
           "toolCallRequiredBeforeDraft": [
             "get_subskill_prompt({ subskillName: \"generate-messages\", offset, limit }) until hasMore=false",
-            "for approval-only parent-thread review, use get_subskill_asset({ subskillName: \"create-campaign-v2\", assetPath: \"references/message-review-safety-gate.md\" }) instead of loading generate-messages"
+            "parent approval uses references/message-review-safety-gate.md only"
           ],
-          "stateSource": "campaignBrief, selected source state, selectedLeadListId, workflowTableId, bounded review-batch row ids/hash",
+          "stateSource": "campaignBrief, source, selectedLeadListId, workflowTableId, review-batch row ids/hash",
           "outputState": "messageDraftRecommendation"
         }
       ],
@@ -887,11 +908,12 @@
         "get_subskill_asset",
         "get_campaign",
         "get_rows_minimal",
+        "update_campaign",
         "AskUserQuestion",
         "request_user_input"
       ],
       "toolRules": [
-        "Before message drafting, the Message Draft Builder branch loads the full get_subskill_prompt({ subskillName: \"generate-messages\" }) prompt and drafts from campaignBrief, selected source state, selectedLeadListId, workflowTableId, and imported review-batch rows. For approval-only parent-thread template review, load references/message-review-safety-gate.md and do not load the full generate-messages prompt.",
+        "Message Draft Builder loads full get_subskill_prompt({ subskillName: \"generate-messages\" }) from live state. Parent approval uses message-review-safety-gate only.",
         "Do not use brief.md, lead-review.md, or lead-sample.json as required live state; those files are optional debug context only.",
         "The compact messageDraftRecommendation must return templateRecommendation, tokenFillRules, renderedSample, concerns, status, basisToken, outputAt, outputHash, and error or retry detail.",
         "If campaign/source/table/review-batch basis does not match, classify the output stale or blocked."
@@ -902,7 +924,6 @@
         "save_rubrics",
         "import_leads",
         "confirm_lead_list",
-        "update_campaign",
         "queue_cells",
         "start_campaign",
         "generate_messages"
@@ -1124,8 +1145,14 @@
           "cellSource": "pending_generate_message_cells_for_passing_rows using approved_campaign_brief_template"
         },
         {
-          "tool": "wait_for_campaign_table_ready",
-          "purpose": "wait_for_generate_message_cells_to_complete"
+          "tool": "wait_for_rubric_results",
+          "purpose": "wait_for_first_passing_generated_message",
+          "requiredValues": {
+            "includeRows": false,
+            "minPassedCount": 1,
+            "minMessagesCount": 1
+          },
+          "readVia": "stats_only_tool_result"
         },
         {
           "action": "observe_generate_message_results",
@@ -1169,25 +1196,24 @@
             "currentStep": "auto-execute-messaging",
             "watchNarration.stage": "review-ready"
           },
-          "watchNarrationRule": "Say what just happened, that review-batch messages are ready in Messages, and that the next action is reviewing or approving generated messages before Settings."
+          "watchNarrationRule": "Say the first passing generated message is ready in Messages; next is review before Settings."
         },
         {
           "action": "ask_generated_message_review_choice",
           "uses": "request_user_input",
           "choices": [
-            "Approve generated messages",
+            "Approve generated message and continue to Settings",
             "Revise filters",
             "Revise message template",
             "Pause here"
-          ],
-          "rule": "Do not advance to Settings until the generated review-batch messages have been reviewed and approved."
+          ]
         }
       ],
       "allowedTools": [
         "get_subskill_asset",
         "get_rows_minimal",
         "queue_cells",
-        "wait_for_campaign_table_ready",
+        "wait_for_rubric_results",
         "update_campaign",
         "AskUserQuestion",
         "request_user_input"
@@ -1201,6 +1227,7 @@
       "hardRules": [
         "critique_failure_never_escalates",
         "critique_sample_size_bounded_by_config",
+        "first_passing_generated_message_unblocks_review",
         "critics_fixed_at_targeting_copy_voice",
         "synthesis_enforces_phase_84_token_contract",
         "opus_reserved_for_highest_value_subset",

package/skills/create-campaign-v2/references/sample-validation-loop.md

@@ -60,9 +60,10 @@ auto-revise leads.
      explicit batch count anyway so future larger expansion batches do not
      accidentally stop early
      (see §Known Tool Behaviors #3)
-   - minPassedCount=1 means one passing filtered row unblocks Step 15
-     Generate Message observation. Do not wait for all sample rows to finish
-     before messages start.
+   - minPassedCount=1 means one passing filtered row unblocks Step 15 Generate
+     Message observation. Step 15 then waits only for one generated message
+     (`minMessagesCount=1`) before review. Do not wait for all sample rows to
+     finish before messages start.
 
 7. call `wait_for_rubric_results` with `includeRows=false`; extract ONLY:
    - ready: boolean
@@ -101,7 +102,9 @@ auto-revise leads.
 10. branch:
    if passInSample >= 1:
        proceed to Step 15 (auto-execute-messaging) with currently passing rows
-       so Generate Message can start without waiting for the full sample
+       so Generate Message can start without waiting for the full sample. Once
+       one passing generated message is ready, stop for user review instead of
+       waiting for a stronger sample.
    else:
        diagnose (see Brief-vs-List Diagnosis below)
        revisionRound += 1
@@ -179,7 +182,8 @@ processing makes the experience feel frozen.
 
 Workaround: treat timeout stats as a partial sample. If at least one row has
 passed, move to Step 15 and observe or queue Generate Message for the passing
-rows. If zero rows have passed and no active processing is visible, stop at
+rows; Step 15 stops when one generated message is ready. If zero rows have
+passed and no active processing is visible, stop at
 `Status: sample-needs-revision` before Settings. Show the completed / passed /
 pending counts and ask whether to revise source, revise filter/rubric, or wait
 once only if active processing is still visible.

package/skills/create-campaign-v2/references/step-13-import-leads.md

@@ -106,7 +106,7 @@ fills the source lead list; it does **not** clone rows into the campaign table:
 ```text
 import_leads({
   campaignOfferId,
-  targetLeadCount: <sourceCandidateTarget; provider default>,
+  targetLeadCount: <sourceCandidateTarget from approved good-fit math>,
   // Signal Discovery only:
   targetEngagerCount: <ceil(targetGoodFitLeads / sampledFitRateAfterCleanup)>,
   maxPostsToScrape: <postsNeeded from approved math>
@@ -114,9 +114,15 @@ import_leads({
 ```
 
 Provider is inherited from the selected source decision (not re-selected here)
-and should already be saved on the campaign before import. Response returns
-`{ imported, skipped, duplicates }` — surface all three to the escalation logic
-so dedup ratios are visible.
+and should already be saved on the campaign before import. For Sales Nav and
+Prospeo, `<sourceCandidateTarget>` is not the 25-row review batch. It is the
+source-list export/materialization count from the approved source math:
+`min(rawResultCount, providerMax, ceil(targetGoodFitLeads /
+projectedFitRateAfterCleanup))`. If projected good fits remain below the target
+(often about 150+ usable prospects unless the campaign/source defaults specify
+otherwise), return to find-leads and refine filters before import. Response
+returns `{ imported, skipped, duplicates }` — surface all three to the
+escalation logic so dedup ratios are visible.
 
 For Signal Discovery, do not scrape every currently selected/promoted sample
 post by default. Before `import_leads`, reconcile selected posts with the