76-van-hanh-san-tmdt

76-van-hanh-san-tmdt is a skill for Claude Code from minhnv0807/ai-business-skills. It costs 275 tokens per session (4,415 once invoked), scanned A, original, MIT.

An e-commerce operations guide for shops on Shopee, TikTok Shop, and Lazada. It evaluates profit and loss per order, including fees, advertising costs, vouchers, returns, and sales campaigns.

In plain words
What is it for?
Use it to calculate order contribution, find break-even advertising targets, assess marketplace ads, and prepare mega-sale, voucher, and livestream activities.
Why use it?
It helps reveal whether orders and marketplace advertising are actually profitable after all deductions, rather than judging performance from sales revenue alone.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-business-skills plugin — 146 skills, 6 agents, 10 MCP servers shipped together

Good fit Use it to calculate order contribution, find break-even advertising targets, assess marketplace ads, and prepare mega-sale, voucher, and livestream activities.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/minhnv0807/ai-business-skills/76-van-hanh-san-tmdt
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add minhnv0807/ai-business-skills --skill 76-van-hanh-san-tmdt
Clone the repo
git clone --depth 1 https://github.com/minhnv0807/ai-business-skills

Made for: Claude Code.

Or install ai-business-skills, the plugin that ships this one along with the rest of its 146 skills, 6 agents, 10 MCP servers.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 76-van-hanh-san-tmdt

README.md
[![agentmods](https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/76-van-hanh-san-tmdt/github.svg)](https://agentmods.dev/skills/minhnv0807/ai-business-skills/76-van-hanh-san-tmdt)
Your own site
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/76-van-hanh-san-tmdt"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/76-van-hanh-san-tmdt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for 76-van-hanh-san-tmdt

Your own site · 80×15
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/76-van-hanh-san-tmdt"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/76-van-hanh-san-tmdt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 275 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,415 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00275 $0.04415
Opus 5.5 $0.00110 $0.01766
Sonnet 5.5 $0.00055 $0.00883
Haiku 4.5 $0.00028 $0.00441

Measured today against content hash 20ac6dd6790b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

76-van-hanh-san-tmdt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/vi/76-van-hanh-san-tmdt/SKILL.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Van Hanh San TMDT — P&L Tung Don Truoc, Ads Sau

Quy tac van hanh chung: skills/vi/references/quy-tac-van-hanh.md (dac biet quy tac 2, 3, 7). Phap ly: moi dieu luat trong skill nay chi link ve skills/vi/references/phap-ly-marketing-vn.md. Khong phai tu van phap ly / thue.

Skill nay lo viec van hanh gian hang DANG CHAY: don nay lai hay lo sau khi tru het phi, ads co dang ngoi tren muc hoa von khong, mega sale co ap dung duoc khong. Khong mo gian hang (skill 11), khong dat gia tu dau (skill 17).

Thu thap thong tin

Doc .agents/product-marketing-context.md truoc (AOV, gia von, bien loi nhuan, nganh hang). Chi hoi cai con thieu, toi da 4 cau:

  1. San nao, nganh hang gi, mo hinh gi? (Shopee / TikTok Shop / Lazada; Mall hay shop thuong; ban qua video, live hay tim kiem)
  2. Bo so don hang mau: gia ban, gia von, trong luong / phi van chuyen shop chiu, ty le hoan don thuc te. Neu chua co → dung placeholder [CAN SO LIEU THAT].
  3. Phi that dang bi tru: gui file doi soat (settlement / bao cao doi soat) 1-2 thang gan nhat. Khong co → chi nhap phi tu Seller Center, ghi ngay kiem.
  4. Viec can lam la gi? Tinh P&L / danh gia ads tren san / chuan bi mega sale / len run sheet livestream / sua review va chat.

Thieu data van lam duoc phan tinh bang bien, ghi gia dinh o dau output (quy tac 1).

Nguyen tac

  1. P&L don hang truoc, ads sau. Khong ai duoc dua target ROAS khi chua co bien dong gop truoc ads cua don that.
  2. Moi loai phi la mot bien co ten, co ngay kiem. Khong gop thanh "phi san ~ X%". Phi san doi lien tuc (quy tac 4).
  3. Khong bao gio ghi cung muc phi. Skill nay khong chua ty le phi cua san nao. Phi lay tu Seller Center / file doi soat cua chinh shop; con so trong vi du la gia dinh.
  4. ROAS cua san phai quy ve doanh thu thuan. Ghi ro chi so ROAS cua san tinh tren GMV (truoc voucher / hoan don) hay doanh thu thuan; chi so hoa von chi dung doanh thu thuan sau voucher cua shop.
  5. Gan nhan bang chung (quy tac 3): phi tu file doi soat = observed; phi tu bao chi / ban tin = reported; ROAS_be tinh tu ca hai = inferred.
  6. Chi doc va soan nhap (quy tac 7). Doi ngan sach Shopee Ads / GMV Max, bat-tat chuong trinh, dang ky mega sale, dang voucher deu qua cong duyet 6 buoc.
  7. Hanh vi la do (hub muc 7): khong danh gia gia, khong ep so luong review, khong cho nguoi khac "mua giu cho" de len rank. Danh gia gia mao (review gia) la ranh do do, khong lam.

Read the full file on GitHub · 228 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 228 lines · 275 tokens per session scan A 20ac6dd6790b

Subscribe to this mod's changes

76-van-hanh-san-tmdt is a skill published in the GitHub repository minhnv0807/ai-business-skills (635 stars, last pushed yesterday), licensed MIT. It adds 275 tokens to every session and 4,415 once invoked, about $0.0011 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-28.