agentleFS
riccardovandrariccardovandra/forge-gtm/.claude/skills/campaign-strategy/SKILL.md

campaign-strategy

Skill4 starsChanged 8 months agoMITView on GitHub

Generate cold email sequences from product profiles and tier definitions. Supports standard (angle-based) and tier-based (situation messaging) modes.

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 6

    Distinctive

    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:

    Create high-converting cold email sequences.

    line 8
  2. Distinctive:

    After buyer tiering produces tier definitions

    line 13
  3. Distinctive:

    Use when you have a business document, case study, or offer description.

    line 20
  4. Distinctive:

    Use when you have a product profile + tier definitions from the outreach pipeline.

    line 30
  5. Distinctive:

    All sequences follow the same structure:

    line 39
  6. Distinctive:

    Check against BANNED.md before finalizing.

    line 65

“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “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

Campaign Strategy

Create high-converting cold email sequences.

When to Activate

  • User asks to "write emails", "create a sequence", "build a campaign"
  • After buyer tiering produces tier definitions
  • Part of the /outreach pipeline (Step 3)

Two Modes

Standard Mode

Use when you have a business document, case study, or offer description. Generate sequences based on messaging angles.

Angles:

  • Case study: Lead with a specific customer result
  • Pain/poke: Lead with a problem they're likely experiencing
  • Direct offer: Lead with what you do and why it matters
  • Trigger-based: Lead with a specific event or signal

Tier-Based Mode (PVP)

Use when you have a product profile + tier definitions from the outreach pipeline. Each tier gets its own sequence with different messaging.

Structure per tier:

  • Hook: Describe THEIR situation (not your offer)
  • Value: Something you deliver IN the email (not teased)
  • Bridge: A question that flows naturally from the value

Email Structure

All sequences follow the same structure:

Thread 1 (Days 0-3):
  Email 1.1 - Subject (3-4 words) + main message
  Email 1.2 - Empty subject (auto-threads) + follow-up

Thread 2 (Days 7-10):
  Email 2.1 - New subject (3-4 words) + different angle
  Email 2.2 - Empty subject (auto-threads) + soft referral

Process

Step 1: Load Context

Read:

  • Client's offer (workspace/clients/{client}/offer.md)
  • Product profile (if tier-based mode)
  • Tier definitions (if tier-based mode)
  • Output style rules (.claude/output-styles/outreach.md)

Step 2: Generate Sequences

See SEQUENCE-GENERATOR.md for generation rules.

Check against BANNED.md before finalizing.

Step 3: Review Checkpoint

STOP before sending. Present the sequences for human review:

Review checklist:

  • Under 75 words per email
  • Clear "why you, why now?" in email 1.1
  • Specific numbers (3.72x not "significant improvement")
  • No banned patterns
  • Soft CTAs (question format)
  • Two distinct threads with different angles

Approve or request changes?

Step 4: Output

Save to:

workspace/outreach/{date} - {client}/tier-{N}/campaign-sequence.md

Or for standard mode:

workspace/clients/{client}/campaigns/{campaign}/email-sequence.md

Related Skills

  • prospect-research - Step 1 of outreach pipeline
  • buyer-tiering - Step 2 of outreach pipeline
  • list-builder - Build lists to send sequences to

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.