一键导入
quickstart
Guided first-use setup. Walk through filling context.md and ingesting the first sales call. Use when the repo is empty or context.md is unfilled.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Guided first-use setup. Walk through filling context.md and ingesting the first sales call. Use when the repo is empty or context.md is unfilled.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Dashboard of current GTM state across all active modules. Use when user asks about status, progress, or what to do next.
Upgrade this GTM Context OS instance to the latest template developments. Fetches the latest template, reconciles what's new against THIS instance's structure, and applies approved changes on a review branch — pausing before anything destructive. Operator-initiated.
Smoke test before merging dev to main. Bootstraps a clean worktree, runs evals, checks instruction consistency — all automated via sub-agents.
First thing to run. Checks repo state and recommends what to do next. Use when operator says 'what do I do', 'help me get started', 'where do I begin', or just seems lost.
Audit the health of THIS instance's lived-in state — structural completeness, evidence chains, index integrity, output hygiene, drift, and context.md consistency (conflicts + cached-vs-source drift). Reports findings and fixes safe drift; flags judgment calls. Runs inside Claude Code, no API key.
Process raw documents into structured, attributed knowledge. Drop docs into _intake/, run this skill to dissect them into the right places. Incremental — run as many times as needed.
| name | quickstart |
| description | Guided first-use setup. Walk through filling context.md and ingesting the first sales call. Use when the repo is empty or context.md is unfilled. |
Guided setup for first-time use of the GTM Context OS.
context.md is still template"This is your GTM Context OS — a system that builds intelligence about your market from sales conversations and uses it to drive targeting, messaging, and outbound campaigns.
Everything starts with understanding your business and your buyers. Let's fill that in."
Walk through each section conversationally — don't dump 20 questions at once:
First, the basics:
Then ICP:
Then positioning:
Then competitors:
Fill in context.md as answers come in. Confirm the completed version with the user.
"The system is built on understanding real buyer demand — not hypothetical pain points. The best source is sales call recordings.
Do you have recorded sales calls (from Gong, Fireflies, Zoom, or transcripts in any format)?"
If yes: "Paste a transcript or give me the file path. I'll run a PULL analysis and show you how the demand layer works."
Read demand/pull-framework.md and run a PULL analysis on the transcript. Save to demand/pull-analyses/ and update pull-index.json.
If no: "That's fine — the demand layer builds over time. For now, let's capture your current hypothesis about who has demand."
Ask:
Write this as demand/hypothesis.md:
# Demand Hypothesis
**Date:** YYYY-MM-DD
**Status:** Untested
## Primary Scenario
**Who:** [role + company type]
**Trigger:** [what pushes them to act]
**Project:** [what they're trying to accomplish]
**Alternatives tried:** [what they've looked at]
**Why alternatives fail:** [the gap]
## How to Test
Ingest 5+ sales call transcripts to validate or refine this hypothesis.
"Your Context OS is ready. Here's what you have:
context.md — Your ICP, positioning, and competitor landscapedemand/ — [Either first PULL analysis or hypothesis]status.md — Will track progress as you workNext steps:
/setup-api to connect your call recorder)/gtm-os-status anytime to see where things stand"Update status.md with a setup entry.