@sellable/mcp 0.1.0

package/skills/research/SKILL.md

@@ -0,0 +1,258 @@
+---
+name: research
+description: Fast parallel research protocol for prospect + sender research.
+visibility: internal
+---
+
+# Research Protocol (Fast + Parallel)
+
+This is the shared research flow for **all** skills (craft-message, campaign-messages, enrich-prospects, create-campaign).
+The orchestrator remains the main model (e.g., Opus). Use host-aware parallel execution:
+
+- Claude host: `Task` subagents on Sonnet-4.5
+- Codex host: `multi_tool_use.parallel` for independent tool calls
+
+## Override Rules
+
+1. If the user provides specific research instructions, treat them as a hard override.
+2. Only use `mcp/sellable/skills/research/override.md` if it explicitly includes the marker `OVERRIDE: true`.
+   - If the file is missing or only contains the template text, ignore it.
+3. If `mcp/sellable/skills/research/config.json` exists, load it and override defaults below.
+
+## Inputs
+
+Provide as many as you have. Use `"Unknown"` for missing fields.
+Do not assume workers can read history; explicitly interpolate these inputs into each parallel work unit.
+
+- `name`
+- `title`
+- `companyName`
+- `companyLinkedinUrl` (optional)
+- `linkedinUrl`
+- `companyDomain`
+- `experienceSummary`
+- `headline` (sender only)
+- `positioningMode` (boolean)
+- `researchMode` (optional: "sender" | "prospect", default: "prospect")
+- `debugMode` (optional, default: true)
+- `progressMode` (optional, default: true)
+- `parallelMode` (optional, default: "wide")
+
+## Execution Backend Routing (Host Capability)
+
+Determine execution backend once per run:
+
+1. If `Task` tool is available, use `task-subagents` backend.
+2. Else if `multi_tool_use.parallel` is available, use `parallel-tools` backend.
+3. Else use `sequential-tools` backend.
+
+Backend rules:
+
+- `task-subagents`: use the Task templates below as written.
+- `parallel-tools`: map the same research units to direct tool calls and dispatch independent calls together with `multi_tool_use.parallel`.
+- `sequential-tools`: run the same units one by one while preserving output schema.
+
+Never claim Task subagents were launched when using tool-parallel or sequential execution.
+
+## Optional Config (config.json)
+
+If `mcp/sellable/skills/research/config.json` exists, read it before execution.
+Supported keys (defaults in parentheses):
+
+- `parallelMode` ("wide")
+- `agentCount` (6)
+- `maxToolCallsPerAgent` (2)
+- `progressMode` (true)
+- `debugMode` (true)
+
+If `agentCount` < 6, drop agents in this order (first dropped first):
+
+1. Reviews + Traffic
+2. Company LinkedIn Snapshot
+3. Jobs + Funding
+4. Role Context
+5. Homepage Snapshot
+6. Post Analyzer
+
+## Global Performance Rules
+
+- For `task-subagents`: spawn **all 6 Sonnet agents in a SINGLE message** for `researchMode="prospect"` using `Task` with `model: "sonnet"`, `subagent_type: "general-purpose"`, and **NO `run_in_background`** (regular Task calls in one message run concurrently; background mode causes notification spam).
+- For `researchMode="sender"`, delegate to the `research-sender` subskill (0-3 agents).
+- For `parallel-tools`: run the same 6 research units (prospect) by batching independent tool calls with `multi_tool_use.parallel`. For sender, delegate to `research-sender`.
+- For `sequential-tools`: run the same units sequentially.
+- **CRITICAL: Launch ALL agents in one message.** Do not launch agents sequentially or wait for one before starting the next. The whole point is parallel execution.
+- Tool budget: **max {maxToolCallsPerAgent} tool calls per agent** (default 2). If you hit the budget, stop and write `None found`.
+- Prefer MCP tools over WebSearch/WebFetch when possible.
+- Avoid duplicate WebFetch across agents (only the Homepage Snapshot agent should fetch the homepage).
+- If inputs are missing or a tool fails, return `Unknown` / `None found` (do NOT add more tool calls).
+
+## Mode Switching (sender vs prospect)
+
+- `researchMode="sender"`: Delegate to `research-sender` subskill (enrichment-first, 0-3 agents). Do NOT use prospect agent templates.
