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

instantly-autoreply

Skill16 starsChanged 9 months agoMITView on GitHub

Auto-generate intelligent replies to incoming Instantly email threads using knowledge bases. Use when user asks about email auto-replies, Instantly responses, or automated email handling.

  • Reads credentials

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

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Instantly Auto-Reply

Goal

Auto-generate intelligent replies to incoming emails from Instantly campaigns using campaign-specific knowledge bases.

Scripts

  • ./scripts/instantly_autoreply.py - Main auto-reply script

How It Works

  1. Receives incoming email thread from Instantly webhook
  2. Looks up campaign ID in knowledge base sheet
  3. Retrieves campaign context (offers, credentials, tone)
  4. Generates contextual reply using Claude
  5. Sends reply through Instantly API

Knowledge Base

Spreadsheet: 1QS7MYDm6RUTzzTWoMfX-0G9NzT5EoE2KiCE7iR1DBLM

Each row contains:

  • Campaign ID
  • Campaign Name
  • Knowledge Base (service details, offers, credentials)
  • Reply Examples (tone/style guidance)

Usage

# Process incoming thread
python3 ./scripts/instantly_autoreply.py --thread_id <id>

Environment

INSTANTLY_API_KEY=your_key
ANTHROPIC_API_KEY=your_key

Schema

Inputs

NameTypeRequiredDescription
thread_idstringYesInstantly thread ID to reply to

Outputs

NameTypeDescription
reply_sentbooleanWhether reply was sent successfully

Credentials

NameSource
INSTANTLY_API_KEY.env
ANTHROPIC_API_KEY.env

Composable With

Skills that chain well with this one: instantly-campaigns

Cost

Claude API per reply

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.