@sellable/mcp 0.1.0

package/skills/create-campaign/SKILL.md

@@ -0,0 +1,286 @@
+---
+name: create-campaign
+description: Guide a user through creating a LinkedIn outbound campaign with profile enrichment, sender research, JTBD positioning, lead sourcing, and ICP filtering. Use when starting a fresh campaign or resuming an existing one (cmp_... ID). Handles provider selection, brief generation, and lead import with watch-mode UI orientation.
+visibility: internal
+---
+
+# Create Campaign (Legacy)
+
+Legacy internal workflow kept for compatibility with older direct MCP callers.
+The public `sellable:create-campaign` skill now loads the approval-gated
+`create-campaign-v2` workflow.
+
+You are a LinkedIn Outbound Expert specializing in booking meetings for B2B companies. Craft simple, conversational outreach that gets busy executives to respond.
+
+**Data integrity rule**: Never hallucinate or make up social proof, reviews, case studies, or success metrics. Only use data from context or explicitly provided by the user. If missing, mark as "Not provided" -- never invent placeholders.
+
+**Objective**: Create a LinkedIn outbound campaign through guided discovery: enrich profile, gather positioning via AskUserQuestion, draft a JTBD-based campaign angle, create campaign with brief, and hand off to lead sourcing. Campaign created with positioning, brief saved, user ready for leads.
+
+## Bootstrap
+
+1. Load tools (SINGLE message with ToolSearch calls):
+   - `ToolSearch("select:mcp__sellable__enrich_sender")`
+   - `ToolSearch("select:mcp__sellable__create_campaign")`
+   - `ToolSearch("select:mcp__sellable__update_campaign")`
+   - `ToolSearch("select:mcp__sellable__update_campaign_brief")`
+   - `ToolSearch("select:mcp__sellable__bootstrap_create_campaign")`
+   - `ToolSearch("select:mcp__sellable__get_campaign_context")`
+   - `ToolSearch("select:mcp__sellable__get_auth_status")`
+   - `ToolSearch("select:mcp__sellable__wait_for_lead_list_ready")`
+   - `ToolSearch("select:mcp__sellable__wait_for_campaign_table_ready")`
+   - `ToolSearch("select:mcp__sellable__get_rows_minimal")`
+   - `ToolSearch("select:mcp__sellable__list_subskill_prompts")`
+   - `ToolSearch("select:mcp__sellable__get_subskill_prompt")`
+   - `ToolSearch("select:mcp__sellable__search_subskill_prompts")`
+   - `ToolSearch("select:mcp__sellable__complete_sender_research")`
+2. Detect optional campaign ID (pattern: `cmp_...`).
+3. Resume boundary (STRICT):
+   - No campaignId from user -> stay in fresh-create mode.
+   - Do NOT call `get_campaigns` or `get_campaign` to hunt for IDs.
+   - Do NOT call `create_campaign({ campaignId: ... })` unless that exact ID came from user input.
+4. Call `bootstrap_create_campaign({ campaignId? })`.
+5. If `safeToProceed !== true`: STOP. Show `blockingErrors` and `nextStep`. Fail-fast: `Bootstrap incomplete. Resolve blockingErrors and rerun bootstrap_create_campaign before provider/search/import tools.`
+6. Continue only when preflight passes.
+7. Bootstrap no longer returns skill prompt or policy prose (both loaded via host). `framework.policy` = `"[loaded via host skill prompt]"`.
+8. Load framework and obey: `framework.flow`, `framework.providerRegistry`, `framework.providers`, `framework.plugins`, `framework.overrides`.
+9. Resume-first when campaignId provided: call `create_campaign({ campaignId })` for watchUrl, then `get_campaign_context({ campaignId, refresh: true })`. Use `context.navState` + `framework.flow` to decide next step.
+10. Do NOT load `get_linkedin_profile` -- use `enrich_sender` instead.
+11. Do NOT load `.sellable/` config files at bootstrap -- other skills load them when relevant.
+12. Check if user provided context (LinkedIn URL, company info, or campaign direction).
+13. Workspace + LinkedIn URL (REQUIRED after bootstrap):
+    - If bootstrap succeeded: state workspace as fact and ask for LinkedIn URL in one message. Example: "Starting a campaign in **{workspaceName}**. What's your LinkedIn URL? I'll pull your background, company info, and proof points to build the positioning."