+- `researchMode="prospect"` (default): Use **Prospect Flow** (hooks + role context).
+
+### Progress UX (no-dead-air)
+
+If `progressMode=true`:
+
+1. Print a one-liner before launching:
+
+`Launching 6 research agents in parallel (posts, homepage, LinkedIn, role, growth, reviews)...`
+
+2. **In the SAME message**, dispatch all 6 Task calls (no `run_in_background`). Multiple Task calls in one message run concurrently — all 6 launch simultaneously and results return together.
+
+3. After all complete, print the synthesis.
+
+If `researchMode="sender"`, delegate to `research-sender` subskill (it handles its own progress UX).
+
+### Debugging Output
+
+Each subagent must include a final line:
+
+`DEBUG: tool_calls=[...]; skipped=[...]`
+
+If `debugMode=false`, omit the DEBUG line.
+
+## Prospect Flow (parallelMode="wide")
+
+**CRITICAL: Launch ALL 6 agents in a SINGLE message (no `run_in_background`).** Multiple Task calls in one message run concurrently. All results return together when the last agent finishes. Do NOT use `run_in_background: true` — it causes notification spam.
+
+```
+Single message with 6 Task calls (all run concurrently):
+├── Task Agent 1: Post Analyzer
+├── Task Agent 2: Homepage Snapshot
+├── Task Agent 3: Company LinkedIn
+├── Task Agent 4: Role Context
+├── Task Agent 5: Jobs + Funding
+└── Task Agent 6: Reviews + Traffic
+
+All 6 results return together → synthesize.
+```
+
+### Agent 1: Post Analyzer
+
+```json
+{
+  "subagent_type": "general-purpose",
+  "model": "sonnet",
+  "run_in_background": false,
+  "description": "Analyze posts for hooks",
+  "prompt": "Analyze LinkedIn posts for {name}.\\n\\nIf linkedinUrl is missing or 'Unknown', do NOT call tools and return (omit DEBUG line if debugMode=false):\\n---\\nTOP THEMES: None found\\nRECENT FOCUS: None found\\nBEST HOOKS: None found\\nENGAGEMENT: None found\\nDEBUG: tool_calls=[]; skipped=[linkedinUrl missing]\\n---\\n\\nOtherwise, call mcp__sellable__fetch_linkedin_posts with:\\n- linkedinUrl: \\\"{linkedinUrl}\\\"\\n- limit: 6\\n\\nThen return EXACTLY (omit DEBUG line if debugMode=false):\\n---\\nTOP THEMES: [3 topics they post about most]\\nRECENT FOCUS: [What's top of mind from last 3 posts]\\nBEST HOOKS: [2 short topics or 1 short quote + 1 topic]\\nENGAGEMENT: [What type of content gets most reactions]\\nDEBUG: tool_calls=[fetch_linkedin_posts]; skipped=[]\\n---\\n\\nKeep under 120 words. Use at most one quote (<=12 words)."
+}
+```
+
+### Agent 2: Homepage Snapshot
+
+```json
+{
+  "subagent_type": "general-purpose",
+  "model": "sonnet",
+  "run_in_background": false,
+  "description": "Homepage snapshot",
+  "prompt": "Capture homepage claims and CTA for {companyName}.\\n\\nIf companyDomain exists, call WebFetch on https://{companyDomain}. Otherwise, do NOT search.\\n\\nReturn EXACTLY (omit DEBUG line if debugMode=false):\\n---\\nWEBSITE: [Key homepage claims + CTA or 'None found']\\nPOSITIONING_HINTS: [Product/category/offer if obvious, else 'Unknown']\\nPROOF: [Logos, metrics, testimonials or 'Unknown']\\nDEBUG: tool_calls=[WebFetch]; skipped=[]  (if WebFetch called)\\nDEBUG: tool_calls=[]; skipped=[companyDomain missing]  (if not called)\\n---\\n\\nKeep under 90 words."
