Most AI stacks get organized by tool. This one is organized by the job description you'd hand a new SDR: build the list, score it, personalize the opener, test the subject line, and fix the sequence when replies dry up. Seven skills, one job, free and open source in gtm-skills. Each one maps to something you'd otherwise pay a person to do, and each links straight to the skill file plus the matching Intempt agent that runs it at scale once you're past the manual stage.
Most AI stacks for outbound are organized by tool: a prompt for cold email, a prompt for subject lines, a prompt for list building, scattered across a doc nobody re-reads. You end up with a folder of clever prompts and no idea which one to open on a Tuesday morning.
An SDR doesn't show up with a folder of prompts. They show up with a job description: build the list, know who's worth calling, write the message, and fix it when it stops working. Seven jobs, over and over, every week.
TL;DR
- gtm-skills' SDR pack is 7 free skills covering the real SDR job: list building, ICP scoring, profile reading, cold email writing, subject line testing, Monday prioritization, and sequence auditing.
- Install once with npx skills add sidchaudhary/gtm-skills, then paste the skill you need into a Claude project.
- Each skill maps to a real, nameable part of the job - not a generic 'write me an email' prompt.
- Intempt's Outreach Rep agent is the always-on version of the same job description, wired into your actual pipeline data.
Why the job description is the right map
A tool-first stack asks "which prompt do I need." A job-first stack asks "what does an SDR actually do this week," then builds one skill per answer. That's the whole difference. It's also why these seven hold together instead of overlapping: the-list-builder feeds the-fit-scorer, which feeds the-cold-opener, which pairs with the-profile-reader and closes with the-subject-line-lab. Nothing here is guessing what a rep does. It's the job, broken into its real parts.
How to install these in about 60 seconds
- Run npx skills add sidchaudhary/gtm-skills, or clone the repo directly.
- Open Claude and create a project. Name it after the skill, for example "Cold Opener."
- Paste the skill's SKILL.md into the project instructions.
- Start a chat inside that project and give it your inputs.
Works in Claude chat, in a Claude Project, or in Claude Code. Nothing else to install.
The 7 skills
1. The List Builder
Builds and qualifies a prospect list from an ICP definition, sourced from data you provide or public web research, scored Hot/Warm/Cold/Skip with evidence and confidence per lead. Feeds directly into the-fit-scorer and the-cold-opener. Read the skill.
2. The Fit Scorer
Scores an account list against your ICP criteria and returns a priority tier - High, Medium, or Low - with a one-sentence rationale per account. Use it before an outbound campaign so the good hours go to the good accounts, not the whole list. Read the skill.
3. The Monday List
Takes a batch of weekly intent signals across your pipeline and returns a ranked outreach list with signal, rationale, and suggested channel per account. This is what you open first on a Monday instead of a stale spreadsheet. Read the skill.
4. The Profile Reader
Takes a prospect's LinkedIn profile text and returns three distinct personalization angles for a cold email opening line, each grounded in something specific the prospect actually wrote or did publicly. Not a generic '{{first_name}}, I noticed...' fill-in. Read the skill.
5. The Cold Opener
Takes prospect research, a specific trigger signal, and a product value prop, and writes a complete cold email body under 120 words, personalized to the signal. Pairs with the-profile-reader for the angle and the-subject-line-lab for the send. Read the skill.
6. The Subject Line Lab
Takes a cold email body and target persona and generates five scored subject line variants with a recommendation. Run this before sending any sequence at scale, not after the open rates come back disappointing. Read the skill.
7. The Sequence Doctor
Audits a cold outbound sequence and returns a gap analysis per email, rewrites for the three weakest emails, and a recommendation for any missing step. This is the one you reach for when reply rates drop and you need to know why, not just that they did. Read the skill.
The order to build them in
Don't install all seven on day one. Start with the-list-builder and the-fit-scorer - a stale, unscored list is the most common reason outbound underperforms, and fixing it changes every number downstream. Add the-profile-reader and the-cold-opener once you have a list worth writing to. The-subject-line-lab slots in right before you actually send. Keep the-monday-list and the-sequence-doctor as recurring checks, not one-time setup: the Monday list every week, the sequence audit whenever reply rates move.
What to never hand over
Three things stay with a human, permanently. The decision to actually contact someone - these skills draft the list and the message, you approve both. The moment that flips is the moment you become the outbound everyone complains about. Anything that reads as annoyed on the other end - a bad reply gets a human response, every time, not an automated one. And the final send button on anything that could be mistaken for spam at volume.
When you outgrow the manual version
These seven skills run one job at a time, on whatever you paste in. Intempt's Outreach Rep agent is the same job description wired into your actual pipeline: it builds and scores the list from your real CDP data, drafts and sends the sequence, and routes replies automatically, so you're not pasting the same inputs in every morning. Same seven jobs. The difference is whether a person is doing the pasting or the data already lives in the system.
Frequently asked questions. Answered.
Seven free Claude Skills that cover the actual SDR job: building a prospect list, scoring it against your ICP, reading a LinkedIn profile for a real personalization angle, writing the cold email, testing the subject line, prioritizing Monday's outreach by signal, and auditing a sequence that's stopped converting. Install with npx skills add sidchaudhary/gtm-skills, MIT licensed.
