tech-stack-signal-reader
/tech-stack-signal-reader
Detect which tools a company runs from its own website and turn the stack into a qualification and an angle. Use when someone wants to know what CRM or sequencer or analytics a company uses, wants to find companies on a competitor, or wants tech stack based targeting.
- Author
- mambalabsdev ↗
- Repository
- mamba-labs-skills ↗
- Licence
- MIT
- Last repository change
- 12.10.2026
Assessment and security
- Files in this package
- 9
- Scripts
- 1
- HTML comments
- 0
- URLs in SKILL.md
- 2
No signals detected. Repository changed on 12.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
- 1 scripts in this package. Review them before installing, as Claude may execute them.
Scripts: scripts/check-output.py
What it does and when to use it
Detect which tools a company runs from its own website and turn the stack into a qualification and an angle. Use when someone wants to know what CRM or sequencer or analytics a company uses, wants to find companies on a competitor, or wants tech stack based targeting.
Original author description
Detect which tools a company runs from its own website and turn the stack into a qualification and an angle. Use when someone wants to know what CRM or sequencer or analytics a company uses, wants to find companies on a competitor, or wants tech stack based targeting.
How it works
- What this does
- Requirements
- When to use it
- Inputs
- Shared context this skill reads
- Tool connection
- Method
- Approval stop
- Output
- Check the output before you return it
SKILL.md preview
---
name: tech-stack-signal-reader
description: |
Detect which tools a company runs from its own website and turn the stack into a qualification and an angle. Use when someone wants to know what CRM or sequencer or analytics a company uses, wants to find companies on a competitor, or wants tech stack based targeting.
license: MIT
compatibility: "Claude Code, Claude Desktop, Codex CLI, Cursor, Gemini CLI, and other agents that read SKILL.md. Live data steps need only what the Requirements section of the skill lists."
tags: [signal_based_selling, signal_research]
metadata:
title: "Tech Stack Signal Reader"
category: "signal-research"
tags: "signal_based_selling, signal_research"
keywords: "signals, what crm do they use, find companies using this tool, detect their tech stack, competitor displacement targeting, what analytics are they running"
version: "2.1.0"
requirements: "Needs an Apify token (usage billed to your Apify account); Node.js 18+."
---
# Tech Stack Signal Reader
## What this does
A detected tool is a fact; a useful signal is what the tool implies. This skill detects the stack from the live site, then reads it three ways: what it qualifies, what it disqualifies, and what it says about the company's maturity, which is usually the most useful of the three.
## Requirements
Check these before you run the skill. Nothing outside this table is needed.
| Requirement | Needed | Used for | What it costs you |
| --- | --- | --- | --- |
| Apify account and API token (`APIFY_TOKEN`) | Required | Runs the live data actors | A free Apify account works. Each run bills your own Apify account at the actor's Store price: gtm-tech-stack-signal-scraper 0.015 USD per company. |
| Node.js 18 or newer | Required | The MCP tool calls | Free. It starts the Mamba Labs MCP server with `npx`. |
**Missing a required item?** Stop before the live steps and tell the user which item is
missing and what it is for. Do not run the step without it and do not present an empty
result as an answer. Keys are read from the environment at run time and are never
written into a file, a prompt or the output.
## When to use it
- what CRM do they use
- find companies using this tool
- detect their tech stack
- competitor displacement targeting
- what analytics are they running
## Inputs
- **domain**: the company domain
- **technologies**: the tools you care about detecting
- **meaning**: what each detection implies for your offer
## Shared context this skill reads
Before doing anything else, read whichever of these exist at the project root and
use them instead of asking the user to repeat themselves:
- `ICP.md`
If none exist, do the work from what the user gives you, then offer to write the
missing file so the next skill in the pack starts warmer.
## Tool connection
Detection reads the live site and its additional pages rather than a historical index, which is the difference between a current stack and one from two years ago. Pass the tools you named as `technologies` to report only those (hubspot, salesforce, marketo, pardot, intercom, drift, apollo, outreach, gong, zoominfo); Clay, Salesloft, Instantly and Lemlist leave no trace on a website and cannot be detected.
This skill calls live data through the Mamba Labs MCP server, which runs the
actors on Apify with your own Apify token (https://console.apify.com/account/integrations).
- Installed as a plugin: the server is already wired, and the plugin asks for the token once.