+}
+```
+
+### Agent 3: Company LinkedIn Snapshot
+
+```json
+{
+  "subagent_type": "general-purpose",
+  "model": "sonnet",
+  "run_in_background": false,
+  "description": "LinkedIn company snapshot",
+  "prompt": "Get LinkedIn company info for {companyName} ({companyDomain}).\\n\\nStep 1: Determine the company LinkedIn URL.\\n- If companyLinkedinUrl is provided and not 'Unknown', use it directly.\\n- Otherwise, do ONE WebSearch query: \\\"site:linkedin.com/company {companyDomain}\\\"\\n- Extract the linkedin.com/company/... URL from search results. If not found, return 'None found' for all fields.\\n\\nStep 2: Call mcp__sellable__fetch_company with the LinkedIn URL.\\n\\nReturn EXACTLY (omit DEBUG line if debugMode=false):\\n---\\nLINKEDIN: [Notable company page info or 'None found']\\nHEADCOUNT_HINTS: [Any size/growth signals or 'Unknown']\\nDEBUG: tool_calls=[WebSearch, fetch_company]; skipped=[]  (if both called)\\nDEBUG: tool_calls=[fetch_company]; skipped=[]  (if URL was provided)\\nDEBUG: tool_calls=[WebSearch]; skipped=[no LinkedIn URL found]  (if search found nothing)\\n---\\n\\nKeep under 90 words."
+}
+```
+
+### Agent 4: Role Context (no tools)
+
+```json
+{
+  "subagent_type": "general-purpose",
+  "model": "sonnet",
+  "run_in_background": false,
+  "description": "Analyze role context",
+  "prompt": "Analyze context for this person with NO tools.\\n\\nName: {name}\\nTitle: {title}\\nCompany: {companyName}\\nExperience: {experienceSummary}\\nHeadline: {headline}\\n\\nReturn EXACTLY (omit DEBUG line if debugMode=false):\\n---\\nROLE\\nPRIORITIES: [Likely TODOs this week]\\nPAIN POINTS: [Common challenges for this role]\\nDECISION POWER: [What they can buy/approve]\\nCONVERSATION STARTERS: [2-3 relevant topics]\\nDEBUG: tool_calls=[]; skipped=[no tools allowed]\\n---\\n\\nKeep under 110 words."
+}
+```
+
+### Agent 5: Jobs + Funding Signals (single search)
+
+```json
+{
+  "subagent_type": "general-purpose",
+  "model": "sonnet",
+  "run_in_background": false,
+  "description": "Jobs and funding signals",
+  "prompt": "Gather growth signals for {companyName} ({companyDomain}).\\n\\nDo ONE WebSearch query: \\\"{companyName} jobs careers hiring funding series press release\\\".\\n\\nReturn EXACTLY (omit DEBUG line if debugMode=false):\\n---\\nHIRING: [Notable job titles/teams or 'None found']\\nFUNDING: [Round, amount, date or 'None found']\\nPRESS: [Recent announcement or 'None found']\\nDEBUG: tool_calls=[WebSearch]; skipped=[]\\n---\\n\\nKeep under 100 words."
+}
+```
+
+### Agent 6: Reviews + Traffic (single search)
+
+```json
+{
+  "subagent_type": "general-purpose",
+  "model": "sonnet",
+  "run_in_background": false,
+  "description": "Reviews and traffic signals",
+  "prompt": "Find reviews/traffic for {companyName}.\\n\\nDo ONE WebSearch query: \\\"{companyName} G2 reviews Capterra TrustRadius Similarweb traffic\\\".\\n\\nReturn EXACTLY (omit DEBUG line if debugMode=false):\\n---\\nREVIEWS: [G2/other review signal or 'None found']\\nTRAFFIC: [Traffic estimate source or 'None found']\\nDEBUG: tool_calls=[WebSearch]; skipped=[]\\n---\\n\\nKeep under 80 words."
+}
+```
+
+## Sender Flow (parallelMode="wide")
+
+**Sender research uses the dedicated `research-sender` subskill.**
+
+When `researchMode="sender"`:
+
+1. Load via `get_subskill_prompt({ subskillName: "research-sender" })`
+2. Follow its instructions — it handles enrichment-first logic and conditional agent spawning
+3. Do NOT use the prospect agent templates below for sender research
+
+## Synthesize Results (Orchestrator)
+
+After all agents return, combine into a short Research Notes block. **Strip DEBUG lines before final output.**
+
+**If researchMode="sender":** Handled by `research-sender` subskill — do not synthesize here.
+
+**If researchMode="prospect":**
+
+If the caller passed cross-skill insights (from `.sellable/insights/cross-skill.md`), use them to prioritize hooks — e.g., if engage sessions show "AI compute time" angles get high engagement, rank those hooks higher.
+
+```markdown
+## {Name} - {Title} at {Company}
+
+**Top of Mind:** [From post analysis]
+**Company Context:** [From homepage + LinkedIn + reviews/traffic]
+**Pain Points:** [From role analysis]
+
+**Hooks to Use:**
+
+- [Specific post quote or topic]
+- [Recent company news angle]
+- [Role-specific conversation starter]
+- [Cross-skill insight angle, if relevant]
+
+**Growth Signals:**
+
+- [Hiring signal]
+- [Funding signal]
+- [Press signal]
+```
+
+If `positioningMode=true` and WEBSITE is not "None found":
+
+- For **prospect mode**, append the Positioning Notes block below.
+- For **sender mode**, populate the **Positioning Notes** line inside the sender summary using these fields.
+
+```markdown
+**Positioning Notes:**
+
+- OFFER: ...
+- TARGET: ...
+- PAINS: ...
+- PROOF: ...
+- DIFF: ...
+```

package/skills/research/config.json

@@ -0,0 +1,9 @@
+{
+  "parallelMode": "wide",
+  "agentCount": 6,
+  "maxToolCallsPerAgent": 2,
+  "senderMaxAgents": 2,
+  "senderMaxToolCallsPerAgent": 3,
+  "progressMode": true,
+  "debugMode": true
+}

package/skills/research/override.md

@@ -0,0 +1,13 @@
+# Research Override (Optional)
+
+OVERRIDE: false
+
+If you want to replace the default sonnet research protocol, put your custom
+instructions here. The `research` subskill will treat this file as authoritative.
+
+This file is intentionally empty by default. To activate, set `OVERRIDE: true`
+and replace the template with your own rules, prompts, and
+formats to override:
+
+- Prospect Research Pattern
+- Sender + Positioning Research Pattern

package/skills/research-prospect/SKILL.md

@@ -0,0 +1,99 @@
+---
+name: research-prospect
+description: Dedicated prospect research protocol for hooks, context, and personalization.
+visibility: internal
+---
+
+# Research Prospect (Dedicated)
+
+Use this subskill for lead/prospect research before message drafting.
+This protocol is standalone and does not depend on the generic `research` subskill.
+
+## Objective
+
+Produce high-signal prospect context for outreach:
+
+- What they care about (posts/themes)
+- Company context and momentum
+- Personalization hooks and conversation starters
+
+## Inputs
+
+Provide as many as available. Use `"Unknown"` when missing.
+
+- `name`
+- `title`
+- `companyName`
+- `companyDomain`
+- `companyLinkedinUrl` (optional)
+- `linkedinUrl` (optional)
+- `experienceSummary` (optional)
+
+## Execution Backend Routing
+
+Choose backend once:
+
+1. If `Task` is available: use Task subagents in parallel.
+2. Else if `multi_tool_use.parallel` is available: batch independent tool calls via `multi_tool_use.parallel`.
+3. Else: run units sequentially.
+
+Never claim Task subagents were used when they were not.
+
+## Evidence Retrieval Routing (Web)
+
+Use host-native web tools for external context:
+
+- Claude host: use `WebSearch` + `WebFetch`.
+- Codex host: use `web.search_query` + `web.open`.
+
+Hard rule:
+
+- Do NOT use shell scraping for research extraction (`curl`, `_next` bundle grep, JS chunk scanning).
+- If a page is JS-heavy and unreadable, pivot to alternate sources and explicitly mark what remained unavailable.
+
+## Research Units (6)
+
+Run these units with maximal safe parallelism for the selected backend.
+
+1. Post Analyzer
+
+- Use LinkedIn posts when `linkedinUrl` exists.
+- Extract top themes, recent focus, and best hooks.
+
+2. Homepage Snapshot
+
+- Fetch company homepage when domain exists.
+- Extract positioning/proof hints.
+
+3. Company LinkedIn Snapshot
+
+- Resolve company LinkedIn URL if needed, then call `fetch_company`.
+- Extract company context and headcount hints.
+
+4. Role Context (No Tools)
+
+- Infer likely priorities, pains, and decision context from role/title.
