Agent skills

The Reply.io Agent Skill — install one skill and your agent learns the core outreach workflows, executed through the reply CLI.

Status: Available (v1)

The Reply.io Agent Skill packages the core outreach workflows as one installable skill. It drives the CLI — the skill decides what to do, the CLI does it:

AI agent  →  Agent Skill (workflows, guardrails)  →  reply CLI  →  Reply.io v3 API

Install

npm i -g reply-cli
export REPLY_API_KEY=...
git clone https://github.com/replyio/reply-skill.git ~/.claude/skills/reply

Then ask your agent things like “import this CSV and skip duplicates”, “show me interested replies from this week”, or “which sequences are underperforming?”.

What’s in v1

Four workflows, each with dry-runs, verification steps, and hard confirmation gates (nothing sends, starts, or deletes without explicit approval):

Import prospects — CSV → mapping preview → dedupe → list → verify
Launch outreach — account & schedule checks → sequence → enrollment → confirmed start
Manage replies — inbox triage → thread context → approved reply → categorize
Analyze performance — reports + per-sequence stats → diagnosis → recommendations

The catalog below shows each outcome-level skill and its availability. Entries marked Coming soon depend on API endpoints that aren’t generally available yet (prospect search, enrichment) — they’ll join the same skill as workflows when the endpoints ship.

Find Prospects Coming soon

Turn an ICP description into a saved, deduplicated prospect list.

# Coming soon — will ship as a workflow in github.com/replyio/reply-skill

Inputs: ICP description in natural language (titles, industries, company size, geography) · Optional exclusion list (existing customers, competitors)
Outputs: A contact list populated with matching prospects · A summary of search filters used and match counts
Composes: Prospect Search API , Contact Data API

Build an ICP Coming soon

Derive an ideal customer profile from your best existing customers or a business description.

# Coming soon — will ship as a workflow in github.com/replyio/reply-skill

Inputs: A business/offer description, or a list of best-customer domains
Outputs: A structured ICP (titles, seniorities, departments, industries, sizes, locations) · Ready-to-run Prospect Search filters
Composes: Contact Data API , Analytics API , Prospect Search API

Enrich Contacts Coming soon

Fill missing emails, phones, and firmographics across a whole contact list.

# Coming soon — will ship as a workflow in github.com/replyio/reply-skill

Inputs: A contact list (or filter) identifying records to enrich
Outputs: Enriched contact records with validation status · A gap report of contacts that could not be enriched
Composes: Contact Enrichment API , Contact Data API , Email Validation API

Import Prospects

CSV in, deduplicated contacts out — mapped, verified, and organized into a list.

git clone https://github.com/replyio/reply-skill.git ~/.claude/skills/reply

Inputs: A CSV file (or pasted rows) of prospects · Dedupe preference (skip existing vs. update) and an optional target list
Outputs: Added / updated / skipped / failed counts with per-row failure reasons · A verified contact list ready for outreach
Composes: Contact Data API

Launch Outreach

Verify accounts, build the sequence, enroll contacts, and start — with a confirmation gate before anything sends.

git clone https://github.com/replyio/reply-skill.git ~/.claude/skills/reply

Inputs: Target contacts (a list, a fresh import, or explicit IDs/emails) · A sequence to reuse, or a name plus message drafts for a new one
Outputs: A running sequence with assigned mailboxes, schedule, and contacts · The sequence ID, enrollment counts, and skipped contacts with reasons
Composes: Sequence API , Templates & Schedules API , Mailbox Management API , Contact Data API

Handle Replies

Triage the inbox, surface interested prospects, and send approved replies.

git clone https://github.com/replyio/reply-skill.git ~/.claude/skills/reply

Inputs: Optional filters (category, sequence, unread, meeting intent)
Outputs: Sent replies (each explicitly approved) and categorized threads · A queue of threads still needing attention
Composes: Conversations & Inbox API

Book Meetings Coming soon

Convert interested replies into scheduled meetings via Reply's booking calendar.

# Coming soon — will ship as a workflow in github.com/replyio/reply-skill

Inputs: Threads with meeting intent (or a filter for them) · The booking calendar link and scheduling preferences
Outputs: Threads driven to a booked meeting, confirmed in-thread · Booked meetings visible in the meetings report
Composes: Conversations & Inbox API , Analytics API

Analyze Campaign Performance

Turn raw reporting data into decisions — what to scale, pause, or rewrite.

git clone https://github.com/replyio/reply-skill.git ~/.claude/skills/reply

Inputs: A time window and the sequences (or the whole account) to analyze
Outputs: A performance readout (delivered, opens, replies, interested, meetings) with diagnosis · One or two recommended actions — executed only on confirmation
Composes: Analytics API , Sequence API

Frequently asked questions

Do skills exist today?

Yes — one installable skill covering four workflows (import prospects, launch outreach, manage replies, analyze performance). Clone github.com/replyio/reply-skill into your agent's skills directory. Workflows that depend on unreleased API endpoints (prospect search, enrichment) remain coming soon.

What is a skill, concretely?

A folder of markdown instructions (SKILL.md plus workflow files) that an agent platform like Claude Code loads on demand. It encodes which CLI commands to run, in what order, what to verify, and where to stop for human confirmation. No runtime code — all execution goes through the reply CLI.

How is this different from MCP?

MCP gives an agent tools (individual operations). The skill gives it procedure — multi-step workflows with confirmation gates and verification. They compose - an agent can follow the skill's procedure using MCP tools or CLI commands.