- Installed by hand: copy `.mcp.json` from this folder into your project root and set
`APIFY_TOKEN` in your environment, or run:
```
claude mcp add mamba-gtm-suite -e APIFY_TOKEN=<your token> -- npx -y @mambalabsdev/mcp-gtm-suite@1.12.0
```
| Actor | MCP tool | Used for | Store page |
| --- | --- | --- | --- |
| GTM Tech Stack Signal Enrichment | `detect_gtm_tech_stack` | tool detection from the live site, with additional page crawling | https://apify.com/mambalabs/gtm-tech-stack-signal-scraper |
Runnable example input, matched to the live tool schema:
`detect_gtm_tech_stack`:
```json
{
"domain": "example.com",
"crawl_additional_pages": true
}
```
**Cost line.** Before any live call, state how many calls you plan and which actors
they bill. After the run, report the calls made, the calls that failed, and the Apify
usage where the tool reports it. Each actor bills the user's own Apify account at its
Store price.
**No token, no live data.** If no Apify token is available, say so and stop the live
steps. Never fill a live section from memory and present it as live.
## Method
1. Detect on the live site, and crawl beyond the homepage. Many tools only load on a pricing, signup or documentation page.
2. Split the results into qualifiers, disqualifiers and maturity markers before writing anything.
3. Treat a missing detection as unknown rather than as absence. A tool loaded behind a login will never be detected from outside.
4. Read the combination, not the items. A modern analytics stack next to a legacy CRM is a specific and actionable situation; either one alone is not.
5. Write the angle from the gap the combination implies, not from the tool name. Naming their CRM back to them proves you ran a scanner.
6. State detection confidence per tool, because a script tag is stronger evidence than a favicon.
7. Check the output with `scripts/check-output.py` before you return it.
## Approval stop
This skill does not send email or write to a CRM. If the user asks it to, stop first:
show what would be sent or written and wait for an explicit yes.
## Output
The detected stack with confidence per tool, the qualifier and disqualifier split, the maturity read, and one angle built from the combination.
## Check the output before you return it
Save the output to a file and run `python3 scripts/check-output.py <file>`. The
contract it checks is `scripts/output-contract.json`.
- Exit 0, `COMPLETE`: return the output.
- Exit 2, `INCOMPLETE`: do not present the output as finished. Fill what you can, run
the check again, and if parts stay missing, return the output under the heading
`Incomplete` with every reason the check printed.
## Quality bar
- A missing detection is reported as unknown, not as absence
- Pages beyond the homepage are crawled
- The angle comes from the combination rather than a single tool name
- Confidence is stated per detection
## Related skills
- `ai-adoption-signal-reader`
- `outbound-stack-fingerprint`
- `gtm-signal-aggregator`
Ships in the **signal-based-selling** pack.
Files in this package (9)
- .mcp.json 1 KB
- LICENSE 1 KB
- SKILL.md 6 KB
- evals/cases.json 1 KB
- listing/listing.json 3 KB
- listing/logo.png 12 KB
- listing/logo.svg 2 KB
- scripts/check-output.py 7 KB
- scripts/output-contract.json 1 KB
Versions
The database has no other skills named tech-stack-signal-reader.
Database snapshot: 13.11.2026 · package version 6e5cd8f4cfd8 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100ai-adoption-signal-reader
Detect whether a company has shipped AI features or adopted AI vendors, and read that as a budget and priority signal. Use when someone targets companies adopting AI, wants to know if a prospect is building AI features, or needs an AI readiness read on an account list. - 100tech-stack-signal-outreach
Use this skill when a company's technology choices are a buying signal for you: \"target companies using X\", \"they just added a tool we integrate with\", \"technographic outreach\", \"companies switching away from a competitor\". Reads technology signals (tools added, removed… - 100revops-tech-stack
Design, audit, and consolidate the RevOps technology stack — CRM, enrichment, sequencing, analytics, integration architecture, and cost optimization. Use when auditing GTM tools, designing revenue technology, or consolidating vendor spend. Triggers on: "RevOps stack", "sales… - 100tech-stack-detective
Reverse-engineer a company's tech stack from public signals — job listings, StackShare, GitHub, engineering blog, and their live website. Use this skill when a user asks "what tech does Stripe use", "what's Linear's stack", "what does Notion run on", "reverse engineer… - 100account-research
Know a company completely. Opens by asking your goal and where your context lives (CRM? call recorder? team chat? email?), then routes to 4 modes - account deep-dive & plan (external + your internal history with them), org chart (who runs it), tech stack & wedge, competitive… - 100company-context
Researches a company from its URL: firmographics, traction, funding, team, tech stack, hiring and decision-makers, with a 0-25 qualification score, ICP fit read and red flags. Use when asked for company research, a company profile, an account brief or a prospect qualification.