Systems Lab

Agent skill

gtmos-leads-tech-stack

Read the tech stack of every account on a list and sort them into segments: uses a competitor (displace), uses a complement (expand), uses a disqualifier, or none detected.

activeReaches the webInstructions only819 words

Filed under Prospecting and list building.

From ay-automate/gtmos-skills · 107 skill entries · 0 · pushed 2026-11-02

What it does when it runs

Read the tech stack of every account on a list and sort them into segments: uses a competitor (displace), uses a complement (expand), uses a disqualifier, or none detected. With GTM OS connected it fills technographics through the governed enrichment waterfall (estimate first), reads tech_adoption and tech_churn signals, and drafts a definition.segment for the result. Use for \"which of these accounts use Intercom\", \"find Salesforce shops\", \"segment my list by tech stack\", \"technographic targeting\", \"who runs HubSpot\".

Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
  • api.looot.ai
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about gtmos-leads-tech-stack

Opens your assistant with this page's recorded context. Check the linked sources before relying on it.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/ay-automate/gtmos-skills.git /tmp/gtmos-skills
git -C /tmp/gtmos-skills sparse-checkout set "skills/gtmos-leads-tech-stack"
mkdir -p ~/.claude/skills/gtmos-leads-tech-stack
cp -R "/tmp/gtmos-skills/skills/gtmos-leads-tech-stack/." ~/.claude/skills/gtmos-leads-tech-stack/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

Or take the whole library

This repo ships a .claude-plugin manifest, so Claude Code can install all 107 skills at once. Plugin skills are invoked as /<plugin>:<skill>, so they never collide with your own.

/plugin marketplace add ay-automate/gtmos-skills
/plugin

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from ay-automate/gtmos-skills/blob/86780d2f545cdc0a1de971917aa04b41bb0b3ccd/skills/gtmos-leads-tech-stack/SKILL.md, which is licensed MIT (skill frontmatter). 819 words, 10 headings.

Tech-stack targeting

Part of GTM OS Skills. Adapted from gtm-tech-stack-targeting in loootai/gtm-skills (MIT, Copyright (c) 2026 looot). Changed for GTM OS: the operating section below (technographics through the enrichment waterfall with an estimate first, results kept on the account), rewritten cross-references. Notices: THIRD-PARTY-NOTICES.md (installed beside the skills as THIRD-PARTY-NOTICES.md).

With GTM OS connected

Rules (GTMOS-RULES.md). Read policy.get_dry_mode first; in dry mode every effect stops at a draft. E-class operations are proposed and a different person approves them; never approve your own proposal. Numbers come only from operation results, named with the operation. Claims about results, customers or metrics must be backed by active proof from proof.list.

Spend. Quote first (capability.quote, or estimate: true), show the user the total, and run only after a yes that covers exactly that run; pass the quoted amount as the run's cap. The operations marked spends inline below are never granted to GTM OS pack agents: a person runs them, or you quote and hand the run over.

1. Read what is known. records.get on each account (technographics already filled), enrichment.record_freshness {objectType: "gtm.account", id} Q for whether that value is stale, and signals.list Q for tech_adoption / tech_churn signals the daily scan recorded.

2. Fill the gaps, quoted. enrichment.enrich_accounts {ids, estimate: true} previews the technographics fill (it walks enrich.technographics through the governed broker, empty fields only). Show the expected cost, and on a yes run it with the same ids (spends inline). Stale values go through enrichment.refresh_stale {objectType: "gtm.account", fields, estimate: true} first, then a run with maxUsd set to the preview.

3. Segment. Apply the method below. "Not detected" is not "not used": back-end tools such as a CRM leave no trace on a website. Keep that column honest in every output.

4. Keep the segment. To reuse it in plays and routing, draft a definition.segment and propose it with config.propose_changeset M; a person signs it. Outreach to a segment goes through gtmos-outreach-cold-email.

Without GTM OS

Run the workflow below on looot directly: connect the looot MCP server (https://api.looot.ai/mcp) or use the looot skill in this repository. Searching and inspecting are free; runs are paid from the prepaid looot balance. Show the user the endpoint and its price, and run only after a yes.


The method below is looot's gtm-tech-stack-targeting workflow. Job ids are looot's; prices are the cheapest live provider in the public looot catalog on 2026-10-08 and the live price wins. With GTM OS connected, run the same steps through the operations above.

Selling a HubSpot add-on to Salesforce shops wastes the whole sequence. This skill reads the tech stack of every account on a list, tags each one by the technologies the user cares about, and returns segments: uses the competitor, uses a complement, uses neither.

Ask for these inputs

  • The accounts: a list of domains.
  • The technologies to look for, grouped as the user thinks of them: competitors (Intercom, Drift), complements (Segment), disqualifiers (Salesforce when the user only fits HubSpot shops).

Steps and prices

Prices are the cheapest live provider in the public looot catalog on 2026-10-08. inspect shows the live price.

#Job idInputPrice on 2026-10-08
1company.technographicsdomainfrom $0.01 per result (6 providers)
1 (fallback)company.tech-stackdomainfrom $0.065 per call
2 (optional)web.scrape.htmlurl of the homepage, to confirm a tag in the page sourcefrom $0.00044 per call

Expected total for 100 domains: about $1 with company.technographics.

Quote before you run

  1. Domains × $0.01 (or costPerSuccessUsd from search_catalog). Per-result pricing can bill more than one result per domain on some providers, so read the price formula in inspect and quote the upper bound.
  2. Tell the user the total and the balance; wait for a yes. More than 100 runs: an explicit yes.
  3. Cap each run with fallback.maxCostUsd (0.05). company.tech-stack costs more than that on its own, so it only runs when the user raises the cap.

Run it

run {"endpointId": "job:company.technographics", "input": {"domain": "acme.com"}, "idempotencyKey": "tech-<list>-acme.com", "fallback": {"maxAttempts": 3, "maxCostUsd": 0.05}}

Match technology names case-insensitively and by family (HubSpot CRM, HubSpot Marketing Hub and HubSpot all count as HubSpot). A technology missing from the result means "not detected", not "not used": back-end tools such as a CRM often leave no trace on the website. Say this in the output.

Output format

domain,segment,competitors_found,complements_found,disqualifiers_found,all_detected,provider
acme.com,displace,Intercom,Segment,,"Intercom;Segment;Google Analytics;Cloudflare",<provider>

Segments: displace (a competitor found), expand (complement found, no competitor), disqualified, unknown (nothing relevant detected). Then counts per segment and the total actualCost.

Cost and stop rules

  • One run per domain. Dedupe domains first (strip www. and paths).
  • Two failures in a row on different domains: stop and report.

When not to use this skill

  • One company's stack: looot-enrich-a-company or gtmos-research-account.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what gtmos-leads-tech-stack does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.

Build my GTM engine

Tell us what you want to improve. Fedor reviews the workflow and replies by email when there is a useful fit.

Fedor reviews every request personally. If there is a useful fit, he will reply by email.