agentleFS
aiagentwithdhruvaiagentwithdhruv/skills/instantly-campaigns/SKILL.md

instantly-campaigns

Skill16 starsChanged 9 months agoMITView on GitHub

Create cold email campaigns in Instantly with A/B testing. Use when user asks to create email campaigns, set up cold outreach, build email sequences, or configure Instantly campaigns.

  • Reads credentials

3 other projects use a version of this, 3 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 1 is common, 0 are distinctive, and 1 is very specific to this project.

  • 1

    Common

    Most of the 3 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Common:

    Create three email campaigns in Instantly based on a client description and offers.

    line 9
  2. Very specific:

    Read .tmp/instantly_campaign_examples/campaigns.md for inspiration on personalization + social proof + offer structure.

    line 22

“Common” is measured: kept by at least 6 in 10 of the 3 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

Instantly Campaign Creation

Goal

Create three email campaigns in Instantly based on a client description and offers. Each campaign has A/B tested first emails and follow-up sequences.

Inputs

  1. Client Description: Company name, industry, target audience, value proposition
  2. Offers (optional): List of 3 offers. If not provided, will be generated.

Scripts

  • ./scripts/instantly_create_campaigns.py - Creates campaigns via Instantly API
  • ./scripts/read_sheet.py - Read lead data if needed

Process

1. Load Examples

Read .tmp/instantly_campaign_examples/campaigns.md for inspiration on personalization + social proof + offer structure.

2. Generate Campaigns

python3 ./scripts/instantly_create_campaigns.py \
  --client_name "ClientName" \
  --client_description "Description of the client..." \
  --offers "Offer 1|Offer 2|Offer 3" \
  --target_audience "Who we're emailing" \
  --social_proof "Credentials/results to mention"

3. Review Output

The script creates 3 campaigns (one per offer), each with:

  • Email 1: Two A/B variants
  • Email 2: Follow-up bump
  • Email 3: Breakup email

Campaign Structure

Email 1 (A/B Split Test)

  • Personalization hook ({{icebreaker}} or custom opener)
  • Social proof (credentials, results)
  • Offer (clear value proposition)
  • Soft CTA

Email 2 (Follow-up)

  • Brief, friendly bump
  • Reference original email
  • Restate value
  • Clear CTA

Email 3 (Breakup)

  • Short, direct
  • Last chance framing
  • Simple yes/no ask

Available Variables

  • {{firstName}} - Lead's first name
  • {{lastName}} - Lead's last name
  • {{companyName}} - Lead's company
  • {{casualCompanyName}} - Informal company name
  • {{icebreaker}} - AI-generated icebreaker
  • {{sendingAccountFirstName}} - Sender's first name

Edge Cases

  • No offers provided: Generate 3 distinct offers from client description
  • API errors: Script retries once, then fails with detailed error
  • Rate limits: Handled with exponential backoff

Output

{
  "status": "success",
  "campaigns_created": 3,
  "campaign_ids": ["id1", "id2", "id3"],
  "campaign_names": ["Campaign 1", "Campaign 2", "Campaign 3"]
}

Environment

Requires in .env:

INSTANTLY_API_KEY=your_key
ANTHROPIC_API_KEY=your_key

API Learnings

  • Schedule requires name field in each schedule object
  • Timezone: Use America/Chicago (not all IANA values work)
  • HTML: Instantly strips plain text outside HTML tags - wrap in <p> tags
  • Model: Uses claude-opus-4-5-20251101 for generation

Schema

Inputs

NameTypeRequiredDescription
client_namestringYesClient company name
client_descriptionstringYesCompany description and value proposition
offersstringNoPipe-separated offers (auto-generated if missing)
target_audiencestringYesWho we're emailing
social_proofstringYesCredentials/results to mention

Outputs

NameTypeDescription
campaign_idsarray3 Instantly campaign IDs
campaign_namesarrayCampaign names

Credentials

NameSource
INSTANTLY_API_KEY.env
ANTHROPIC_API_KEY.env

Composable With

Skills that chain well with this one: scrape-leads, gmaps-leads, casualize-names, onboarding-kickoff

Cost

Claude API + Instantly plan

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.