+    - If bootstrap failed with `error.type: "workspace"` (no active workspace): follow the `blockingErrors` guidance -- call `list_workspaces` to show available workspaces, then `set_active_workspace` with the user's choice. Re-run `bootstrap_create_campaign` after workspace is set.
+14. If user already provided LinkedIn URL or context, still state the workspace but skip the URL ask.
+
+**Phase 5 tools (load after provider selection):**
+
+- `ToolSearch("select:mcp__sellable__get_provider_prompt")` -- REQUIRED preflight gate
+- `ToolSearch("select:mcp__sellable__search_apollo")` OR `search_sales_nav` OR `search_signals` -- based on provider
+- `ToolSearch("select:mcp__sellable__import_leads")`
+- `ToolSearch("select:mcp__sellable__confirm_lead_list")`
+- `ToolSearch("select:mcp__sellable__wait_for_lead_list_ready")`
+- `ToolSearch("select:mcp__sellable__load_csv_linkedin_leads")`
+
+## Tools
+
+**Framework + Plugins**: `bootstrap_create_campaign` (returns auth + framework + subskill catalog), `get_campaign_context`, `list_subskill_prompts`. `get_campaign_framework` only if bootstrap didn't return framework.
+**Enrichment**: `enrich_sender` (CALL FIRST -- returns clientProspectId)
+**Research**: `get_subskill_prompt({ subskillName: "research-sender" })` -- dedicated protocol, not generic `research`
+**Campaign**: `create_campaign`, `update_campaign`, `update_campaign_brief`
+**Lead Sourcing**: `get_provider_prompt` (CALL FIRST for provider), `search_apollo`, `search_sales_nav`, `search_signals`, `load_csv_domains`, `load_csv_linkedin_leads`, `import_leads`, `confirm_lead_list`, `wait_for_lead_list_ready`, `wait_for_campaign_table_ready`, `get_rows_minimal`
+**Questions**: `AskUserQuestion` -- max 4 questions per call, 2-4 options each
+**Chrome (debug only)**: `read_page`, `get_page_text` -- use only when user reports "I don't see it"
+
+## Phase 0: Apply Framework (from bootstrap)
+
+Bootstrap already returned the full framework. Do NOT call `get_campaign_framework` again -- use `bootstrap.framework` directly. Only call `get_campaign_framework` if bootstrap didn't return it (e.g., framework check failed and was retried).
+
+Apply overrides:
+
+- `providerOrder = overrides.providerOrder || providerRegistry.defaultProviderOrder`
+- `providerPreference = overrides.providerPreference || null`
+- `defaultLeadTarget = overrides.defaultLeadTarget || providerMaxImportCount`
+- `providerMaxImportCount` from `lead-import-limits.json` (active provider's `maxImportCount`; default 250)
+
+Subskill handoff: if a flow step includes `action: "handoff_to_subskill"`, call `get_subskill_prompt({ subskillName: action.target })` and follow immediately.
+
+Review `framework.plugins` and incorporate factual constraints. If warnings, summarize briefly and continue.
+
+**Watch mode**: After every `update_campaign({ currentStep: ... })`, say what changed, tell user what to expect in watch link. In `step-by-step` mode pause for confirmation; in `ask-when-needed`/`autonomous` continue unless a required user choice is missing. Check `navigation.blockedAt` and `navigation.missing` after each step change.
+
+## Phase 1: Initial Discovery
+
+### Step 1: Enrich Sender (REQUIRED)
+
+1. Narrate: "Enriching your LinkedIn profile..."
+2. Call `enrich_sender` with LinkedIn URL without `forceRefresh` (cache-first, compact mode default)
+3. GATE: Store `clientProspectId` from response -- hard stop if missing
+4. Extract: `clientProspectId`, `sender` (fullName, headline, title, company), `companyDomain`
+5. When `enrichmentStatus === "complete"`, also extract `companySnapshot`, `senderBackground`, `proofDigest`
+
+### Step 2: Confirm Company (REQUIRED)
+
+GATE: Do NOT start research until the campaign company/domain is confirmed.
+
+AskUserQuestion: "Yes, research this" / "Different company" (see `references/question-examples.md` for JSON shape).
+
+If "Different company": ask for domain, re-confirm before proceeding.
+
+### Step 3: Research Depth Decision
+
+- `proofDigest.caseStudyCount > 0` AND `proofDigest.reviewHighlight` exists -> `minimal-verification` (0 agents, ~2s)
+- Otherwise -> `deep-proof` (2 agents in parallel, ~30s)
+
+### Step 4: Run Sender Research Subskill
+
+Send progress note: "Running a quick research pass for case studies and growth signals (~30s)..."
+