+
+5. Jobs + Funding Signals
+
+- Search hiring/funding/press momentum.
+
+6. Reviews + Traffic Signals
+
+- Search review and traffic indicators.
+
+## Output
+
+Return exactly this structure:
+
+```markdown
+## {Name} - {Title} at {Company}
+
+**Top of Mind:** [...]
+**Company Context:** [...]
+**Pain Points:** [...]
+**Hooks to Use:** [...]
+**Growth Signals:** [...]
+```
+
+If data is missing, use `None found` rather than guessing.

package/skills/research-sender/SKILL.md

@@ -0,0 +1,158 @@
+---
+name: research-sender
+description: Enrichment-first sender research protocol. 0-3 agents, 30s target.
+visibility: internal
+---
+
+# Research Sender (Enrichment-First)
+
+Use this subskill when creating campaigns and you need sender/company research.
+This protocol is standalone and does not depend on the generic `research` subskill.
+
+## Core Architecture
+
+`enrich_sender` compact mode already returns `companySnapshot`, `senderBackground`, and `proofDigest`.
+Four of the old five research agents duplicated this data. Only Growth Signals + Case Studies are net-new.
+When `companySnapshot.description` is missing/thin, we also run a tiny positioning snippet pass (1 WebSearch) so we don't end up with blank company context.
+
+**This protocol uses enrichment as the baseline and only spawns extra work when proof or positioning context is missing.**
+
+## Inputs
+
+Provide as many as available. Use `"Unknown"` for missing values.
+
+- `name`
+- `title`
+- `companyName`
+- `companyDomain`
+- `companyLinkedinUrl` (optional)
+- `linkedinUrl` (optional)
+- `headline` (optional)
+- `enrichSender` response (REQUIRED — must include `companySnapshot`, `senderBackground`, `proofDigest`)
+
+## Depth Decision (Deterministic — from proofDigest)
+
+Check the `proofDigest` from the `enrich_sender` compact response:
+
+### `minimal-verification` (0-1 agent, 0-1 web calls, ~2-10 seconds)
+
+**Condition:** `proofDigest.caseStudyCount > 0` AND `proofDigest.reviewHighlight` exists (not null)
+
+- Do NOT spawn proof/growth agents (Case Studies, Growth Signals).
+- If `companySnapshot.description` is missing/thin, spawn the **Company Positioning** agent (1 WebSearch, no WebFetch).
+- Synthesize directly from enrichment data (companySnapshot + senderBackground + proofDigest) plus Agent 3 if used.
+- Call `complete_sender_research()` immediately with enrichment counts.
+- ~0 additional tokens.
+
+### `deep-proof` (2-3 agents in parallel, max 5 tool calls total, ~30 seconds)
+
+**Condition:** `proofDigest.caseStudyCount === 0` OR `proofDigest.reviewHighlight` is null
+
+- Spawn exactly **2 agents in parallel** (Case Studies + Growth Signals).
+- If `companySnapshot.description` is missing/thin, also spawn **1 positioning agent** (Company Positioning) in parallel.
+- Homepage, Company LinkedIn, Reviews → all covered by enrichment, skip these entirely.
+- ~100k tokens total.
+
+## Positioning Context (Conditional — from companySnapshot.description)
+
+If `companySnapshot.description` is null/undefined or shorter than ~120 characters, run the **Company Positioning** agent (1 WebSearch, no WebFetch).
+
+## Execution Backend Routing
+
+Choose backend once:
+
+1. If `Task` is available: use Task subagents in parallel (Claude host).
+2. Else if `multi_tool_use.parallel` is available: batch independent tool calls (Codex host).
+3. Else: run units sequentially.
+
+Never claim Task subagents were used when they were not.
