sales-cadence
Designs multi-channel outbound cadences with timing, A/B testing, and content. Use when outbound sequences getting low reply rates, unsure how many touchpoints or what spacing to use, cadence emails sound generic, prospects ignoring calls, A/B tests not moving the needle, sequence performance plateauing, or not sure which channels to include in outreach. Do NOT use for general outreach message writing (use /sales-outreach), marketing cold email (use /cold-email), automated email flows (use /email-sequence), or general Salesloft platform help (use /sales-salesloft).
What this skill does
# Design a Multi-Channel Outbound Cadence
Help the user design a complete outbound cadence for Salesloft, Mailshake, Smartlead, Lemlist, Yesware, or Hunter.io — from architecture and timing through full content for every step, A/B testing, and optimization benchmarks.
## Step 1 — Gather context
If `references/learnings.md` exists, read it first for accumulated knowledge.
Ask the user:
1. **What's the campaign goal?**
- A) Cold outbound — net-new prospects, no prior relationship
- B) Inbound follow-up — responding to a lead that came in
- C) Trigger-based — responding to a signal (job change, funding round, tech install, intent data)
- D) Re-engagement — reviving a cold or stalled conversation
- E) Expansion — reaching new contacts at existing customer accounts
- F) Other — describe it
2. **Who is the target persona?** (title, seniority, industry, company size)
3. **What channels are available?**
- A) Email only
- B) Email + phone
- C) Email + phone + LinkedIn
- D) Email + phone + LinkedIn + video
- E) Other combination — describe
4. **What constraints should I know about?**
- Total duration (e.g., 14 days, 21 days, 30 days)
- Max touches per week
- Existing messaging or value props to incorporate
- Compliance requirements (GDPR, CAN-SPAM, industry-specific)
- Any channels to avoid or emphasize
**If the user's request already provides most of this context, skip directly to the relevant step.** Lead with your best-effort answer using reasonable assumptions (stated explicitly), then ask only the most critical 1-2 clarifying questions at the end — don't gate your response behind gathering complete context.
## Step 2 — Cadence architecture
Design the cadence structure as a table:
| Day | Step | Channel | Action | Notes |
|-----|------|---------|--------|-------|
| 1 | 1 | Email | Intro email (A/B subject lines) | Personalization Level 3+ |
| 1 | 2 | LinkedIn | Profile view + connection request | Same day as email |
| 3 | 3 | Phone | Call attempt #1 + voicemail | Reference email |
| 4 | 4 | Email | Follow-up email (value-add) | Different angle from Step 1 |
| ... | ... | ... | ... | ... |
### Design principles
- **Channel mixing**: Never send 3+ touches in the same channel consecutively. Alternate between email, phone, and LinkedIn.
- **Spacing**:
- Days 1-7: Higher intensity (touch every 1-2 days) — this is when engagement peaks
- Days 8-14: Medium intensity (every 2-3 days)
- Days 15+: Lower intensity (every 3-4 days) — don't burn the prospect
- **Touch count by persona** (typical ranges — adjust based on persona, sales cycle, and industry norms):
- C-suite / VP: 8-12 touches over 21-28 days (less aggressive, more spaced)
- Director / Manager: 12-16 touches over 21-30 days (standard)
- Individual contributor / practitioner: 10-14 touches over 14-21 days (shorter cycle)
- **Phone placement**: Always within 24 hours after an email so you can reference it ("I just sent you a note about...")
- **LinkedIn**: Use early for connection + later for social proof or content sharing. Don't be repetitive with email.
- **Final touch**: Always a "breakup" email — creates urgency without being pushy
## Step 3 — Write content for every step
For each step in the cadence, write the actual content:
### Email templates
For each email:
- **Subject line**: Provide A/B variants (Variant A and Variant B)
- **Body**: Full email text with personalization tokens in `{{brackets}}`
- **CTA**: Specific ask (meeting, reply, resource)
- Keep emails under 125 words for cold outbound, under 200 for warm follow-up
### Call scripts
For each call step:
- **Opening** (first 10 seconds — must earn the right to continue)
- **Reason for calling** (one sentence connecting to their world)
- **Key questions** (2-3 if they engage)
- **Ask** (meeting request with specific time)
- **Voicemail script** (under 30 seconds, always leave one)
### LinkedIn messages
- **Connection request note**: Under 300 characters, no selling
- **Follow-up InMail or message**: Reference a specific post, mutual connection, or insight about their company
- Keep LinkedIn casual and conversational — it's a social platform, not email
### Video guidance (if applicable)
- When to use: Steps 5+ when email hasn't gotten a response
- Duration: 60-90 seconds max
- Structure: Say their name, show you did research, one key insight, soft CTA
For platform-specific cadence implementation (Salesloft, Mailshake, Lemlist, Smartlead, Mixmax, Reply.io, Woodpecker, Hunter.io, Seamless.AI, Closum, Minelead, GetProspect, ZoomInfo, Snov.io, 6sense, Clay, BrandJet, AiSDR, Nooks, Orum, Amplemarket, Sendr, LeadIQ), see references/platforms.md.
### Personalization framework
- **Level 1 (Minimum)**: First name, company name, title — the bare minimum
- **Level 2 (Standard)**: Industry reference, company-size-specific pain point
- **Level 3 (Strong)**: Something specific about their company (recent news, tech stack, job posting, quarterly results)
- **Level 4 (Elite)**: Personal insight (their LinkedIn post, podcast appearance, conference talk, published article)
Recommend Level 3+ for all touches in a cold outbound cadence. Level 2 is acceptable for re-engagement at scale.