+1. Call `get_subskill_prompt({ subskillName: "research-sender" })`
+2. Follow instructions directly -- do NOT delegate to generic `research`
+3. Pass full `enrich_sender` response as `enrichSender` input
+4. GATE: `complete_sender_research` must finish before `create_campaign`
+5. Proof rule: use research if stronger, keep enrichment if not, never fabricate
+
+**If no URL provided:** Ask for LinkedIn profile URL.
+
+## Phase 2: Confirm Scope
+
+After confirmation + research, single AskUserQuestion anchored to companyDomain: "Draft one for me" / "I have an idea" / "Different company/offer" (see `references/question-examples.md`).
+
+- "I have an idea" -> ask for target + angle in 1-2 sentences
+- "Different company/offer" -> ask for correct domain + description, re-run enrichment + research
+- "Draft one for me" -> proceed to Phase 3
+
+## Phase 3: Draft Campaign Angle
+
+Draft ONE JTBD-based angle using sender research + user input + configs.
+
+Leverage configs if loaded: `icp.md` for Target, `cross-skill.md` for messaging insights, `outbound.md` for structure.
+
+Default format: Target / Pain / Offer / Proof (if provided).
+
+GATE: Ask "Want me to use this, or tweak anything?" -- wait for approval.
+
+For quality patterns, Read `references/campaign-quality.md`.
+
+## Phase 4: Create Campaign
+
+### Step 1: Create
+
+Call `create_campaign({ name, clientProspectId, campaignBrief })`.
+
+- GATE: `clientProspectId` MUST come from Phase 1 `enrich_sender`. If missing, call `enrich_sender` first.
+- For brief format, Read `references/brief-template.md`.
+
+### Step 2: Show Watch Link
+
+"Campaign created! **Watch link:** [watchUrl]. Open to see your campaign brief."
+GATE: Wait for user confirmation before proceeding.
+
+### Step 3: Set Execution Mode
+
+Explain interaction modes, then AskUserQuestion: step-by-step (Recommended) / use best judgment / ask when needed.
+Store as `interactionMode`: `step-by-step` / `autonomous` / `ask-when-needed`.
+Default `ask-when-needed` if ambiguous. (See `references/question-examples.md` for preface + JSON.)
+
+## Phase 5: Lead Provider Selection
+
+Execution by `interactionMode`:
+
+- `step-by-step`: pause for provider choice, import, confirm. After choice confirmed, run preflight + search immediately.
+- `autonomous`: proceed with best judgment unless a required decision is missing.
+- `ask-when-needed`: skip repetitive confirmations, pause only for high-impact branches.
+
+### Step 1: Update Step
+
+`update_campaign({ campaignId, currentStep: "pick-provider" })`. Orient user.
+
+### Step 2: Recommend Provider
+
+Analyze ICP against `framework.providers[*].recommendation` fields and `recommendation.prose` template.
+For detailed decision logic, Read `references/provider-selection-strategy.md`.
+Build AskUserQuestion from `providerOrder` + `askOption` (not hardcoded).
+GATE: User selects provider.
+
+### Step 3: Normalize Selection
+
+Store `labelToProviderId` map, resolve `providerId`. Load `providerConfig = framework.providers[providerId]`. Fallback: first valid provider in `providerOrder`.
+
+### Step 4: Update Campaign Step
+
+`update_campaign({ campaignId, currentStep: providerConfig.currentStep, leadSourceProvider: providerConfig.leadSourceProvider })`. Orient user with `providerConfig.watch.stepVisible`.
+
+### Step 5: Provider Preflight
+
+GATE: If `providerConfig.promptProvider` exists, MUST call `get_provider_prompt({ provider: providerConfig.promptProvider, confirmed: true })` BEFORE any search.
+If `promptProvider` is null: manual branch -- tell user to upload list in UI, wait for confirmation, proceed to Phase 6.
+
+### Step 6: Execute Search
+
+Follow provider prompt instructions for search workflow.
+
+If the user already has a CSV on disk:
+
+- LinkedIn profile CSV: use `load_csv_linkedin_leads` instead of provider search + `import_leads`
+- Company-domain CSV: use `load_csv_domains`, then continue with provider search using the returned `domainFilterId`
+
+### Step 7: Import and Wait
+
+1. Call `import_leads`.
+2. If `needsModeSelection: true`: GATE -- AskUserQuestion add/replace. Do NOT assume. Re-call `import_leads` with user's choice.
+3. Call `wait_for_lead_list_ready({ campaignOfferId, jobId, targetLeadCount })`.