+
+## Agent Prompts (when needed)
+
+### Agent 1: Case Studies + Proof (max 3 tool calls)
+
+```json
+{
+  "subagent_type": "general-purpose",
+  "model": "haiku",
+  "description": "Case studies and proof",
+  "prompt": "Find 1-3 concrete proof items for {companyName} ({companyDomain}).\n\nUse only: WebSearch, WebFetch.\n\nTool budget:\n- 1 WebSearch\n- Up to 2 WebFetch (only if the page looks like a case study/testimonial with named customers or metrics)\n\nWebSearch query (run exactly once):\nsite:{companyDomain} (\"case study\" OR \"customer story\" OR testimonial OR results OR \"success story\") \"{companyName}\"\n\nWebFetch: pick up to 2 results that look most likely to contain named customers or metrics.\nIf a fetched page is JS-heavy/empty, skip it and use snippets.\nDo not do a second search.\n\nReturn EXACTLY:\n---\nPROOF_OPTIONS: [Up to 3 items. Each: customer + outcome/metric + timeframe if present; or 'None found']\nSOURCES: [Short source hints]\n---\nKeep under 120 words. No extra commentary."
+}
+```
+
+### Agent 2: Growth/Credibility Signals (max 1 tool call)
+
+```json
+{
+  "subagent_type": "general-purpose",
+  "model": "haiku",
+  "description": "Growth and credibility signals",
+  "prompt": "Find recent growth/credibility signals for {companyName} ({companyDomain}).\n\nUse only: WebSearch.\nTool budget: 1 WebSearch.\n\nWebSearch query (run exactly once):\n\"{companyName}\" {companyDomain} {currentYear} (funding OR raised OR seed OR series OR hiring OR \"we're hiring\" OR launch OR announcement OR \"press release\")\n\nReturn EXACTLY:\n---\nHIRING: [Notable signals or 'None found']\nFUNDING: [Round, amount, date or 'None found']\nPRESS: [Recent announcement or 'None found']\n---\nKeep under 90 words. No extra commentary."
+}
+```
+
+### Agent 3: Company Positioning (max 1 tool call)
+
+```json
+{
+  "subagent_type": "general-purpose",
+  "model": "haiku",
+  "description": "Company positioning context",
+  "prompt": "If the enrichment company description is missing/thin, pull a crisp positioning summary for {companyName} ({companyDomain}) using only search snippets.\n\nUse only: WebSearch.\nTool budget: 1 WebSearch.\n\nWebSearch query (run exactly once):\n\"{companyName}\" about product site:{companyDomain}\n\nReturn EXACTLY:\n---\nPOSITIONING: [1-2 sentences]\nICP: [1 short line, or 'Unknown']\nDIFFERENTIATORS: [Up to 3 short bullets, or 'Unknown']\nSOURCES: [Short source hints]\n---\nKeep under 90 words. No extra commentary."
+}
+```
+
+## Synthesis (Orchestrator — No Agents)
+
+After agents return (or immediately for minimal-verification), merge enrichment baseline + agent findings:
+
+```markdown
+## {Company} - Sender Research
+
+**Company Context:** [companySnapshot.description OR Agent 3 POSITIONING] + [companySnapshot.industry + employeeRange]
+**Positioning Notes:** [proofDigest.positioningOneLiner + keyDifferentiators + Agent 3 DIFFERENTIATORS (if present)]
+**Proof Options:** [proofDigest.caseStudySummary + agent upgrades if deep-proof]
+**Credibility Signals:** [proofDigest.reviewHighlight + agent growth signals if deep-proof]
+**Gaps:** [what's missing]
+```
+
+## Completion Marker (Required)
+
+After synthesis, call:
+
+`complete_sender_research({ depth, proofItemsFound, caseStudyItemsFound, credibilitySignalsFound, notes? })`
+
+Count rules:
+
+- `depth`: "minimal-verification" or "deep-proof"
+- `proofItemsFound`: number of concrete proof items you would confidently use.
+- `caseStudyItemsFound`: number of usable case-study examples.
+- `credibilitySignalsFound`: number of trust signals (reviews/ratings/funding/hiring/press).
+
+If no reliable evidence is found, set counts to 0 and include that in `notes`.
+
+## Progress UX
+
+If launching deep-proof agents:
+
+```
+Running a quick research pass for case studies and growth signals (~30s)...
+```
+
+If also launching the Company Positioning agent:
+
+```
+Running a quick research pass for case studies, growth signals, and positioning (~30s)...
+```
+
+If only launching the Company Positioning agent:
+
+```
+Pulling a quick positioning summary from search snippets (~10s)...
+```
+
+If skipping agents (minimal-verification):
+
+```
+Enrichment already has strong proof — synthesizing directly from baseline data.
