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.
npx skills add minhnv0807/ai-business-skills --skill 71-sales-enablementgit clone --depth 1 https://github.com/minhnv0807/ai-business-skillsWrote 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.
[](https://agentmods.dev/skills/minhnv0807/ai-business-skills/71-sales-enablement)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/71-sales-enablement"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/71-sales-enablement/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.
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/71-sales-enablement"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/71-sales-enablement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00261 | $0.05656 |
| Opus 5 | $0.00130 | $0.02828 |
| Sonnet 5 | $0.00052 | $0.01131 |
| Haiku 4.5 | $0.00026 | $0.00566 |
Grade A, and why
71-sales-enablement 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 9d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sales Enablement — Tai Lieu Ban Hang Va Ky Luat Pipeline
O SME VN, nguoi lam tai lieu ban hang va nguoi giu pipeline thuong la cung mot nguoi — nen skill nay gop lam mot: dua ra dung thu nguoi ban can cam khi dang noi chuyen voi khach, va dung ky luat de khach khong roi rung giua chung.
Thu thap thong tin
Hoi toi da 4 cau:
- Ban gi, cho ai, gia tri don trung binh bao nhieu, tu luc khach hoi den luc chot mat bao lau?
- Ai ban va lead vao qua kenh nao? Chinh chu / 1-2 nhan vien / doi ban hang? Inbox Zalo - Messenger, goi dien, gap truc tiep, gioi thieu?
- Dang co san tai lieu gi, va khach hay tu choi bang cau nao nhat? Ke 3 cau tu choi nghe nhieu nhat, dung nguyen van khach noi.
- Dang quan ly khach tiem nang bang gi? CRM, Google Sheet, so tay, tin nhan chua doc, hay khong quan ly gi ca?
Nguyen tac
- Nguoi ban chi dung cai ho tin. Viet bang ngon ngu nguoi ban dang noi voi khach, khong phai ngon ngu marketing. Neu nguoi ban phai viet lai truoc khi gui thi tai lieu do da sai.
- Doc duoc trong 3 giay khi dang goi. Tai lieu ma phai doc 30 giay moi thay cau tra loi la tai lieu that bai. Moi thu quan trong phai nam trong mot man hinh.
- Moi loi hua deu phai co bang chung. Con so, anh, danh gia co ten, hop dong da lam. Khong co bang chung thi bo cau do ra khoi tai lieu.
- Giai doan pipeline dinh nghia bang tieu chi RA, khong chi tieu chi vao. Tieu chi vao lam pipeline dep; tieu chi ra lam pipeline that. Khong co tieu chi ra thi khach nam mai o mot giai doan va khong ai biet.
- Toc do phan hoi quyet dinh nhieu hon noi dung phan hoi. Khach nhan tin inbox thuong dang nhan tin cho nhieu ben cung luc; ai tra loi truoc thuong duoc noi chuyen truoc.
- Mot nguoi lam ca hai viec. Dung thiet ke he thong can hai vi tri chuyen trach neu doi chi co mot nguoi.
- Bang chung cua hieu qua la nguoi ban dung that. Sau 2 tuan, hoi: da mo tai lieu nao, mo bao nhieu lan. Cai khong ai mo thi bo, dung sua.
Ngoai pham vi: bo phan duyet hop dong rieng, bac duyet chiet khau theo cap quan ly - tai chinh - phap che, va nguong gia tri hop dong de kich hoat quy trinh duyet. Do la so do to chuc cua doanh nghiep lon, khong phai cua doi ban hang 1-5 nguoi. Neu ban da lon den muc can chung, ban da co bo phan phap che roi.
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.
- 9d ago First seen · 259 lines · 261 tokens per session scan A e99c790c4515
71-sales-enablement is a skill published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 26d ago), licensed MIT. It adds 261 tokens to every session and 5,656 once invoked, about $0.0013 per session on Opus 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 2026-09-03.
Other skills, from other repositories
kanban-video-orchestrator
Plan and run multi-agent video production pipelines.
sdlc-review
Review Kanban handoffs and route verified outcomes.
teams-meeting-pipeline
Teams meeting summaries, job replay, Graph subscriptions.
batch
Research and plan a large-scale change, then execute it in parallel across 5–30 isolated worktree agents that each open a PR.
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
subagent-dag-orchestration
Use when a task breaks into several distinct steps that a separate sub-agent could each carry out. A DAG node dispatches to an agent on the roster and cannot call your own tools, so steps that are just your own tool calls (reading files, small edits, running commands) are not a DAG for being many - do those yourself.…