Eight workflows to copy into your agent

Every campaign in a single view: send volume, reply rates, bounce rates, LinkedIn activity, and sentiment. Export to Google Sheets or get a JSON table in chat.

Use the Outreach Magic skill. Pull a campaign performance scorecard for workspace "[WORKSPACE_SLUG]" over the last 14 days.

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

Use the campaign-stats preset or equivalent local data from my SQLite database. Show me a table with:

- Campaign name and activity status (active / paused / exhausted)
- Emails sent, delivered, bounced, and bounce rate
- Total replies, human replies (excluding auto-replies / OOO), and reply rate
- LinkedIn connects, accepts, messages, and replies
- Interested leads vs not interested with sentiment positivity rate
- Last activity date

If I ask you to, create a Google Sheet with this data and share it with me.

What's underneath: Campaign-stats preset: overview, funnels, and sentiment from events/campaigns/leads.

Break down reply rates by industry, job title seniority, or company size. Find which audience segments convert and which to pause.

Use the Outreach Magic skill. For workspace "[WORKSPACE_SLUG]", break down campaign reply performance by lead attributes over the last 30 days.

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

Join lead attributes (industry, job title, company headcount) to reply events and sentiment data from my local database. Show me:

1. Reply rate by industry (top 5, minimum 10 sends per segment)
2. Reply rate by job title seniority bucket (individual contributor, manager, director, VP, C-level, owner)
3. Reply rate by company headcount band (1-10, 11-50, 51-200, 201-1000, 1000+)
4. Segments with zero replies — flag these as potential kill candidates

End with recommendations based on the data. Use only local SQLite data.

What's underneath: Lead attributes joined to reply events with segment-level reply rates.

Ask the agent to prepare next Tuesday's client agenda. It pulls campaign performance, standout replies, and key events from one unified history. You walk into the call ready.

Use the Outreach Magic skill. Prepare next Tuesday's client agenda for [CLIENT NAME / workspace slug].

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

For that workspace, use query presets for the past 7 days (engagement, replies, interested) and include:
- Week-over-week sends, replies, reply rate, and bounce rate
- 3–5 standout replies with a short quote each
- Notable lead status changes and anything tagged urgent
- Deliverability flags (bounce spikes, risky domains)
- The 3 talking points I should lead with on the call

Format as a concise briefing I can paste into my agenda.

What's underneath: Engagement, replies, and interested presets scoped to a workspace.

One lead can live in multiple workspaces, each with its own lead status and events. The agent can update and report by workspace without overwriting global lead context.

Use the Outreach Magic skill. Compare lead status between workspace "[WORKSPACE_A]" and workspace "[WORKSPACE_B]" for the past 7 days.

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

Use workspace-scoped data (workspace summary, workspace lead events/status, not webhook volume totals from events alone). Show:
- Leads whose status changed in each workspace
- Same lead_id with different status in A vs B
- A table: lead identifier, status in A, status in B, last event date

End with which workspace view I should use for follow-up and why.

What's underneath: Workspace summary plus workspace-scoped status and events across two slugs.

Your agent can enrich, verify, and modify contacts directly in your root database so every downstream workflow uses fresh contact data.

Use the Outreach Magic skill. Before we launch campaign/workspace "[SLUG]", audit and fix contact data in the root database.

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

1. List leads missing email, title, company domain, or LinkedIn URL.
2. Check local SQLite before any paid enrich or email-find API calls.
3. Use lead-enrich / email-finder companion skills only for gaps still missing after the DB check.
4. Write verified fields back to root lead records and summarize what changed.

End with: ready or not ready to launch, and how many records still need manual review.

What's underneath: Local database check first, then companion skills only for gaps.

Slice reply rates by country, seniority, industry, company size - whatever the agent has data for. Find out which segments convert, kill the ones that don't, ask follow-up questions the way you'd ask an analyst.

Use the Outreach Magic skill. For campaign "[CAMPAIGN_NAME]" (last 90 days unless I say otherwise), analyze segment performance from my local database.

