1  ---
  2  name: cold-outbound-optimizer
  3  description: Design, analyze, and optimize cold outbound email campaigns for Instantly. Handles end-to-end ICP definition, expert panel scoring (recursive to 90+), sequence copywriting, infrastructure audit, capacity planning, and implementation docs. Use when asked to build cold outbound sequences, optimize cold email, analyze outbound campaigns, build sales sequences, build Instantly sequences, create cold outbound strategies, or design email campaigns. Supports both "start from scratch" and "optimize existing" modes.
  4  ---
  5  
  6  
  7  ## Preamble (runs on skill start)
  8  
  9  ```bash
 10  # Version check (silent if up to date)
 11  python3 telemetry/version_check.py 2>/dev/null || true
 12  
 13  # Telemetry opt-in (first run only, then remembers your choice)
 14  python3 telemetry/telemetry_init.py 2>/dev/null || true
 15  ```
 16  
 17  > **Privacy:** This skill logs usage locally to `~/.ai-marketing-skills/analytics/`. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. See `telemetry/README.md`.
 18  
 19  ---
 20  
 21  # Cold Outbound Optimizer
 22  
 23  ---
 24  
 25  ## Startup: Determine Mode
 26  
 27  Ask the user:
 28  1. Do you have an **existing Instantly account** with campaigns to audit, or are you **starting from scratch**?
 29  2. Do you have an **Instantly API key**? (Required for audit mode.)
 30  
 31  If API key provided → run `scripts/instantly-audit.py` to pull campaigns, account inventory, and warmup scores before proceeding.
 32  
 33  ---
 34  
 35  ## Phase 1: Discovery & Audit
 36  
 37  ### 1A — Infrastructure Check (if API key available)
 38  Run `python3 scripts/instantly-audit.py --api-key <KEY>` and report:
 39  - Active campaigns (name, status, reply rate, open rate)
 40  - Sending accounts (count, warmup score, daily limit)
 41  - Domain inventory
 42  - Warmup gaps: any account with score <80 or <14 days warmup → flag as NOT ready
 43  
 44  ### 1B — Performance Data
 45  - Pull campaign analytics from Instantly
 46  - Ask: "Do you have a spreadsheet with historical outbound data?" If yes, request link.
 47  
 48  ### 1C — ICP Definition
 49  If no ICP defined, collect:
 50  - **Titles:** Who are you targeting? (e.g., VP Marketing, Head of Growth)
 51  - **Industries:** Which verticals?
 52  - **Company size:** Employee count or revenue range?
 53  - **Revenue floor:** Minimum ARR/revenue to qualify?
 54  - **Anti-ICP:** Who to explicitly exclude?
 55  
 56  Use `references/icp-template.md` as the collection template.
 57  
 58  ### 1D — Business Context
 59  Collect:
 60  - What do you sell? (One sentence, no jargon)
 61  - What's the primary offer? (Free trial, audit, demo, consultation)
 62  - Real URLs to reference (pricing page, case studies, relevant content)
 63  - Any proof points? (Client results, stats, social proof)
 64  
 65  ### 1E — Expert Panel Config
 66  Default: 10 experts (see `references/expert-panel.md`).
 67  Ask: "Any industry-specific experts to add, or panelists to swap?" Confirm roster before scoring.
 68  
 69  ---
 70  
 71  ## Phase 2: Expert Panel Recursive Scoring
 72  
 73  **Target: 90/100. Non-negotiable. Iterate until reached.**
 74  
 75  ### Round Structure
 76  Each round produces:
 77  1. **Score table** — all 10 panelists, individual score (0-100), one-line rationale
 78  2. **Aggregate score** — average of all 10
 79  3. **Top weaknesses** — ranked list of what's holding the copy back
 80  4. **Changes made** — specific edits addressing each weakness
 81  5. **Updated copy** — full revised sequence after changes
 82  
 83  ### Scoring Criteria (per panelist's lens — see `references/expert-panel.md`)
 84  - Subject line curiosity / open rate potential
 85  - First sentence pattern interrupt
 86  - Body clarity and brevity
 87  - CTA softness and specificity
 88  - Sequence flow and follow-up logic
 89  - Deliverability risk signals (spam words, link density)
 90  - Personalization believability
 91  
 92  ### Rules
 93  - Scores must be brutally honest. No padding to 90 without earning it.