+```

package/skills/workflow-sequences/SKILL.md

@@ -0,0 +1,85 @@
+---
+name: workflow-sequences
+description: Create workflow tables via Sellable MCP, attach outbound sequence templates, inspect existing tables, and handle overwrite or starter-column compatibility issues safely.
+visibility: public
+---
+
+# Workflow Sequences
+
+Use this when the user wants to create a workflow table for sequencing, attach or replace a sequence template, or inspect which tables already have sequences.
+
+This is the canonical MCP workflow for creating sequencer tables. Prefer this over manually creating workflow table columns or hand-writing sequence `runCondition` expressions.
+
+## Tools
+
+- `mcp__sellable__get_auth_status`
+- `mcp__sellable__list_senders`
+- `mcp__sellable__list_tables`
+- `mcp__sellable__create_workflow_table`
+- `mcp__sellable__attach_sequence`
+
+## Workflow
+
+1. Call `mcp__sellable__get_auth_status({})`.
+   - If auth is not OK, stop and show the returned guidance.
+2. Resolve a sender.
+   - If the user supplied a sender id, use it.
+   - Otherwise call `mcp__sellable__list_senders()` and use the only sender or ask the user to choose.
+3. Decide whether to create a new table or reuse an existing one.
+   - Prefer `create_workflow_table` for new sequence work.
+   - Use `list_tables` when the user wants to reuse or inspect existing tables.
+4. When creating a new table, pass `sequenceActions` that cover every action node you expect to attach later.
+   - This create path produces a lightweight `CampaignOffer + WorkflowTable` shell for durable user-facing workflow work.
+   - `campaignBrief`, rubrics, positioning, and client prospect linkage are optional unless the user asks for them.
+   - `DM` needs a `Message` column.
+   - `INMAIL_OPEN` and `INMAIL_CLOSED` need `Subject` and `Message`.
+   - `COMMENT` needs `Post URL` and `Comment`.
+   - `Reaction Type` is optional for `COMMENT`.
+5. Do not reuse an incompatible table just because it exists.
+   - A table missing the required starter columns will now reject `attach_sequence` with `Table is missing required starter columns`.
+   - If the user wants a `COMMENT` sequence and the table was created for `INVITE` or `DM`, create a fresh table instead of forcing replacement.
+6. Call `mcp__sellable__attach_sequence({ tableId, template, confirmed? })`.
+   - Template must use `version: 2`.
+   - `entryNodeId` must match a node id in `nodes`.
+   - `nodes` must be non-empty.
+   - Express branching in the template only. Do not hand-author raw `runCondition` strings for sequence columns.
+7. Treat overwrite as explicit user intent.
+   - If `attach_sequence` returns `SEQUENCE_EXISTS`, explain that sequence columns already exist.
+   - Only retry with `confirmed: true` when the user wants to replace the existing sequence.
+
+## Business Rules
+
+- `DM` must be reachable only after an accepted invite path or an `If Connected` yes-path.
+- `INMAIL_OPEN` must be on the `If Open Profile` yes-path.
+- Unsupported table types return `Table type does not support sequences`.
+- Missing workspace context means the active workspace is not set correctly.
+
+## Run Conditions
+
+- The MCP caller should not write sequence column `runCondition` expressions manually.
+- The backend derives `runCondition` from the sequence template branches.
+- Canonical branch mappings are:
+  - `is_open_profile` yes/no -> `.is_open === true/false`
+  - `is_connected` yes/no -> `.is_connected === true/false`
+  - action `accepted`, `replied`, `timeout`, `no_reply` -> `.value === true/false`
+- If a user asks to edit raw conditions directly, explain that sequence logic should be expressed as branches in the template instead.
+
+## Good Defaults
+
+- Start with `create_workflow_table` for every new sequence workflow.
+- Treat new user-facing workflow tables as campaign-backed by default, not as bare standalone tables.
+- Pass `sequenceActions` that cover every action node you plan to attach.
+- Recommended first scenarios:
+  - `INVITE` only
+  - `INVITE -> accepted -> DM`
+  - `COMMENT` only
+  - `If Open Profile -> INMAIL_OPEN, else INVITE`
+
+## Output
+
+Return:
+
+- `tableId`
+- `campaignOfferId` when a new table is created
+- whether a sequence was attached or replaced
+- any blocker with the exact MCP or API guidance that should drive the next step