Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

AI Marketing OS (Global) · minhnv0807 | DecimalAI

minhnv0807/34-ai-marketing-os-global

SkillScore55Maintained

Use when the user needs to design, audit, upgrade, or operate an AI Marketing OS for a marketing team: Brand Hub/source of truth, role-based AI agents/projects, skill chains, ChatGPT x Claude x NotebookLM workflows, MCP/connectors, Notion/Drive second brain, ads data loops, SOPs, weekly reviews, and handoffs. Trigger on 'AI marketing OS', 'marketing AI system', 'Brand Hub', 'AI workflow for marketers', 'AI team SOP', 'MCP marketing', 'marketing agent', or 'second brain marketing'.

marketingby minhnv0807

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Marketing & Content pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/minhnv0807-34-ai-marketing-os-global/SKILL.md

decimalai skills pull minhnv0807-34-ai-marketing-os-global --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/minhnv0807-34-ai-marketing-os-global/SKILL.md https://app.decimal.ai/s/minhnv0807-34-ai-marketing-os-global/SKILL.md

Raw file: /s/minhnv0807-34-ai-marketing-os-global/SKILL.md ↗ · machine-readable summary at /s/minhnv0807-34-ai-marketing-os-global.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 26d ago

Yes — +32% lift · at higher cost+53% tokens0% turns55% of whole cases pass with skill (12/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-14	✗→✓	▲ Improved	104%	0%
case-09	✗→✓	▲ Improved	96%	0%
case-12	✗→✓	▲ Improved	108%	0%
case-17	✗→✓	▲ Improved	43%	0%
case-18	✗→✓	▲ Improved	-13%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

minhnv0807 / ai-business-skills

skills/en/34-ai-marketing-os-global/SKILL.md

View on GitHub ↗

License MITImported 8/17/2026Version v1Bundled 1 file

Skill contents

references/

SKILL.md

AI Marketing OS (Global)

This skill designs the operating system for AI-assisted marketing: source of truth, roles, skill chains, data loops, review cadence, and handoffs. The goal is to help a team use AI as an operating system, not as scattered one-off prompts.

Information gathering

Read .agents/product-marketing-context-global.md if available. If the user has a plan, dashboard, SOP, Notion/Drive structure, ads report, or campaign brief, use it as input. Ask up to 4 questions: team structure, 90-day goal, current AI/tool stack, and biggest workflow pain. For detailed patterns, read references/ai-marketing-os-playbook.md.

When to use

Use this skill when the user needs to:

Build an AI Marketing OS for an SMB, agency, SaaS team, creator-led business, education business, service business, or B2B team.
Audit how the team uses AI: repeated prompts, lost context, disconnected chats, weak reporting, or no source of truth.
Design a Brand Hub, skill chain, role-based agent/project setup, MCP/connectors, and Notion/Drive second brain.
Create daily, weekly, and monthly SOPs for content, performance, campaigns, reporting, and handoffs.

Do not use this skill for a single artifact. Use the relevant older skill instead: 00-marketing-plan-global, 01-content-calendar-global, 02-campaign-brief-global, 05-ad-copy-global, 07-marketing-report-global, 10-reverse-kpi-global, or 31-offer-design-global.

Principles

Brand Hub is the source of truth. Scattered context creates inconsistent agent output.
Roles before tools. Define Strategy, Campaign, Content, Design, Performance, and Sales/RevOps before choosing tools.
Skill chains beat one-off prompts. Every workflow should define input, skill, output, and next skill.
Old data before new plans. New plans should read previous reports, dashboards, bottlenecks, and lessons.
Human approval at risk points. Budget, claims, legal/privacy, brand voice, and campaign launch need review.
Small cycles, steady review. Daily check, weekly decision review, monthly retro, quarterly refresh.

Workflow

1. Audit the current AI stack

Score maturity from 0-4:

| Level | Signal | |-------|--------| | 0 | Ad hoc AI use, no saved context | | 1 | Prompt templates, but manual copy/paste | | 2 | Context files and individual skills exist | | 3 | Brand Hub, role workspaces, and review cadence exist | | 4 | Connectors/data loops, dashboards, second brain, and governance exist |

If maturity is below 2, build foundation before adding automation.

2. Design the Brand Hub

Minimum Brand Hub:

Brand Guidelines: logo, color, typography, tone, voice, do/don't.
Customer Insight: persona, pain, trigger, objection, customer language.
Positioning & Offer: promise, proof, path, offer ladder.
Content Pillars: pillars, angles, source content, platform rules.
KPI Framework: revenue target, funnel KPI, benchmarks, decision rules.
Campaign Template: phases, budget split, asset list, approval flow.

When a file changes, update the relevant role workspaces.

3. Map role workspaces

| Role | Main work | Common repo skills | |------|-----------|--------------------| | Strategy | Market, offer, budget, KPI | 00, 08, 09, 10, 31 | | Campaign Lead | Brief, timeline, assets, handoff, retro | 02, 07, 20, 34 | | Content | Calendar, scripts, copy, UGC, email | 01, 04, 05, 06, 14 | | Design | Visual brief, brand system, landing page | 12, 30 | | Performance | Tracking, audit, reporting, data decisions | 03, 07, 13, 19, 21 | | Sales/RevOps | Lead quality, handoff, outreach | 18, 33 |

If the user uses Claude Projects, ChatGPT Projects/GPTs, NotebookLM, Notion, Drive, or MCP, map each tool to these roles. Keep the system vendor-neutral unless the user has already chosen a stack.

4. Build skill chains

Default workflow chains:

| Workflow | Suggested chain | |----------|-----------------| | Brand/client onboarding | product-marketing-context-global -> 09 -> 08 -> 31 -> 10 -> 34 | | Campaign launch | 02 -> 31 -> 10 -> 01/04/05/06 -> 12 -> 21 -> 07 | | Weekly performance | 13 -> 03/21 -> 07 -> 34 updates Brand Hub | | Content engine | 09 -> 01 -> 04/05/06 -> 15 -> 07 |

If previous-period data exists, read it before creating a new plan.

5. Set up data and second brain

Minimum stack:

Storage: Drive/SharePoint/Dropbox for files and assets.
Database: Notion/Coda/Sheets for resource table, campaign archive, case studies, and decision log.
Analytics: Meta Ads, TikTok Ads, Google Ads, GA4, CRM, email, UTM.
Connector layer: MCP or equivalent connectors for knowledge base, marketing analytics, design, email, and CRM.

Every important output needs owner, date, source, version, and next action.

6. Create operating cadence

| Cadence | Focus | Output | |---------|-------|--------| | Daily 15m | Spend, delivery, comments/inbox, tracking issues | Blocker list | | Weekly 30-60m | KPI vs target, winners/losers, bottleneck, next actions | Weekly decision log | | Monthly | Revenue, channel mix, offer, team load, Brand Hub changes | OS retro + roadmap | | Quarterly | Market, positioning, offer ladder, tool stack | Strategy refresh |

7. Governance and risk

Check:

Access: who can see customer data, ads data, CRM, and revenue.
Claims and proof: do not let AI invent proof or regulated claims.
Privacy: do not paste PII into unapproved tools.
Prompt injection: be careful with websites, comments, inbox exports, and external files.
Brand drift: compare new outputs against the Brand Hub.

Output template

markdown
# AI Marketing OS — [Business/team]

## 1. Current diagnosis
| Area | Level 0-4 | Evidence | Priority |

## 2. Brand Hub
| File | Status | Owner | Update cadence |

## 3. Role workspaces
| Role | Tool/workspace | Context loaded | Main output |

## 4. Skill chains
| Workflow | Skill chain | Required input | Output |

## 5. Data loop and connectors
| Data source | Tool/connector | Metric | Cadence |

## 6. Operating SOP
| Cadence | Owner | Checklist | Output location |

## 7. 30-60-90 day roadmap
| Phase | Work | Owner | Done when |

## 8. Risks and governance
| Risk | Mitigation | Approver |

Related skills

product-marketing-context-global: create the initial source context.
00-marketing-plan-global: create marketing plans inside the OS.
02-campaign-brief-global: convert strategy into campaign execution.
07-marketing-report-global: create the reporting layer for the data loop.
13-data-analysis-global and 21-ads-audit-global: analyze data and find bottlenecks.
31-offer-design-global, 32-seo-growth-global, 33-b2b-lead-gen-global: growth modules inside the OS.

Quality checklist

Has a clear Brand Hub, not scattered chat context.
Has role workspaces and skill chains, not just a tool list.
Uses previous data before creating new plans.
Defines daily/weekly/monthly cadence and output locations.
Includes owners, deadlines, and approval gates for campaigns, budget, and claims.
Covers privacy, access, prompt injection, and brand drift.

Illustrative Want to see what minhnv0807/34-ai-marketing-os-global would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

9/2/2026, 07:00 UTC · 22 cases

Lift

+32%

55% vs 23%

Agent turns

1.0 vs 1.0

Tokens

+53%

4,836.64 vs 3,159.14

fail → pass · 8pass → pass · 4fail → fail · 9pass → fail · 1

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-14 Our marketing team meets randomly whenever issues arise. We want a structured meeting schedule with clear durations and specific outputs for each session. How should we schedule these reviews?	fail→pass	14,589	19,884	+36%	1	1	0%	2,536	5,182	+104%	0	0	—
case-01 Our mid-sized B2B SaaS marketing team is struggling with fragmented AI usage—people use disconnected ChatGPT windows, lose customer context, and copy-paste prompts manually. Can you design a comprehensive AI marketing operating system for us? We want a complete architecture document structured into sections: an audit of our current AI maturity, setup for a centralized brand source of truth, workspace configurations across marketing roles, step-by-step skill chains for campaign and content workflows, a second-brain data loop with tools/connectors, daily to quarterly review SOPs, a phased rollout plan spanning the next 3 months, and risk governance guidelines.	fail→fail	49,318	48,833	-1%	1	1	0%	8,316	10,272	+24%	0	0	—
case-02 I run a digital marketing agency with 12 team members handling strategy, ad performance, content creation, and sales handoffs. We want to stop using isolated prompts and build an integrated AI-assisted marketing setup for our client accounts. Please lay out a full blueprint for our AI Marketing OS. Make sure the deliverable covers: a diagnostic matrix of our current AI adoption, mandatory brand hub components, role-based tool assignments, mapped workflow chains for client onboarding and performance reporting, integration points for our assets and analytics tools, recurring meeting cadences with concrete outputs, a 3-phase implementation roadmap, and risk management protocols for brand consistency and privacy.	fail→fail	51,559	40,019	-22%	1	1	0%	8,320	9,337	+12%	0	0	—
case-03 Our creator-led e-commerce business relies heavily on AI for ad copy, social calendars, and campaign briefs, but everything feels chaotic with constant brand voice drift and missed reporting context. Help us establish a formal AI marketing system. Please generate a complete OS blueprint that details: our operational maturity assessment, a core brand repository blueprint, setup maps for content and performance roles, linked multi-step prompt/skill sequences, second brain setup with data connectors, daily/weekly/monthly/quarterly meeting routines, a 30-60-90 day execution roadmap, and safety controls covering claims verification and data privacy.	fail→fail	48,185	40,099	-17%	1	1	0%	8,314	8,208	-1%	0	0	—
case-04 We need compelling ad text for our new SaaS feature launch tomorrow. Write 3 variations of Facebook ad copy targeting product managers.	fail→fail	18,286	13,389	-27%	1	1	0%	2,108	4,052	+92%	0	0	—
case-05 Here are our Meta ad numbers for last week: $5,000 spend, 120 conversions, $41.66 CPA, 2.1x ROAS. Please write a weekly ad performance summary report.	pass→pass	14,108	17,858	+27%	1	1	0%	1,809	4,214	+133%	0	0	—
case-06 We are planning a Black Friday campaign for our apparel store. Can you generate a campaign brief document outlining campaign goals and deliverables?	pass→fail	22,378	22,106	-1%	1	1	0%	2,882	5,795	+101%	0	0	—
case-07 Our marketing team currently copy-pastes custom prompts from a shared Google Doc without any central brand context or automated connectors. We want to jumps straight to building automated data pipelines and AI agents. Evaluate our current stage and tell us if we should proceed with automation immediately or build foundations first.	pass→pass	15,252	21,687	+42%	1	1	0%	2,443	4,820	+97%	0	0	—
case-08 We want to set up a central repository for our marketing team so our AI tools stop producing off-brand copy. Should we build separate prompt files for each writer, or establish a unified repository? What elements must it contain at minimum?	fail→fail	15,011	13,837	-8%	1	1	0%	2,396	4,201	+75%	0	0	—
case-09 We are assigning specific AI skills to our Strategy team members so they can handle market research, positioning, budget allocation, and target metrics. We plan to assign them ad copywriting skills. Is that the correct mapping, or which repository skills belong to Strategy?	fail→pass	12,922	11,169	-14%	1	1	0%	2,040	4,008	+96%	0	0	—
case-10 When onboarding a new client agency account, our team usually starts by generating ad copy immediately. What sequence of steps and skills should we execute from client context creation through initial system setup?	fail→fail	15,609	18,068	+16%	1	1	0%	2,680	5,148	+92%	0	0	—
case-11 What is the recommended multi-step workflow chain for launching a new marketing campaign, from initial strategy down to post-launch performance reporting?	fail→fail	16,724	15,485	-7%	1	1	0%	2,900	4,791	+65%	0	0	—
case-12 Every Monday morning we review ad performance data and want our system to automatically update our Brand Hub context based on past report findings. What skill sequence handles weekly data evaluation and knowledge base updates?	fail→pass	11,660	12,442	+7%	1	1	0%	1,990	4,145	+108%	0	0	—
case-13 We are designing our marketing team's second brain architecture. A consultant suggested using a single raw Google Drive folder for everything without databases or analytics tools. How should we properly structure the data and tool stack?	fail→fail	17,093	20,078	+17%	1	1	0%	2,802	5,406	+93%	0	0	—
case-15 What governance safeguards and risk controls must be built into an AI marketing operating system to prevent brand damage, legal issues, or data exposure?	pass→pass	21,228	26,167	+23%	1	1	0%	3,534	5,964	+69%	0	0	—
case-16 Our team is eager to draft next quarter's growth marketing plan. Should we start fresh with creative brainstorming, or is there a required pre-requisite step when setting up plans within the OS?	pass→pass	10,870	11,475	+6%	1	1	0%	1,698	3,757	+121%	0	0	—
case-17 When creating Section 1 (Current diagnosis) of the AI Marketing OS document, what exact tabular structure and column headers must be used?	fail→pass	10,347	3,869	-63%	1	1	0%	1,866	2,661	+43%	0	0	—
case-18 What table schema is required for Section 2 (Brand Hub) in the system blueprint output?	fail→pass	15,266	5,000	-67%	1	1	0%	3,420	2,982	-13%	0	0	—
case-19 How should Section 3 (Role workspaces) be structured in the generated architecture output?	fail→fail	13,816	9,357	-32%	1	1	0%	2,140	3,585	+68%	0	0	—
case-20 What table layout is required for documenting workflow chains in Section 4 (Skill chains) of the OS blueprint?	fail→pass	13,863	5,123	-63%	1	1	0%	1,918	2,964	+55%	0	0	—
case-21 What specific table schema must be used for Section 5 (Data loop and connectors) in the final deliverable?	fail→pass	11,902	2,792	-77%	1	1	0%	2,059	2,414	+17%	0	0	—
case-22 What exact table headers are required for Section 7 (30-60-90 day roadmap) when generating the AI Marketing OS blueprint?	fail→pass	7,414	2,603	-65%	1	1	0%	1,330	2,500	+88%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +32 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 22.7%
Pass rate with the skill: 54.6%
Cases attempted: 22
Cases counted toward lift: 22
Cases that regressed: 1
Skill version measured: v1
Run completed: 9/2/2026, 07:00 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-14

Prompt

Our marketing team meets randomly whenever issues arise. We want a structured meeting schedule with clear durations and specific outputs for each session. How should we schedule these reviews?

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run55

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+98% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 25 days ago

Other measured skills in the registry, with their headline benchmark lift.