For Level 3+ at scale (100+ prospects), consider AI personalization: Smartlead SmartAgents, Clay, or custom GPT workflows to research each prospect and generate personalized snippets for {{custom_field}} merge variables. This automates the research step that makes Level 3-4 feasible at volume.
## Step 4 — A/B testing plan
Design an A/B testing strategy:
| Test # | What to test | Variant A | Variant B | Metric | Min sample size |
|--------|-------------|-----------|-----------|--------|-----------------|
| 1 | Subject line (Step 1) | Pain-focused | Curiosity-based | Open rate | 100 sends each |
| 2 | CTA style (Step 1) | Specific time ask | Open-ended question | Reply rate | 100 sends each |
| 3 | Email length (Step 4) | Short (75 words) | Medium (125 words) | Reply rate | 100 sends each |
### A/B testing rules
- Test one variable at a time
- Run each test for at least 100 sends per variant (200+ preferred) before drawing conclusions
- Primary metric: positive reply rate (not just open rate)
- Wait at least 5 business days before evaluating results
- Roll the winner into the cadence and start the next test
- Always be testing something — cadences decay over time as messaging gets stale
## Step 5 — Metrics and optimization
Provide a benchmarks table:
| Metric | Good | Great | If below "Good"... |
|--------|------|-------|---------------------|
| Open rate | 40-50% | 50%+ | Fix subject lines, check deliverability, verify email addresses |
| Reply rate (total) | 8-12% | 15%+ | Improve personalization, test different angles, check targeting |
| Positive reply rate | 3-5% | 7%+ | Revisit value prop, check ICP fit, strengthen the ask |
| Meeting booked rate | 2-4% | 5%+ | Improve CTA clarity, offer more flexibility, add social proof |
| Bounce rate | <3% | <1% | Clean your list, use email verification tools, check domain health |
| Unsubscribe rate | <1% | <0.5% | Reduce frequency, improve relevance, check compliance |
| Call connect rate | 5-10% | 12%+ | Try different times of day, use local presence dialing, vary call days |
### Optimization cadence
- **Week 1-2**: Let the cadence run, gather baseline data
- **Week 3-4**: Analyze first A/B test results, implement winners
- **Monthly**: Review full-funnel metrics, retire underperforming steps, test new angles
- **Quarterly**: Major refresh — new messaging, updated case studies, seasonal angles
## Before recommending a specific platform skill
This skill covers a strategy domain across many platforms. **Before pointing the user to any specific platform skill** (any `/sales-{platform}` listed in `## Related skills`, e.g., `/sales-mailshake`, `/sales-klaviyo`, `/sales-apollo`), read that platform skRelated in Image & Video
watch
IncludedWatch a video (URL or local path). Downloads with yt-dlp, extracts auto-scaled frames with ffmpeg, pulls the transcript from captions (or Whisper API fallback), and hands the result to Claude so it can answer questions about what's in the video.
physical-ai-defect-image-generation
IncludedUse when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
accelint-react-best-practices
IncludedReact performance optimization and best practices. ALWAYS use this skill when working with any React code - writing components, hooks, JSX; refactoring; optimizing re-renders, memoization, state management; reviewing for performance; fixing hydration mismatches; debugging infinite re-renders, stale closures, input focus loss, animations restarting; preventing remounting; implementing transitions, lazy initialization, effect dependencies. Even simple React tasks benefit from these patterns. Covers React 19+ (useEffectEvent, Activity, ref props). Triggers - useEffect, useState, useMemo, useCallback, memo, inline components, nested components, components inside components, re-render, performance, hydration, SSR, Next.js, useDeferredValue, combined hooks.
elevenlabs-agents
IncludedBuild conversational AI voice agents with ElevenLabs Platform using React, JavaScript, React Native, or Swift SDKs. Configure agents, tools (client/server/MCP), RAG knowledge bases, multi-voice, and Scribe real-time STT. Use when: building voice chat interfaces, implementing AI phone agents with Twilio, configuring agent workflows or tools, adding RAG knowledge bases, testing with CLI "agents as code", or troubleshooting deprecated @11labs packages, Android audio cutoff, CSP violations, dynamic variables, or WebRTC config. Keywords: ElevenLabs Agents, ElevenLabs voice agents, AI voice agents, conversational AI, @elevenlabs/react, @elevenlabs/client, @elevenlabs/react-native, @elevenlabs/elevenlabs-js, @elevenlabs/agents-cli, elevenlabs SDK, voice AI, TTS, text-to-speech, ASR, speech recognition, turn-taking model, WebRTC voice, WebSocket voice, ElevenLabs conversation, agent system prompt, agent tools, agent knowledge base, RAG voice agents, multi-voice agents, pronunciation dictionary, voice speed control, elevenlabs scribe, @11labs deprecated, Android audio cutoff, CSP violation elevenlabs, dynamic variables elevenlabs, case-sensitive tool names, webhook authentication
humanizer
IncludedHumanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.
generating-mermaid-diagrams
IncludedSalesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says "diagram", "visualize", "ERD", or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user wants PNG/SVG image output (use generating-visual-diagrams), or asks about non-Salesforce systems.