agentleFS
prosyo-aiprosyo-ai/gtm-skill/skills/multichannel-cadence/SKILL.md

multichannel-cadence

Skill13 starsChanged 23 days agoMITView on GitHub

Use this skill when you need an outbound cadence that combines email, LinkedIn, phone and video so each touch builds on the last: \"build a multichannel sequence\", \"combine email and LinkedIn outreach\", \"plan a 3-week cadence for Tier 1 accounts\". Chooses channels by persona and tier, orders and spaces the touches, writes the connecting thread across channels, sets daily capacity and exit rules, and produces a day-by-day cadence ready to load into any sequencing tool.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this when one channel is not enough.

    line 16
  2. Distinctive:

    Every touch references the same problem from a new angle: the email names the problem, the LinkedIn message asks a question about it, the …

    line 44
  3. Distinctive:

    MUST stop all channels on a reply in any channel.

    line 61
  4. Distinctive:

    MUST keep each channel inside its safe daily limits.

    line 62
  5. Distinctive:

    MUST respect calling and texting consent rules for the region.

    line 63
  6. Distinctive:

    NEVER send the same message copy across channels.

    line 64

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Use this when one channel is not enough. Prospects who see you in two or three places in a short window remember you; the trick is making the touches feel like one conversation rather than an ambush.

Inputs

  • Persona and tier.
  • Channels available and the sender's capacity per day on each.
  • Offer, proof and the campaign's central problem.

The play

1. Choose channels by persona

PersonaLead channelSupport channels
Founders, small companiesLinkedInEmail
Sales and marketing leadersLinkedIn and emailVideo
Finance, operations, ITEmailPhone
Field and frontline managersPhoneEmail, text where lawful and consented
Enterprise executivesEmail via champion or referralLinkedIn, direct mail

2. Scale effort by tier

  • Tier 1: 10-14 touches over 3-4 weeks, 3-4 channels, 1:1 personalization.
  • Tier 2: 7-9 touches over 3 weeks, 2-3 channels, segment copy plus a personal line.
  • Tier 3: 4-6 touches over 2-3 weeks, 1-2 channels, segment copy.

3. Order the touches

Start where trust is cheapest: a LinkedIn profile view or connection request before the first email makes the email's sender name familiar. Calls work best right after an email ("I sent you a note on Tuesday about..."). Read references/cadence-templates.md for day-by-day templates per tier.

4. Thread the story

Every touch references the same problem from a new angle: the email names the problem, the LinkedIn message asks a question about it, the call follows up on the email, the video shows a 30-second example.

5. Plan capacity

Count touches per day per sender across all active prospects. A Tier 1 cadence for 50 new accounts a week can mean 80+ tasks a day; cut the number of new accounts before cutting quality.

6. Exit rules

Any reply on any channel stops every automated step on every channel. Bookings at the account stop all cadences at that account.

What good looks like

  • A prospect who replies says "I saw your note on LinkedIn too", not "why are you messaging me everywhere?".
  • Channel order makes each touch easier: connection, then email, then call referencing the email.
  • Task load per rep is realistic and finished daily.
  • The common mistake is running separate email and LinkedIn campaigns that each think they own the prospect, sending two unrelated first messages on the same day.

Rules

  • MUST stop all channels on a reply in any channel.
  • MUST keep each channel inside its safe daily limits.
  • MUST respect calling and texting consent rules for the region.
  • NEVER send the same message copy across channels.

Example prompts

  • "Build a 3-week multichannel cadence for Tier 1 CFO accounts: email, LinkedIn and phone."
  • "We have email and LinkedIn only. Design Tier 2 and Tier 3 cadences."
  • "How many new accounts a week can 2 SDRs handle on this cadence?"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.