Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Khi nguoi dung can thiet ke, audit, nang cap hoac van hanh AI Marketing OS cho team marketing: Brand Hub/source of truth, role-based AI agents/projects, skill chain, ChatGPT x Claude x NotebookLM workflow, MCP/connectors, Notion/Drive second brain, Meta Ads data loop, SOP, weekly review, handoff. Dung khi nhac 'AI marketing OS', 'he thong AI marketing', 'Brand Hub', 'Claude Project', 'AI workflow cho marketer', 'SOP AI team', 'MCP marketing', 'agent marketing', 'second brain marketing'.
.claude/skills/minhnv0807-34-ai-marketing-os/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-05 | ✗→✓ | ▲ Improved | 170% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 180% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 104% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 124% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 126% | 0% |
Skill nay thiet ke he dieu hanh marketing co AI: nguon su that, vai tro, skill chain, data loop, review cadence, va handoff. Muc tieu la giup team dung AI nhu mot he thong van hanh, khong phai tap hop prompt roi rac.
Doc .agents/product-marketing-context.md neu co. Neu co file plan, dashboard, SOP, Notion/Drive structure, Ads report, campaign brief, hay lay lam dau vao. Neu thieu thong tin, hoi toi da 4 cau: team hien co, muc tieu 90 ngay, stack dang dung, va diem dau lon nhat. Neu can playbook chi tiet, doc references/ai-marketing-os-playbook.md.
Dung khi user can:
Khong dung skill nay neu user chi can mot output don le. Khi do dung skill cu tuong ung: 00-ke-hoach-mkt, 01-lich-noi-dung, 02-brief-chien-dich, 05-copy-quang-cao, 07-bao-cao-marketing, 10-tinh-kpi-nguoc, 31-offer-design.
Cham maturity tu 0-4:
| Muc | Dau hieu | |-----|----------| | 0 | Dung AI tuy hung, khong co context luu lai | | 1 | Co prompt mau nhung copy/paste thu cong | | 2 | Co context file va skill rieng le | | 3 | Co Brand Hub, role workspace, review cadence | | 4 | Co connector/data loop, dashboard, second brain, governance |
Neu maturity duoi 2, uu tien foundation truoc khi them automation.
Brand Hub toi thieu gom 6 file — moi file co skill tao ra no:
| File Brand Hub | Noi dung | Skill tao file | |----------------|----------|----------------| | Brand Guidelines | logo, mau, font, tone, visual do/don't | 46-brand-guideline | | Brand Voice | personality, tone, vocabulary, banned words, before/after | 35-brand-voice | | Customer Insight | persona 3 tang, pain, trigger, objection, customer language | 09-insight-khach-hang | | Positioning & Offer | promise, proof, path, offer ladder | 58-positioning + 31-offer-design | | KPI Framework | revenue target, funnel KPI, benchmark, decision rules | 10-tinh-kpi-nguoc | | Campaign Template | phase, budget split, asset list, approval flow | 02-brief-chien-dich + 41-campaign-asset-list |
Quy tac vang: moi lan mot file Brand Hub thay doi, cap nhat lai vao TAT CA role workspace lien quan — bo qua buoc nay, cac workspace dung thong tin cu va output lech nhau.
Dung role de tach suy nghi:
| Role | Viec chinh | Repo skill hay dung | |------|------------|---------------------| | CEO/Strategy | Huong di, market, offer, budget, KPI | 00, 08, 09, 10, 31, 58, 59, 61 | | Leader/Campaign | Brief, timeline, review, handoff, retro, team ops | 02, 07, 20, 34, 60, 62-67 | | Content | Brand voice, calendar, brief, caption, script, copy, seeding | 35-40, 01, 04, 05, 06, 14 | | Designer | Asset list, brief visual, brand system, review, landing page | 41-50, 12, 30 | | Performance | Audience, media plan, tracking, structure, test, audit, scale | 51-57, 03, 13, 19, 21 | | Sales/RevOps | Lead quality, handoff, outreach | 18, 33 |
Neu user dung Claude Projects, ChatGPT Projects/GPTs, NotebookLM, Notion, Drive, hay MCP, map tung tool vao role nay. Khong khoa vao mot vendor neu user chua chon stack.
Mac dinh 4 workflow:
| Workflow | Chuoi skill goi y | |----------|-------------------| | Onboard brand/client | product-marketing-context -> 09 -> 08 -> 31 -> 10 -> 34 | | Launch campaign | 02 -> 31 -> 10 -> 01/04/05/06 -> 12 -> 21 -> 07 | | Weekly performance | 13 -> 03/21 -> 07 -> 34 update Brand Hub | | Content engine | 35 -> 09 -> 01 -> 36 -> 37/04/05/38 -> 42/43/44 -> 39 -> 40 | | Performance loop | 51 -> 10 -> 54 -> 53 -> 52 -> 19 -> 21 -> 55/56 -> 07 -> 57 | | Design pipeline | 41 -> 42/43/45 -> 47 -> 50 | | Leader cadence | 00 -> 61 -> 02 -> 62/47 -> 07 weekly -> 63 |
Neu co data ky truoc, luon doc truoc khi tao plan moi.
Toi thieu:
Moi output quan trong can co owner, date, source, version, next action.
| Cadence | Noi dung | Output | |---------|----------|--------| | Daily 15p | Spend, delivery, comment/inbox, tracking issue | Blocker list | | Weekly 30-60p | KPI vs target, winner/loser, bottleneck, next action | Weekly decision log | | Monthly | Revenue, channel mix, offer, team load, Brand Hub changes | OS retro + updated roadmap | | Quarterly | Market, positioning, offer ladder, tool stack | Strategy refresh |
Neu user dung Claude Projects (hoac ChatGPT Projects/GPTs tuong duong), chuyen OS thanh 5 project: Leader/CEO, Content, Designer, Performance, Knowledge Base. Moi project = custom instruction theo role + skill SOP + knowledge upload. Quy trinh 4 buoc: tao project theo role -> viet custom instruction -> upload skill + knowledge (gioi han ~20 file/project, uu tien skill hay dung) -> test trigger phrase. Chi tiet instruction mau, thu tu uu tien upload, va FAQ: doc references/ai-marketing-os-playbook.md. Kho knowledge nen tang de upload: thu muc knowledge/ cua repo.
Phan nay bat buoc khi OS co bat ky automation nao chay theo lich hoac chay tu dong theo trigger.
Moi hanh dong ma AI/automation co the lam phai duoc xep vao 1 trong 2 tang:
| Tang | Hanh dong | AI tu lam duoc? | |------|-----------|-----------------| | Tang 1 — AI tu lam | Doc du lieu, phan tich, so sanh, cham diem, soan nhap, chuan bi san cho nguoi duyet | Co — khong can hoi | | Tang 2 — phai co nguoi duyet | Tieu tien / doi ngan sach · gui tin nhan cho khach · dang noi dung cong khai · xoa hoac an du lieu · doi cai dat tai khoan | Khong — mac dinh dung lai va cho duyet |
Ranh gioi de nho: soan nhap la Tang 1, bam gui la Tang 2.
Tang 2 chi duoc bo qua buoc duyet tung lan khi co DU CA 4 dieu sau. Thieu 1 trong 4 thi quay ve che do soan nhap + cho duyet.
| Dieu kien | Y nghia | Vi du | |-----------|---------|-------| | Uy quyen ghi bang van ban | Nguoi co tham quyen cho phep, luu lai duoc | Mot dong trong decision log co ten + ngay | | Tran chi tieu tuyet doi | Muc tran ngay/tuan khong bao gio duoc vuot | "Toi da 3 trieu/ngay — cham tran thi dung va bao" | | Gioi han thay doi moi lan | Mot lan chay khong duoc doi qua nhieu | "Khong doi qua 20% ngan sach moi lan chay" | | Danh sach duoc phep (allowlist) | Chi campaign/tai khoan/list duoc liet ke moi duoc dong den | 3 campaign duoc scale; con lai chi duoc de xuat |
Bon truong hop nay luon phai co nguoi, ke ca khi da du 4 dieu kien tren: khung hoang hoac binh luan tieu cuc · khieu nai khach hang · bat thuong doanh thu hoac spend · hanh dong cham den toan bo danh sach khach (gui hang loat, xoa hang loat).
Moi automation phai co cach tat ngay lap tuc. Ghi ro trong SOP:
Khong duoc de trang thai "khong co cach dung". Mot automation khong dung duoc la rui ro, khong phai tai san.
Bat theo dung thu tu, va moi lan chi bat 1 cai. Doi cai truoc chay on va co nguoi thuc su doc output roi moi bat cai sau.
| Buoc | Bat cai gi | Vi sao phai truoc | |------|-----------|------------------| | 1 | Tracking dung + review hang tuan | Moi automation con lai deu doc so. Tracking sai thi ca he thong hanh dong theo so sai | | 2 | Giu khach dang co (nhac lich, cham soc sau mua, cuu don that bai) | Re nhat, bao ve doanh thu dang co | | 3 | Kich hoat (onboarding, tin nhan chao, nhac hoan tat) | Vit thung truoc khi do them nuoc | | 4 | Keo khach moi (ads, content, SEO) | Do them nuoc khi thung da kin | | 5 | Toi uu doanh thu (gia, goi, upsell) | Chi co y nghia khi luong da du lon |
Doi chieu bang maturity o buoc 1: maturity duoi 2 thi chua bat automation Tang 2 nao — lam foundation truoc.
Automation khong sinh ra hanh dong la chi phi, khong phai thanh tuu.
markdown# AI Marketing OS — [Ten business/team] ## 1. Chan doan hien tai | Hang muc | Muc 0-4 | Bang chung | Uu tien | ## 2. Brand Hub can co | File | Tinh trang | Owner | Update cadence | ## 3. Role workspace | Role | Tool/workspace | Context can nap | Output chinh | ## 4. Skill chain | Workflow | Skill chain | Input bat buoc | Output | ## 5. Data loop va connector | Nguon data | Tool/connector | Metric | Tan suat | ## 6. SOP van hanh | Cadence | Ai lam | Checklist | Noi luu output | ## 7. Roadmap 30-60-90 ngay | Giai doan | Viec can lam | Owner | Done khi | ## 8. Rui ro va governance | Rui ro | Cach phong tranh | Ai duyet | ## 9. So dang ky automation | Automation | Tang 1/2 | Tran chi tieu | Gioi han moi lan | Allowlist | Ai tat duoc | Tat bang cach nao | ## 10. Thu tu bat automation | Thu tu | Automation | Dieu kien du de bat | Ngay bat | Ra soat lai ngay |
product-marketing-context: tao source context dau tien.35-brand-voice, 46-brand-guideline, 09-insight-khach-hang, 58-positioning, 10-tinh-kpi-nguoc: tao 6 file Brand Hub.00-ke-hoach-mkt: tao marketing plan dua vao OS.02-brief-chien-dich: chuyen strategy thanh campaign.07-bao-cao-marketing: tao weekly/monthly report cho data loop.13-phan-tich-du-lieu va 21-audit-ads-performance: doc data va tim bottleneck.39-content-audit, 40-next-content-plan, 57-next-ads-plan, 63-campaign-retrospective: vong lap data -> plan ky sau.31-offer-design, 32-seo-growth, 33-b2b-lead-gen: growth modules dua vao OS.knowledge/ (10 file tu duy + trien khai theo role).| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 44,091 | 44,377 | +1% | 1 | 1 | 0% | 6,822 | 10,900 | +60% | 0 | 0 | — |
case-02 | fail→fail | 44,426 | 53,632 | +21% | 1 | 1 | 0% | 7,443 | 12,521 | +68% | 0 | 0 | — |
case-03 | fail→fail | 51,514 | 54,822 | +6% | 1 | 1 | 0% | 7,488 | 12,531 | +67% | 0 | 0 | — |
case-04 | pass→pass | 14,733 | 11,405 | -23% | 1 | 1 | 0% | 1,545 | 5,200 | +237% | 0 | 0 | — |
case-05 | fail→pass | 21,319 | 16,399 | -23% | 1 | 1 | 0% | 2,571 | 6,945 | +170% | 0 | 0 | — |
case-06 | fail→pass | 19,850 | 20,663 | +4% | 1 | 1 | 0% | 2,397 | 6,718 | +180% | 0 | 0 | — |
case-07 | pass→pass | 19,928 | 20,154 | +1% | 1 | 1 | 0% | 3,200 | 7,382 | +131% | 0 | 0 | — |
case-08 | pass→pass | 19,179 | 20,269 | +6% | 1 | 1 | 0% | 2,572 | 7,294 | +184% | 0 | 0 | — |
case-15 | pass→pass | 23,658 | 18,303 | -23% | 1 | 1 | 0% | 2,745 | 7,097 | +159% | 0 | 0 | — |
case-09 | fail→pass | 21,648 | 19,769 | -9% | 1 | 1 | 0% | 3,265 | 6,645 | +104% | 0 | 0 | — |
case-10 | fail→pass | 23,080 | 21,095 | -9% | 1 | 1 | 0% | 3,051 | 6,837 | +124% | 0 | 0 | — |
case-11 | fail→pass | 24,564 | 27,215 | +11% | 1 | 1 | 0% | 3,544 | 8,003 | +126% | 0 | 0 | — |
case-12 | fail→fail | 25,566 | 38,226 | +50% | 1 | 1 | 0% | 3,815 | 9,796 | +157% | 0 | 0 | — |
case-13 | fail→pass | 14,152 | 10,800 | -24% | 1 | 1 | 0% | 2,708 | 5,296 | +96% | 0 | 0 | — |
case-14 | fail→pass | 15,758 | 28,387 | +80% | 1 | 1 | 0% | 2,508 | 7,794 | +211% | 0 | 0 | — |
case-16 | pass→pass | 17,212 | 14,862 | -14% | 1 | 1 | 0% | 2,103 | 5,946 | +183% | 0 | 0 | — |
case-17 | pass→pass | 14,106 | 17,993 | +28% | 1 | 1 | 0% | 2,272 | 6,460 | +184% | 0 | 0 | — |
case-18 | pass→pass | 16,532 | 15,301 | -7% | 1 | 1 | 0% | 2,461 | 6,655 | +170% | 0 | 0 | — |
case-19 | fail→pass | 22,564 | 15,917 | -29% | 1 | 1 | 0% | 2,886 | 5,698 | +97% | 0 | 0 | — |
case-20 | pass→pass | 23,990 | 22,689 | -5% | 1 | 1 | 0% | 2,913 | 7,480 | +157% | 0 | 0 | — |
case-21 | pass→fail | 51,003 | 41,599 | -18% | 1 | 1 | 0% | 4,627 | 10,056 | +117% | 0 | 0 | — |
case-22 | pass→pass | 26,272 | 33,011 | +26% | 1 | 1 | 0% | 2,831 | 6,974 | +146% | 0 | 0 | — |
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.
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.
Other measured skills in the registry, with their headline benchmark lift.