{"_id":"@ads-repo/project-intelligence-os","name":"@ads-repo/project-intelligence-os","dist-tags":{"latest":"0.1.0"},"versions":{"0.1.0":{"name":"@ads-repo/project-intelligence-os","version":"0.1.0","description":"A structured context brain for one advertising client. Scaffolds a folder any AI coding agent (Claude Code, Codex, Cursor, ChatGPT) opens already knowing the business — then onboards it with a single slash command.","keywords":["google-ads","meta-ads","ppc","ai-agent","claude-code","codex","cursor","agents-md","skill","template","adsrepo"],"homepage":"https://adsrepo.com","license":"SEE LICENSE IN LICENSE.md","author":{"name":"AdsRepo","email":"denis@adsrepo.com"},"type":"module","bin":{"project-intelligence-os":"bin/create.mjs"},"engines":{"node":">=18"},"publishConfig":{"access":"public"},"gitHead":"ef0b229a106e8921d09c2283f4010ce0a195a491","_id":"@ads-repo/project-intelligence-os@0.1.0","_nodeVersion":"25.9.0","_npmVersion":"11.12.1","dist":{"integrity":"sha512-TCAO31YjYVgDXWfWcRnF9Ck6MvA7CcERFbxRXjwmgerXfcRqCYorqXxOUXiLyms4yAodkfUz6nEWmGukjuNc+A==","shasum":"f49716ad8382a51dea8bab350b5d8af824228163","tarball":"https://registry.npmjs.org/@ads-repo/project-intelligence-os/-/project-intelligence-os-0.1.0.tgz","fileCount":35,"unpackedSize":100037,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEQCIG2nzoeOF+2xIjpD2Bs1JbqDoAuv5v2fYslZMPVfiCFGAiAS2oZ9WncWt8DTotzb1vLNYp2DAdMFPvyWPrd5W41pew=="}]},"_npmUser":{"name":"denis-adsrepo","email":"denis@adsrepo.com"},"directories":{},"maintainers":[{"name":"adsrepo","email":"tomas@adsrepo.com"},{"name":"denis-adsrepo","email":"denis@adsrepo.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/project-intelligence-os_0.1.0_1786612583288_0.5505805241563682"},"_hasShrinkwrap":false}},"time":{"created":"2026-08-13T09:16:23.127Z","0.1.0":"2026-08-13T09:16:23.454Z","modified":"2026-08-13T09:16:23.709Z"},"maintainers":[{"name":"adsrepo","email":"tomas@adsrepo.com"},{"name":"denis-adsrepo","email":"denis@adsrepo.com"}],"description":"A structured context brain for one advertising client. Scaffolds a folder any AI coding agent (Claude Code, Codex, Cursor, ChatGPT) opens already knowing the business — then onboards it with a single slash command.","homepage":"https://adsrepo.com","keywords":["google-ads","meta-ads","ppc","ai-agent","claude-code","codex","cursor","agents-md","skill","template","adsrepo"],"author":{"name":"AdsRepo","email":"denis@adsrepo.com"},"license":"SEE LICENSE IN LICENSE.md","readme":"# Client Intelligence OS\n\n> A structured \"brain\" for **one** advertising client/account. Open the folder in any LLM agent (Claude Code, Cursor, Codex, ChatGPT) and it starts every conversation with full account + business context — so the answers to *any* question are grounded.\n\n**This is the core of the whole system.** The more context the LLM has, the better it manages the ads. This template is used by **everyone**:\n- **In-house teams / solo managers** of one company → use this folder on its own.\n- **Agencies** → the **Agency Intelligence OS** wraps many of these (one per client) under `clients/`. Same OS, just structured for multiple accounts (see *Connection* below).\n\n## What this OS is (and isn't)\nThis OS is **just two things: the context structure + the onboarding.** Nothing else. Connectors, credentials, fetch scripts, and reporting tools live **separately** (the `Setup/` folder + their own explainers) so the template stays clean and standardized for any client.\n\n## How the context gets built: fetch first, then ask\nOnboarding (`_setup/onboarding.md`) **fetches the account reality first** via the connectors (Google Ads / Meta / GA — credential-based scripts that live separately in `Setup/connectors/`): campaign structure, spend, conversion actions, and recent spikes. **Then** it asks the human only what the data can't tell — how conversions are *really* tracked (margin vs revenue, primary action), what caused anomalies, and the business context. If the connectors aren't set up, it simply asks. Result: the richest, most standardized client context we can produce, the same way every time.