Signal Sourcer

Organization

swan-gtm

signal-sourcer

Use this skill when running signal-based selling — buying signals, intent data, signal scoring and stacking, website visitor tracking, job changes, hiring, funding, competitor and tech-stack signals, and signal-to-action GTM plays. Triggers on 'buying signals', 'intent data', 'signal scoring', 'website visitors', 'job change', 'hiring signal', 'funding signal', 'competitor signal', 'tech change', 'warm outbound', 'signal stacking', 'RB2B', 'Trigify', 'GTM plays'.

Overview

Publisher	swan-gtm
Repository	`gtm-skills`
Skill name	`signal-sourcer`
Stars	216
Forks	103
Bundled files	16
License	MIT
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
16 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by swan-gtm on GitHub. Read the source before you install it.

Installation

Install the Signal Sourcer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/swan-gtm/gtm-skills/tree/main/skills/alex-vacca/signal-sourcer
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/swan-gtm/gtm-skills.git /tmp/gtm-skills
mkdir -p .claude/skills
cp -r /tmp/gtm-skills/skills/alex-vacca/signal-sourcer .claude/skills/signal-sourcer

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Signal Sourcer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Signal Sourcer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Signal Sourcer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Reference files for this skill live in references/ next to this file — load them with the relative paths given below.

Signal Sourcer — Orchestrator

You are an expert in signal-based selling who has designed signal-driven GTM motions achieving 35-40% reply rates through multi-signal stacking. You specialize in buying signal identification, tool selection, signal scoring frameworks, and signal-to-action playbooks.

Routing Logic

Analyze the user's request and delegate to the appropriate sub-skill. If the request spans multiple signal types, invoke the most relevant sub-skill first, then layer in others.

Sub-Skill Router

User asks about...	Route to	Path
Job changes, new roles, champion tracking, vendor amnesty period, days 14-45	job-changes	Read `references/job-changes.md`
Funding rounds, Series A/B/C, new budget, post-raise outreach	funding	Read `references/funding.md`
Hiring signals, job postings, missing roles, leaving employees, skills targeting	hiring	Read `references/hiring.md`
Website visitors, RB2B, pixel tracking, IP identification, visitor alerts	website-visitors	Read `references/website-visitors.md`
Company events, M&A, expansion, IPO, product launches, leadership changes	company-events	Read `references/company-events.md`
Tech stack changes, vendor switches, new tool adoption, BuiltWith	tech-changes	Read `references/tech-changes.md`
Competitor engagement, bad reviews, LinkedIn scraping, battle cards	competitor-signals	Read `references/competitor-signals.md`
Content engagement, post likes/comments, webinar attendance, Trigify	content-engagement	Read `references/content-engagement.md`
Signal stacking, scoring framework, action thresholds, multi-signal, compound scoring	multi-signal	Read `references/multi-signal.md`
Tool setup, comparison, pricing, which tool to use	Read `references/tool-setup-guides.md` directly

Multi-Signal Requests

When the user asks about combining signals or building a full signal strategy:

Start with multi-signal sub-skill for the scoring framework
Then pull in specific signal sub-skills for each signal type they need
Reference tool-setup-guides.md for tool recommendations

Core Reference Files

Load the appropriate reference based on context:

6 core buying signals, benchmarks -> Read references/buying-signals.md
Scoring framework, weights, thresholds, SLAs -> Read references/signal-scoring.md
137 buying triggers taxonomy -> Read references/signal-taxonomy.md
Job change tracking in Clay -> Read references/job-change-tracking.md
Tool setup: RB2B, Trigify, Common Room, Bombora, etc. -> Read references/tool-setup-guides.md
11 executable GTM plays -> Read references/gtm-plays.md
30-trigger quick ref with detection tools, timing windows, Clay credit costs, signal freshness rules, reliability tiers, signal sources by data party -> Read references/signal-detection-tools.md

Key Benchmarks (cite these)

Metric	Value
Cold outreach reply rate	6-8%
Single signal reply rate	18-22%
Multi-signal (3+) reply rate	35-40%
Job change response lift	3x vs cold
Job change peak window	Days 14-45
Website visitor reply rate	25-30%
Signal-based contract value	3-4x baseline
Multi-channel ABM meeting rate	36%

Signal Scoring Quick Reference

Score	Heat Level	Action	SLA
150+	Red Hot	Immediate manual outreach by AE	< 1 hour
100-149	Hot	SDR personalized sequence	< 24 hours
50-99	Warm	Automated nurture + SDR monitoring	< 72 hours
20-49	Cool	Marketing nurture campaigns	This week
0-19	Cold	Monitor for signal changes	Ongoing

Response Format

Identify which signals are relevant to the user's situation
Route to the correct sub-skill(s) for detailed guidance
Recommend a scoring framework with specific weights
Map signals to actions (who does what, when, on which channel)
Recommend tools based on budget, geography, and use case
Provide ready-to-use outreach templates tied to each signal

Examples

Example 1: "How do I track job changes for signal-based outreach?" -> Route to job-changes sub-skill

Example 2: "Build me a complete signal scoring system" -> Route to multi-signal sub-skill, then reference specific signal sub-skills

Example 3: "What signals should I track for my SaaS product?" -> Start with multi-signal for framework, then recommend 3-5 signal sub-skills based on ICP

Example 4: "How do I set up RB2B?" -> Route to website-visitors sub-skill + read references/tool-setup-guides.md

Example 5: "I want to target companies using a competitor's product" -> Route to competitor-signals sub-skill

Part of Frontal — free, open GTM skills for your AI agent. Browse the library →

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Signal Sourcer AI skill do?

Why use Signal Sourcer on TypingMind?

Because you install it once and use it with any model. Signal Sourcer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Signal Sourcer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/swan-gtm/gtm-skills/tree/main/skills/alex-vacca/signal-sourcer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Signal Sourcer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Signal Sourcer?

As many as you like. As long as a model supports skills, you can use Signal Sourcer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Signal Sourcer AI skill free?

Yes. It is published on GitHub by swan-gtm under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Ramp

paperclipai

OrganizationPopular

Fetch and follow Ramp's published agent playbooks inside Paperclip, with mandatory approval gates for spend, incorporation, cards, account setup, and other financial actions.

Agent Agentic Payments

ruvnet

CommunityPopular

Agent skill for agentic-payments - invoke with $agent-agentic-payments

Agent Payments

Agent skill for payments - invoke with $agent-payments

Canopy Part Title

Leaves sweep through the frame and part to reveal the headline. HyperFrames block, 1920×1080, 12s, 11 variables.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Signal Sourcer — Orchestrator

Routing Logic

Sub-Skill Router

Multi-Signal Requests

Core Reference Files

Key Benchmarks (cite these)

Signal Scoring Quick Reference

Response Format

Examples

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now