00-gtm-router
Plan and run the full API-first GTM chain - the orchestrator (step 00) that turns an ICP description plus optional budget, volume, and urgency into the right…
Reference module for the Headless GTM chain, not a skill to invoke. Holds the record contract every chain skill reads and writes (CONVENTIONS.md) plus the Python helpers they import (common.py, schema.py). Installed alongside the chain so those imports and references resolve;
$ npx -y skills add Zevenue/headless-gtm --skill headless-gtm-shared --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/headless-gtm-sharedContext preview
The summary Claude sees to decide when to auto-load this skill.
Reference module for the Headless GTM chain, not a skill to invoke. Holds the record contract every chain skill reads and writes (CONVENTIONS.md) plus the Python helpers they import (common.py, schema.py). Installed alongside the chain so those imports and references resolve;
name: headless-gtm-shared description: > Reference module for the Headless GTM chain, not a skill to invoke. Holds the record contract every chain skill reads and writes (CONVENTIONS.md) plus the Python helpers they import (common.py, schema.py). Installed alongside the chain so those imports and references resolve; read CONVENTIONS.md when you need the JSONL record shape, the runs/ layout, or the cost-gate rules.
This folder is a library, not a skill. Nothing invokes it directly. It ships as a skill folder for one reason: the `SKILL.md` marker is what makes skill installers copy a directory, and every chain skill depends on this one.
| File | What it is | Who uses it | |---|---|---| | `CONVENTIONS.md` | The chain contract: JSONL records, additive per-stage fields, the `runs/<run-id>/` layout, deviation logging | Every chain skill references it; read it before changing any output format | | `common.py` | `.env` loading, the >$10 cost gate, output-dir resolution, run slugs, run metadata | Imported by the chain scripts | | `schema.py` | `ProspectRecord` construction and the CSV/JSON writers | Imported by the discovery scripts | | `requirements.txt` | The full dependency list for the chain, mirrored at the repo root | `pip install` |
A script exited with `cannot find headless-gtm-shared/common.py`. The skill was copied out without this folder. Copy `skills/headless-gtm-shared/` next to the skill that failed, so the layout is:
<skills-dir>/ ├── headless-gtm-shared/ <- this folder ├── 02-apify-maps-discover/ └── ...
The `npx skills add` installer picks this folder up on its own. Only a manual single-folder copy can miss it.
export or a secrets manager always beats a `.env` on disk. The loader only fills in what is missing.
under the skill. An installed skill is a read-only package; client output belongs in the project you are working in.
GTM without the SaaS layer. An outbound pipeline built as agent skills for Claude Code and Codex: describe an ICP in plain English and the chain takes it from company discovery to verified, signal-ranked contacts - every step running on raw vendor APIs, not
Plan and run the full API-first GTM chain - the orchestrator (step 00) that turns an ICP description plus optional budget, volume, and urgency into the right…
The qualification gate of the GTM chain - judges every discovered company against the client's ICP before any paid enrichment, so credits are spent only on…
B2B company discovery and list building via the Prospeo search API. Use when the user wants to find companies from an ICP, build a prospect or TAM list, search…
Seed-based B2B company discovery via the Prospeo company-lookalike API. Use when the user has example companies and wants more like them - "find companies…
Find local-business (SMB) prospects via Google Maps using the Apify Compass actor. Use for Zevenue Step-2 Discovery (Vertical) when the ICP is Maps-addressable…
Scrapes a company website into clean, page-typed markdown using Firecrawl map + scrape + extract. Triggers on: "scrape this company", "read their website",…