Set Up the Outbound Email Skill

---
name: surface-campaign-pipeline
description: Set up or resume a campaign in Surface Vault with three scheduled tasks for prospecting, qualification or enrichment, and personalized draft outreach using Surface MCP. Use for building this pipeline, including its file contracts, provider grants, schedules, and bounded commissioning runs.
---

# Surface campaign pipeline

Create a campaign operated through committed Vault records by **Prospect → Qualify → Draft Outreach**. Use Surface MCP for all campaign, Vault, connection-catalog, and task operations. Public web research may inform seller/ICP facts when permitted. Do not fall back to SQL, app REST, browser automation, credential files, or direct provider tools to complete setup.

Use the providers the user's Surface environment actually exposes. Clay, Apollo, MarqRadar, and Amplemarket are examples, not dependencies. Missing capabilities produce explicit blockers or Vault-only output, never invented tools or a false claim of a working pipeline.

## Scope and intake

1. Establish seller, target segment, intended team/environment, provider preferences, and whether the user wants setup only, real commissioning runs, or recurring operation. Reuse supplied answers. Inspect available Surface tools and returned environment identifiers; a production app hostname does not establish whether the workspace is a test environment. Ask only when scope is ambiguous.
2. List scheduled-task connections, browse campaign files, and list existing tasks. Follow pagination. Resume matching campaigns with saved IDs; a failed run does not justify another folder/task.
3. Check workspace Company files describe the actual seller before borrowing claims or exclusions. Otherwise keep sourced seller context inside this campaign. Record URLs and uncertainty. Never invent customers, proof, contacts, or evidence.
4. Present defaults briefly and proceed when sane defaults were authorized. Ask only for material missing facts, especially seller/segment, intended environment, or sender mailbox. Obtain sender first name from the user or a verified profile, not a guess from an address. Do not impose per-file approval checkpoints.

Suggested starting values; adapt to user intent, provider latency, and current tool limits:

| Setting | Starting value |
| --- | --- |
| Cadence | Hourly: Prospect :00, Qualify :20, Draft Outreach :40 |
| Timezone | User's stated timezone; otherwise environment timezone, explicitly disclosed |
| Prospect batch | Up to 5 new accounts, 2 contacts/account, 10 contacts/run |
| Qualify batch | Up to 3 accounts/run, including resumed work |
| Outreach batch | Up to 3 contacts/run; fewer for expensive sequence creation |
| Initial ceiling | 30 accounts for commissioning; larger only if requested |
| Task budget | 15 minutes, 20 documents, 60,000 output tokens |
| Soft stop | Stop new work by 8 minutes, 12 provider calls, or about 35,000 output tokens |
| Provider call ceiling | 15 per run, including reads, writes, polls, and verification |
| Outreach | Email only; four steps on business days 0, 3, 7, 11 |
| Publication | Inactive drafts only; no launch, resume, activation, or sending |
| Notifications | Vault summaries; Slack only when separately requested with a resolved destination |

These are ceilings, not quotas. Do not widen the ICP to fill them. The account ceiling limits **new accounts**, not bounded contact repair for existing accounts. Do not promise 100 contacts/hour; scale only after measured runs reliably commit within budget.

## Build the campaign contract

Read [references/vault-contract.md](references/vault-contract.md) when creating/adapting files. Build seller context, ICP, exclusions, complete sequence copy, persistence templates, and initial checkpoints before task creation. Seed empty data tables, not fake prospects.

Choose an outreach representation before marking setup ready:

- Prefer reusable persona sequences with **documented per-contact fields** for every variable part of every email, and a way to verify each recipient's rendered content.
- If unsupported, use a dedicated draft per contact when the provider supports it and this fits the user's scope. Name it deterministically with campaign, copy version, persona, and stable contact ID. Build across bounded runs if needed.
- Otherwise choose `vault_only`: save personalized copy and disclose that automatic provider enrollment is unavailable. Do not call this a fully commissioned external-outreach pipeline.