+   GATE: Handle each `ready: false` reason:
+   - `cancelled`: the operator cancelled this import; restart with tighter filters if needed
+   - `import_failed` / `stalled_import`: tell user, ask to retry
+   - `tool_timeout_guard` / `timeout`: tell user polling timed out, re-run wait
+   - `missing_job_id`: ask for ID
+   - NEVER say "running successfully" unless `ready: true`
+
+### Cancelling and restarting mid-import
+
+If the operator realizes the active filter is wrong while an import is in flight, call `cancel_lead_import` with `{ campaignOfferId, tableId, provider }`. All three fields are required; there is no auto-detect. Pass the provider from the active campaign context.
+
+Partial rows are preserved. Provider credits are not refunded. After cancel, call `import_leads` again with the new filters. `wait_for_lead_list_ready` returns `{ ready: false, reason: "cancelled" }` for the old import until the new one starts.
+
+Supported in this phase: `apollo`, `prospeo`, and `sales-nav`. Signal Discovery cancel is tracked in a follow-on phase.
+
+### Step 8: User Reviews Lead List (HARD STOP)
+
+**GATE: Do NOT call `confirm_lead_list` until the user explicitly confirms.**
+
+Orient user: "[X] leads found. Review the lead list in the watch link and let me know when it looks good."
+
+STOP HERE. Wait for user to say "looks good", "confirmed", "yes", etc. This gate applies in ALL modes including `autonomous`. The user must review the list before it gets imported into the campaign table.
+
+### Step 9: Confirm and Post-Import
+
+Only after user confirms:
+
+1. Call `confirm_lead_list({ campaignOfferId, jobId, targetLeadCount })`. Narrate: "Importing leads into your campaign table..."
+2. `update_campaign({ campaignId, currentStep: "filter-choice" })`.
+3. `wait_for_campaign_table_ready({ campaignId })` -- GATE: must be `ready: true`.
+4. `get_campaign_context({ campaignId, refresh: true })`.
+5. `get_rows_minimal({ tableId: workflowTableId, limit: 10, page: 1 })`.
+6. Filter recommendation: compare sample to ICP. Pick Add filters / Skip filters / Refine list first. Warn if list is small (<150) or ICP already narrow.
+
+## Phase 6: Hand Off
+
+**If "add filters":**
+
+- `update_campaign({ campaignId, currentStep: "filter-rules" })`
+- Do NOT set `enableICPFilters: true` yet
+- Hand off to `create-rubric` via `get_subskill_prompt`
+
+**If "skip filters":**
+
+- `update_campaign({ campaignId, currentStep: "messages", enableICPFilters: false, useMessagingTemplate: false })`
+- `get_campaign_context({ campaignId, refresh: true })` + `get_rows_minimal({ tableId: workflowTableId, limit: 5 })`
+- Show lead preview, offer to draft first message
+
+**Debug**: If user reports missing content, use `read_page({ filter: "interactive" })`.
+
+## Rules
+
+1. Never hallucinate social proof -- mark "Not provided"
+2. JTBD framework -- tasks on their TODO list today
+3. Single best meeting value -- ONE offer
+4. Title format: "[Meeting Value] for [Target Audience]"
+5. No emojis. Bold sparingly.
+6. Max 1-2 questions per phase
+7. Auto-proceed on affirmatives: yes/looks good/continue/ok/sure/ready/next/go ahead/let's go
+8. Narrate progress: "Enriching your profile...", "Creating campaign..."
+9. Never use WebSearch more than once in a row
+10. Believable transformations (15-30%, not 10x)
+11. Blank lines between thoughts. Max 2-3 sentences per paragraph.
+12. Social proof = user's answer verbatim
+13. Subskills via `get_subskill_prompt` only, never as slash commands
+14. Chrome tools for debugging only (user reports "I don't see it")
+
+## References
+
+| File                                        | Load when                                    |
+| ------------------------------------------- | -------------------------------------------- |
+| `references/provider-selection-strategy.md` | Phase 5, before recommending provider        |
+| `references/brief-template.md`              | Phase 4, when writing campaign brief         |
+| `references/campaign-quality.md`            | Phase 3, when drafting campaign angle        |
+| `references/question-examples.md`           | Any phase, for AskUserQuestion JSON examples |