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

Join lead_attributes to replies/events. Break down reply rate by seniority and country. Output:
- A table: segment, sends, replies, reply rate
- Top 2 segments to double down on and bottom 2 to pause or kill, with one-line rationale
- Flag segments with fewer than 30 sends as low sample

What's underneath: Lead attributes joined to replies and events with sample-size warnings.

For any campaign, find the exact messages that earned replies. The agent groups them by theme and surfaces what is working. Feeds directly into the next sequence.

Use the Outreach Magic skill. Across all campaigns in the past 14 days, find copy that earned positive replies.

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

Use the replies query preset or equivalent local data. Group winning subject lines and opening hooks by theme. For each theme include: reply count, a ≤25-word example quote, and source campaign/workspace.

Finish with 3 specific ideas to test in my next sequence.

What's underneath: Reply rows grouped into themed subject and opening analysis.

Email and LinkedIn history merge into one timeline with auto-deduplication so your agent always uses matched profiles and complete context.

Use the Outreach Magic skill. Show everything we know about [LEAD NAME] at [COMPANY] from local SQLite.

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

Merge email touches, LinkedIn touches, enrichment attributes, tags, and workspace status into one chronological timeline (dedupe duplicate events). Quote the last real reply before drafting.

Then write a follow-up email that continues that thread, not generic outreach fluff.

If the lead is missing from the database, tell me exactly what to import or connect first.

What's underneath: Merged timeline, events, and attributes with thread-aware follow-up draft.

Before hitting send on a new campaign, audit the lead list: completeness scores, enrichment gaps, and duplicate detection in one pass.

Use the Outreach Magic skill. Audit campaign/workspace "[SLUG]" for launch readiness using local SQLite.

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

1. Count leads missing email, first name, or company domain
2. Check for duplicate leads by email across the campaign
3. Verify enrichment status: which fields are populated per lead
4. Flag leads that already exist in another workspace (cross-workspace collision)

End with a readiness score: green (launch ready), yellow (fix before launch with notes), or red (do not launch). List the top 3 blockers if not green.

What's underneath:

Quick morning briefing on what happened in the last 24 hours across campaigns. New replies, bounces, interested leads — without opening a sequencer tab.

Use the Outreach Magic skill. Pull a 24-hour digest across all active campaigns and workspaces from local SQLite.

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

Show:
- Total new replies, grouped by campaign (most replied-first)
- New interested / positive stage changes and which leads
- Bounce count and top 3 bounce domains
- Any leads that moved from cold to warm or booked a meeting (Calendly events)
- Sender health flags: bounce rate above 5% on any campaign

Format as a one-minute read. Bullets only, no fluff.

What's underneath:

Check bounce rates broken down by sending domain. Catch deliverability problems before they crater your sender reputation.

Use the Outreach Magic skill. Analyze bounce patterns from my local database for the past 30 days.

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

Group bounces by sending domain and campaign. Output:
- A table: domain, total sends, bounces, bounce rate, trend vs the prior 30 days
- Domains with bounce rate above 5% flagged in red
- The 3 most common bounce messages (SMTP codes) and what they mean
- Campaigns contributing the most bounces to each domain

Recommend which domains need DKIM/SPF review and which campaigns to pause.

What's underneath:

Teams running multiple workspaces see every client in a single view: sends, replies, reply rate, bounces, and stage changes. No tab switching.

Use the Outreach Magic skill. Show me an agency-wide performance snapshot across all workspaces for the past 7 days.

Use the installed Outreach Magic skill. Use built-in query presets when they fit. If numbers look stale, sync the database first. Do not invent metrics. Show query output or counts from my local database.

For each workspace, show:
- Total sends and replies
- Reply rate percentage and bounce rate
- Notable lead status changes (interested, meeting booked)
- Any workspace with zero replies flagged as at risk

Then rank workspaces by reply rate highest to lowest. End with a one-line action item for the bottom 2 workspaces.

Use local workspace-scoped data. Do not use invented metrics.

What's underneath: