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 74-copy-hai-lopgit 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/74-copy-hai-lop)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/74-copy-hai-lop"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/74-copy-hai-lop/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/74-copy-hai-lop"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/74-copy-hai-lop.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 | $0.00187 | $0.03721 |
| Opus 5.5 | $0.00075 | $0.01488 |
| Sonnet 5.5 | $0.00037 | $0.00744 |
| Haiku 4.5 | $0.00019 | $0.00372 |
Grade A, and why
74-copy-hai-lop 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 1mo 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copy Hai Lop — Slogan / Poster / Cau Ngan De Nho
Skill nay bo sung, khong thay the
05-copy-quang-caohay37-caption-social. 05 so huu copy tra tien, gioi han ky tu, chinh sach nen tang, 6 bien the pheu. 37 so huu caption organic dai. 74 so huu cau ngan hai lop + brief poster. Khong tron lane.
Co che chuyen giao (khong phai "hoc noi dirty"): mot cau dong thoi dung o hai ngu canh. Tac gia chi viet lop mat. Nguoi doc tu nhay mot nhip sang lop trong. Nhip nhay do la ly do ho dung lai / chia se.
Nguon method (MIT, khong nhap poster hay cau goc thuong hieu nuoc ngoai): xem references/bien-gioi-va-nguon.md.
Thu thap thong tin
Mac dinh giao the phuong an, khong hoi khao sat. Chi hoi khi that su thieu.
- Ban gi, cho ai? Day la slot duy nhat duoc phep chan truoc khi viet. Neu khong suy ra duoc lop trong thi hoi 1 cau, roi dung.
- Neu user da noi ro san pham / dip / kenh: khong hoi them. Viet gia dinh thanh 1 dong ("Toi lam theo 'dang anh feed, khach cuoi tuan' — sai thi noi, toi doi").
- Khong bia them slot ngan sach, KPI, doi thu, brand color. Can thi gia dinh hoac ghi o cuoi "ban co the bo sung".
- Neu ngay le / so lieu user dua lech thuc te, ghi 1 cau canh bao trong output — khong dung flow.
Toi da 4 cau neu that su thieu. Uu tien 1 cau hoac 0.
Nguyen tac
- Hai lop, mot nhip. Lop mat doc duoc ma khong can biet brand. Lop trong la gia tri san pham, khong phai tro cuoi rieng. Chuoi lien tuong chi duoc mot mui ten. Hai mui ten tro len = do, viet lai.
- Diem to la chet. Viet xong cau la dung. Khong them "y la...", "day chinh la suc manh cua...".
- Cong thuc la cach viet, khong phai cach nghi. Truoc khi chon cong thuc, tim moc noi (
references/tim-moc-noi.md). Khong bam thi bo dip, dung gắng. - 3-5 the phai khac that. Khac cong thuc, khac chu the hinh, khac giong. Khong giao 3 bien the cua cung mot y.
- Cau tren poster <= 12 chu. Tot nhat 4-8. Dai hon chi khi la cap doi / song song. Caption dai de o phan phu, khong len hinh.
- Roi vao "ban", khong vao thong so. Nguoi ta chia se vi "cau nay noi minh", khong vi "san pham tot".
- Doc brand voice truoc.
35-brand-voice+ context san pham. Cau hay ma lech person brand = bo. - Khong dung skill nay de chay ads. Neu user muon len camp, lay cau thang roi dua
05-copy-quang-caoviet lai theo pheu + policy.
What ships with it
7 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.
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.
- 1mo ago First seen · 235 lines · 187 tokens per session scan A b8cb7a1f5faf
74-copy-hai-lop is a skill published in the GitHub repository minhnv0807/ai-business-skills (618 stars, last pushed 1mo ago), licensed MIT. It adds 187 tokens to every session and 3,721 once invoked, about $0.0007 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 2026-09-03.
Other skills, from other repositories
anatomy
Explain an idea as an interactive isometric machine figure.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.
creative-ideation
Generate ideas via named methods from creative practice.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
claude-api
Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude…
llava
Vision-language chat: VQA, captioning, image dialogue.