\n\n---\n\n## What you get\n\nA 5-folder brain, deliberately simple:\n\n| Folder | What lives here | Changes |\n|---|---|---|\n| `00-context/` | One file per domain: business + **unit economics**, audience, **offer & messaging**, channels, **measurement & tracking**, competitors, creative, constraints, history, operations, tech-stack, **naming conventions**. | Rarely |\n| `01-goals-budget/` | North-star (`north-star.md`), **targets** (KPIs, guardrails, real-goal mapping — `targets.md`), budget (`budget.md`), 90-day **roadmap** (`roadmap.md`). | Monthly/quarterly |\n| `02-reporting/` | Self-contained reports (one folder each: data + script + HTML). | Often |\n| `03-notes/` | Raw captures (calls, threads). Distilled into `00-context/` via the update ritual. | Constantly |\n| `04-automations/` | Recurring scripts / scheduled tests (e.g. A/B tests from the AB-Test skill). | As needed |\n\nPlus three front-door files:\n- **`CLIENT.md`** — the 5-second identity card.\n- **`AGENTS.md`** — short router that tells any agent how to use the folder.\n- **`CLAUDE.md`** — one-line stub pointing at `AGENTS.md`.\n\n## Quick start\n\n1. Create the folder — either run\n\n   ```\n   npx @ads-repo/project-intelligence-os <your-company>\n   ```\n\n   or copy `template/` and rename it to your client (e.g. `acme/`). The `npx` route also wires the `onboard-client` skill into Claude Code, Codex and Cursor so it's a slash command from the first message.\n2. Open the folder in your LLM agent and say **\"Run the onboarding.\"** (No account setup needed. If you've connected your accounts via `Setup/`, it also imports conversion actions, campaigns + spend so you type less.)\n3. It picks a **scope** (paid-advertising by default, or broader CMO/all-channel), **fetches** what the accounts *and your website* already know, then runs a **Core interview** (~20-25 questions, many pre-filled). ~20-25 min → populated `CLIENT.md`, all `00-context/` files, goals, budget, roadmap.\n4. Go deeper any time with **\"deep-dive on `<domain>`\"**; after any working session say **\"Update context\"** — the one ritual to learn (documented in the client's `AGENTS.md` §3).\n\n## Tiered capture: Core now, Deep-dive later\nEvery file has a **Core (`[C]`)** layer filled at onboarding and a **Deep-dive (`[D]`)** layer marked `⬜ deep-dive pending` that fills over time — so the brain gets rich without a 90-minute setup.\n\n## The facts that make automations smarter\n- **`00-context/01-business.md`** — **unit economics** (margin, target CAC, profitability requirement) so decisions optimize profit, not just revenue.\n- **`00-context/05-measurement.md`** — every conversion action catalogued + the **tracking model** (revenue vs margin, primary action, attribution).\n- **`01-goals-budget/targets.md`** — the *real* goal per campaign / product line / funnel stage (not just the platform's optimization setting).\n- **`00-context/12-naming-conventions.md`** — the naming *schema* + a machine dictionary so the agent can decode any campaign name and point automations at the right place.\n\nThese turn the brain into something an LLM can act on without re-scanning the live account every time.\n\n---\n\n## Connection to the Agency Intelligence OS\n\nThe Agency OS keeps one client brain per client under `clients/<name>/`, all using **this exact schema** — it embeds a copy of this `template/` at `clients/_TEMPLATE`. The two ship as separate, self-contained downloads and are kept identical by a small sync script in the Agency OS (`sync-template.sh`), so the schema never drifts (see `Agency-Intelligence-OS/clients/README.md`).\n\n> Keep it **detailed but not complicated**. Five folders, one ritual, two smart context files. That's the whole system.\n\n---\n\nCopyright (c) 2026 Tomas Kliment & Denis Capko / adsrepo.com. All rights reserved. See LICENSE for terms — https://www.adsrepo.com/license\n","readmeFilename":"README.md","_rev":"1-ee6ec7a1f3fdf0f3fdd6c7cb881d2c81"}