Never put one recipient's literal company/evidence into a shared sequence and reuse it for other companies. Preserve existing occupied drafts, reconcile them, and choose a compatible strategy for future contacts.

Use `ready_for_draft_pipeline` only when the core contract is coherent. Track readiness by stage: a missing sender/outreach connector must not block account discovery or research. Missing qualification capability blocks Qualify and downstream eligibility, not setup files. Draft-copy approval is not live-send authorization.

## Create three tasks

Read [references/task-instructions.md](references/task-instructions.md). Materialize its shared rules **plus the relevant stage block** into each task's saved instructions, resolving placeholders to actual paths, IDs, settings, and choices. Runtime tasks cannot read this local skill. Put schemas/copy in Vault and critical execution/recovery rules directly in task instructions.

Name tasks `{Short campaign name} · Prospect`, `{Short campaign name} · Qualify`, and `{Short campaign name} · Draft Outreach`. Save returned task IDs/URLs in `setup-log.md`.

Grant only each stage's provider(s) and Vault reads/writes. POST-based research/enrichment may need a write grant; constrain permitted operations in instructions. A broad connector write grant does not authorize live outreach. Grant optional web reads only where needed; no Slack by default. Inspect current Surface schemas rather than assuming config fields or provider capabilities.

Create tasks paused and verify returned state. For existing tasks, use `get_scheduled_task` and current `updatedAt` for updates. Omitted fields preserve configuration; supplied permission arrays replace arrays. Re-read and merge after conflicts. Wait if an active run prevents editing. Preserve another actor's acceptance/scheduling choices unless changing them is requested.

Offsets reduce overlap but do not enforce dependencies. Consume committed eligible rows and own separate files; never assume the prior stage succeeded because its scheduled time passed.

## Verify and commission within authorized scope

Setup verification is read-only: read back files and all task configurations, grants, exact paths, stage gates, copy strategy, and timezone. Check all referenced fields exist, copy is complete, days increase, exclusions exist, and unresolved settings are explicitly blocked. Report setup separately from runtime verification.

`run_scheduled_task` performs real external actions and may spend credits. A request to create this skill or set up tasks alone is not authorization to run them. Continue without re-asking when commissioning/recurring operation was already authorized. Otherwise leave the concrete setup paused and ask only for the missing execution authorization.

For authorized commissioning:

1. Run Prospect once; inspect status, all activity pages, write outcomes, and saved records.
2. Run Qualify against committed scan-ready accounts. Pending reports are normal: save exact IDs and resume with a fresh bounded polling allowance in a later authorized run. Never resubmit to make the first test look complete.
3. Run Draft Outreach when a qualified account has an eligible contact. Verify personalized content, sender, provider draft lifecycle, membership, and contacted/sent state when available. A lead status named `active` is not necessarily a live sequence; inspect sequence lifecycle and documented semantics.
4. Accept a completed run using `accept_scheduled_task_run` only after outputs pass review. Use `activate_scheduled_task` only when recurring execution is authorized and that stage passed commissioning. Surface schedule activation and provider campaign activation differ; only the former belongs here.

Read [references/recovery.md](references/recovery.md) on failures, uncertain writes, authentication, truncation, or count mismatches. Do not repeatedly run blocked tasks. If downstream has no eligible work, report the bottleneck rather than claiming full pipeline validation.

## Finish

Return campaign/task links supplied by tools, schedules/timezone, paused/armed state, provider/copy strategy, verified counts by stage, and remaining blockers. Say whether anything ran and whether contacts entered inactive drafts. No live campaigns or prospect messages are part of this skill.

Keep choices, IDs, verification, and unresolved recovery work in `setup-log.md`. Record new provider techniques in one campaign `surface-mcp-notes.md`, separating observed behavior from assumptions. Avoid raw credentials, personal contact dumps, and full execution logs in that notes file.

Installing manually? Keep all 5 files together. SKILL.md uses the reference files.