 94  - If round score < 90: identify top 3 weaknesses, revise copy, run next round.
 95  - If round score ≥ 90: finalize copy and proceed to deliverables.
 96  - Show every round in the final doc — the iteration trail is part of the value.
 97  
 98  ---
 99  
100  ## Phase 3: Deliverables
101  
102  ### Strategy Doc
103  Create a document (Google Doc, Notion, or markdown) with:
104  
105  1. **Pre-Analysis / Brutal Truth** — what the existing campaigns are doing wrong (or baseline if starting from scratch)
106  2. **ICP Summary** — confirmed targeting parameters
107  3. **Infrastructure Status** — account inventory, warmup readiness, capacity math
108  4. **Scoring Rounds** — full panel vote tables for every round
109  5. **Final Email Copy** — all steps for all campaigns, Instantly-ready format
110  6. **Implementation Plan** — step-by-step setup instructions
111  7. **Capacity Math** — accounts × daily send rate = pipeline projections
112  8. **Weekly Metrics Targets** — open rate, reply rate, positive reply rate, meetings booked
113  9. **STOP List** — what to kill immediately
114  10. **START List** — what to launch first
115  
116  ### Format Rules for Final Copy
117  Follow all rules in `references/instantly-rules.md` and `references/copy-rules.md`.
118  
119  ### Human Review Gate
120  **Do NOT push anything to Instantly automatically.** The doc is for human review. Get explicit approval before any API writes.
121  
122  ### Iteration
123  After review, collect feedback and re-run scoring on revised copy if needed.
124  
125  ---
126  
127  ## Capacity Math Formula
128  
129  ```
130  Accounts ready (score ≥80, ≥14 days warmup) × 30 emails/day = conservative daily volume
131  Accounts ready × 50 emails/day = aggressive daily volume
132  Daily volume × 22 working days = monthly send capacity
133  Monthly sends × expected reply rate = expected replies
134  Expected replies × qualification rate = pipeline opportunities
135  ```
136  
137  ---
138  
139  ## Weekly Metrics Targets (Baselines)
140  
141  | Metric | Good | Great |
142  |--------|------|-------|
143  | Open rate | 40%+ | 60%+ |
144  | Reply rate | 3%+ | 7%+ |
145  | Positive reply rate | 1%+ | 3%+ |
146  | Meeting rate | 0.5%+ | 1.5%+ |
147  
148  Adjust targets based on niche and offer. Cold traffic to a free audit converts differently than a paid trial.
149  
150  ---
151  
152  ## Add-On Recommendations (mention but don't build)
153  
154  - **LinkedIn automation:** HeyReach or similar for multi-channel sequences. Separate workflow.
155  - **Lead enrichment:** Clay or Apollo for personalization data before upload.
156  - **Lead pipeline:** Use `scripts/lead-pipeline.py` for Apollo → LeadMagic → Instantly automation.
157  
158  ---
159  
160  ## Reference Files
161  
162  | File | Purpose |
163  |------|---------|
164  | `references/instantly-rules.md` | Variable syntax, sequence structure, deliverability rules |
165  | `references/expert-panel.md` | Default 10-expert roster with scoring lenses |
166  | `references/copy-rules.md` | Email copy rules (first sentence, CTA, stats framing) |
167  | `references/icp-template.md` | ICP data collection template |
168  | `scripts/instantly-audit.py` | Pulls campaigns, accounts, warmup scores via Instantly v2 API |
169  | `scripts/lead-pipeline.py` | End-to-end lead sourcing pipeline |
170  | `scripts/competitive-monitor.py` | Competitor tracking and intelligence |
171  | `scripts/cross-signal-detector.py` | Multi-source signal detection |
172  | `scripts/cold-outbound-sender.py` | Send approved outbound emails |