package/skills/create-campaign/context/README.md

@@ -0,0 +1,67 @@
+# Create Campaign Customization
+
+This folder is the safe place to add context and defaults without editing `SKILL.md`.
+
+## How it works
+
+- `context/registry.json` is the source of truth.
+- The registry currently uses a `plugins` array; treat each item as a context entry.
+- The MCP tool `get_campaign_framework` loads every enabled entry listed there.
+- Each entry can contribute:
+  - Freeform context (from the file)
+  - Structured overrides (from the registry entry)
+
+## File responsibilities
+
+- `context.md`
+  - Organization-wide truths and hard constraints
+  - Brand voice rules that should apply broadly
+  - Compliance or proof restrictions
+  - No campaign-specific examples or draft copy
+- `learnings.md`
+  - Short, factual notes from observed campaign outcomes
+  - What worked, what failed, what converted better
+  - No aspirational advice or invented numbers
+- `references/*.md`
+  - Reusable examples, contrastive good/bad patterns, and prompt inspiration
+  - Offer structures, token-fill examples, calibration examples
+  - This is where "what good looks like" should live, not in `context.md`
+
+## Add a new context file
+
+1. Copy `_TEMPLATE.md` to a new file in this folder.
+2. Add an entry to `context/registry.json` with `enabled: true`.
+3. (Optional) Add overrides in the registry entry.
+
+## Overrides (registry.json)
+
+Use overrides to adjust deterministic behavior:
+
+```json
+{
+  "overrides": {
+    "providerPreference": "sales-nav",
+    "providerOrder": ["sales-nav", "apollo", "signal-discovery"],
+    "defaultLeadTarget": 250,
+    "researchMode": "user-directed",
+    "researchNotes": "Always start with Sales Nav + posted recently"
+  }
+}
+```
+
+Prefer leaving `defaultLeadTarget` unset so the provider max from `lead-import-limits.json`
+is used automatically.
+
+## Learning log
+
+Add short, factual notes to `learnings.md`. It is loaded automatically.
+
+When adding examples:
+
+- Put organization-wide truths in `context.md`
+- Put observed outcomes in `learnings.md`
+- Put reusable prompt examples in:
+  - `references/campaign-quality.md`
+  - `references/offer-patterns.md`
+  - `references/token-fill-examples.md`
+  - `references/copy-calibration-examples.md`

package/skills/create-campaign/context/_TEMPLATE.md

@@ -0,0 +1,12 @@
+# Context File: <name>
+
+Describe any context that should shape campaign creation.
+
+## What this plugin changes
+
+- Example: prefer Sales Navigator for enterprise ICPs
+- Example: exclude healthcare and government
+
+## Evidence-backed notes only
+
+Do not add claims unless they are true and supported.

package/skills/create-campaign/context/context.md

@@ -0,0 +1,35 @@
+# Campaign Context
+
+Use this file for organization-wide truths that should influence every campaign.
+
+## Global Rules
+
+- Clear over clever.
+- Use only real proof, logos, testimonials, or metrics that came from the client or trusted research.
+- If proof is thin, surface it as an open question instead of filling the gap with generic claims.
+- Default to 5th-grade readability unless the buyer, industry, or cited material clearly requires more technical language.
+- Messages should sound like a human peer, not a landing page or an AI writing assistant.
+- Imperfection is acceptable when it improves naturalness. Polished does not mean sterile.
+
+## Offer Constraints
+
+- Prefer low-friction offers that give value before asking for time.
+- Avoid generic "free audit", "free assessment", or framework-named offers unless the deliverable is concrete and differentiated.
+- If the prospect has only shown mild interest, the next ask should usually be easier than booking a meeting.
+
+## Proof Discipline
+
+- Named proof beats vague credibility claims.
+- Use the client's own words, customer language, and concrete product specifics when available.
+- Never overstate transformations or invent quantitative outcomes.
+
+## Scope
+
+Good contents for this file:
+
+- Compliance constraints
+- Cross-client voice principles
+- Global exclusions
+- Proof rules
+
+Do not put campaign-specific examples or calibration snippets here. Those belong in the reference docs.

package/skills/create-campaign/context/learnings.md

@@ -0,0 +1,16 @@
+# Campaign Learnings
+
+This log captures what has worked in real campaigns.
+
+Entries should be short, specific, and based on observed outcomes.
+
+**Cross-skill learnings** that would help other skills (engage, create-post) should ALSO be written to `.sellable/insights/cross-skill.md` so the entire system learns.
+
+## Log
+
+- 2026-01-25: Initialized learning log. Add entries manually when outcomes are observed.
+- 2026-04-08: Lower-friction "send something valuable first" offers often convert warm interest better than asking for a meeting immediately.
+- 2026-04-08: A/B CTA structures are useful when one option is passive or lightweight and the other is a higher-commitment path.
+- 2026-04-08: 5th-grade readability and peer tone are quality constraints, not optional polish.
+- 2026-04-08: Token-fill quality matters enough to warrant explicit good and bad examples; awkward interpolation can ruin otherwise strong copy.
+- 2026-04-08: Positive reply rate does not guarantee meetings if the follow-up ask is too heavy for the prospect's level of intent.

package/skills/create-campaign/context/registry.json

@@ -0,0 +1,19 @@
+{
+  "version": "v1",
+  "plugins": [
+    {
+      "id": "context",
+      "path": "mcp/sellable/skills/create-campaign/context/context.md",
+      "enabled": true,
+      "description": "Organization-wide truths, constraints, and messaging rules that should influence every campaign.",
+      "overrides": {}
+    },
+    {
+      "id": "learnings",
+      "path": "mcp/sellable/skills/create-campaign/context/learnings.md",
+      "enabled": true,
+      "description": "Observed campaign outcomes and lightweight learnings; reusable prompt examples live in references/*.md.",
+      "overrides": {}
+    }
+  ]
+}

package/skills/create-campaign/core/flow.v1.json

@@ -0,0 +1,217 @@
+{
+  "version": "v1",
+  "workflow": "campaign-builder",
+  "principle": "State machine first, prose second",
+  "events": [
+    "campaign_created",
+    "user_ready_for_leads",
+    "provider_selected",
+    "provider_prompt_loaded",
+    "leads_imported",
+    "user_ready_for_rubric",
+    "user_filter_choice",
+    "user_filter_choice_add",
+    "user_filter_choice_skip"
+  ],
+  "steps": [
+    {
+      "id": "campaign-created",
+      "label": "Campaign Brief",
+      "onEnter": [
+        {
+          "tool": "create_campaign",
+          "requiredFields": ["clientProspectId", "campaignBrief"]
+        }
+      ],
+      "allowedTools": [
+        "create_campaign",
+        "update_campaign_brief",
+        "AskUserQuestion"
+      ],
+      "watchRequired": true,
+      "waitFor": "user_ready_for_leads",
+      "transitions": {
+        "user_ready_for_leads": "pick-provider"
+      }
+    },
+    {
+      "id": "pick-provider",
+      "label": "Provider Selection",
+      "currentStepValue": "pick-provider",
+      "onEnter": [
+        {
+          "tool": "update_campaign",
+          "requiredFields": ["campaignId", "currentStep"],
+          "requiredValues": {
+            "currentStep": "pick-provider"
+          }
+        },
+        {
+          "action": "watch_mode_orient"
+        }
+      ],
+      "allowedTools": [
+        "update_campaign",
+        "confirm_lead_list",
+        "wait_for_campaign_table_ready",
+        "AskUserQuestion"
+      ],
+      "watchTemplates": {
+        "change": "I moved you to provider selection.",
+        "watch": "You should see the provider selection step in the watch link now.",
+        "wait": "Tell me when you see it, and I will continue."
+      },
+      "waitFor": "provider_selected",
+      "transitions": {
+        "provider_selected": "provider-search"
+      }
+    },
+    {
+      "id": "provider-search",
+      "label": "Provider Search",
+      "onEnter": [
+        {
+          "tool": "update_campaign",
+          "requiredFields": ["campaignId", "currentStep", "leadSourceProvider"]
+        },
+        {
+          "action": "watch_mode_orient"
+        },
+        {
+          "tool": "get_provider_prompt",
+          "requiredFields": ["provider"]
+        }
+      ],
+      "allowedTools": [
+        "update_campaign",
+        "get_provider_prompt",
+        "search_apollo",
+        "search_sales_nav",
+        "search_prospeo",
+        "search_signals",
+        "select_promising_posts",
+        "set_headline_icp_criteria",
+        "import_leads",
+        "wait_for_lead_list_ready",
+        "cancel_lead_import",
+        "confirm_lead_list",
+        "AskUserQuestion"
+      ],
+      "watchTemplates": {
+        "change": "I opened the {{provider.label}} step.",
+        "watch": "You should now see the {{provider.label}} search UI in the watch link.",
+        "wait": "I will start provider preflight + search now. If the step does not look right in the watch link, tell me and I will pause to debug."
+      },
+      "waitFor": "leads_imported",
+      "transitions": {
+        "leads_imported": "confirm-lead-list"
+      }
+    },
+    {
+      "id": "confirm-lead-list",
+      "label": "Confirm Lead List",
+      "currentStepValue": "confirm-lead-list",
+      "onEnter": [
+        {
+          "tool": "update_campaign",
+          "requiredFields": ["campaignId", "currentStep"],
+          "requiredValues": {
+            "currentStep": "confirm-lead-list"
+          }
+        },
+        {
+          "action": "watch_mode_orient"
+        }
+      ],
+      "allowedTools": ["update_campaign", "AskUserQuestion"],
+      "watchTemplates": {
+        "change": "I moved you to the lead list confirmation step.",
+        "watch": "You should see the lead list we found and can confirm it looks right.",
+        "wait": "Tell me when it looks good, and I will move to ICP scoring."
+      },
+      "waitFor": "user_ready_for_rubric",
+      "transitions": {
+        "user_ready_for_rubric": "filter-choice"
+      }
+    },
+    {
+      "id": "filter-choice",
+      "label": "Enable Filtering",
+      "currentStepValue": "filter-choice",
+      "onEnter": [
+        {
+          "tool": "update_campaign",
+          "requiredFields": ["campaignId", "currentStep"],
+          "requiredValues": {
+            "currentStep": "filter-choice"
+          }
+        },
+        {
+          "action": "watch_mode_orient"
+        }
+      ],
+      "allowedTools": [
+        "update_campaign",
+        "wait_for_campaign_table_ready",
+        "get_campaign_context",
+        "get_rows_minimal",
+        "AskUserQuestion"
+      ],
+      "watchTemplates": {
+        "change": "I moved you to the Enable Filtering step.",
+        "watch": "You should see the yes/no choice for ICP filtering.",
+        "wait": "I will sample the imported leads and then ask whether you want to add filters or skip."
+      },
+      "waitFor": "user_filter_choice",
+      "transitions": {
+        "user_filter_choice_add": "handoff",
+        "user_filter_choice_skip": "messages-preview"
+      }
+    },
+    {
+      "id": "messages-preview",
+      "label": "Messages",
+      "currentStepValue": "messages",
+      "onEnter": [
+        {
+          "tool": "update_campaign",
+          "requiredFields": ["campaignId", "currentStep"],
+          "requiredValues": {
+            "currentStep": "messages"
+          }
+        },
+        {
+          "tool": "get_campaign_context",
+          "requiredFields": ["campaignId"]
+        },
+        {
+          "tool": "get_rows_minimal",
+          "requiredFields": ["tableId"]
+        }
+      ],
+      "allowedTools": [
+        "update_campaign",
+        "get_campaign_context",
+        "get_rows_minimal",
+        "get_table_rows",
+        "AskUserQuestion"
+      ],
+      "terminal": true
+    },
+    {
+      "id": "handoff",
+      "label": "Handoff to Rubric + Messages",
+      "onEnter": [
+        {
+          "action": "provide_watch_link"
+        },
+        {
+          "action": "handoff_to_subskill",
+          "target": "create-rubric"
+        }
+      ],
+      "allowedTools": ["AskUserQuestion"],
+      "terminal": true
+    }
+  ]
+}