agentmods.dev

04-script-video

04-script-video is a skill for Claude Code from minhnv0807/ai-business-skills. It costs 154 tokens per session (7,606 once invoked), scanned A, original, MIT.

A short-video script writing guide for TikTok, Reels, and Shorts. It structures the opening hook and timing, then provides two versions for comparison.

In plain words
What is it for?
Use it to write short scripts with an opening hook, timed sections, and alternative versions for testing.
Why use it?
It helps turn a product or personal-brand idea into a video that starts clearly and stays organized. It removes the problem of not knowing what to say or show at each moment.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the ai-business-skills plugin — 147 skills, 6 agents, 10 MCP servers shipped together

not rated 641repo +1 changed 6d ago A scan SkillSpector: pass 154 tokens original MIT

Good fit Use it to write short scripts with an opening hook, timed sections, and alternative versions for testing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/minhnv0807/ai-business-skills/04-script-video
View source ↗ minhnv0807/ai-business-skills opa.business
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 04-script-video
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 147 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 04-script-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/04-script-video/github.svg)](https://agentmods.dev/skills/minhnv0807/ai-business-skills/04-script-video)
Your own site
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/04-script-video"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/04-script-video/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 04-script-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/04-script-video"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/04-script-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,606 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00154 $0.07606
Opus 5.5 $0.00062 $0.03042
Sonnet 5.5 $0.00031 $0.01521
Haiku 4.5 $0.00015 $0.00761

Measured 6d ago against content hash bb2e13710cef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

04-script-video 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 6d 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.

skills/vi/04-script-video/SKILL.md · 496 lines

How it starts

The opening of the file, as written. The whole thing — 496 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Script Video

Buoc 0: Kiem tra context file

Truoc khi viet script, doc ca 2 file (neu ton tai):

  1. .agents/product-marketing-context.md (marketing san pham)
  2. .agents/personal-brand-context.md (personal brand)

Quyet dinh mode:

  • Chi co product-marketing-context.md → MODE A (mac dinh, hanh vi cu — sections ben duoi)
  • Chi co personal-brand-context.md → MODE B (Personal Brand Mode — section "Personal Brand Mode" ben duoi)
  • Co ca 2 → HOI 1 cau: "Ban dang viet video ban san pham hay xay personal brand?"
  • Khong co → De xuat tao context phu hop (chay skill product-marketing-context hoac 22-personal-brand-context truoc)

Thu thap thong tin

Hoi toi da 4 cau truoc khi viet:

  1. San pham / dich vu gi? Mo ta ngan, USP chinh, gia (neu co).
  2. Nen tang + thoi luong mong muon? TikTok (15/30/45/60s), Reels (15/30/60s), YouTube Shorts (30/60s). Neu khong chon — mac dinh TikTok 30s.
  3. Doi tuong muc tieu? Gioi tinh, do tuoi, noi dau chinh, muc tieu ho muon dat.
  4. Goc do noi dung? TOFU (thu hut moi), MOFU (thuyet phuc), BOFU (chot don). Neu khong chon — mac dinh TOFU.

Nguyen tac cot loi

5 loai hook (3 giay dau)

# Loai hook Cong thuc Vi du
1 Cau hoi Dat cau hoi cham noi dau — buoc nguoi xem phai suy nghi "Ban co biet tai sao da ban cu len mun mai khong?"
2 Con so Mo dau bang so lieu bat ngo, cu the "97% nguoi dung sai buoc nay moi sang"
3 Gay tranh cai Noi nguoc lai niem tin pho bien "Rua mat 2 lan/ngay chinh la ly do da ban te hon"
4 Tinh huong Dung POV, vao vai, ke chuyen ngan "POV: Lan dau di spa ma khong biet chon gi"
5 Ket qua truoc Show ket qua dau — roi giai thich cach lam "Da minh sau 2 tuan dung cai nay — xem cach lam"

Quy tac chon hook:

  • TOFU: Uu tien hook 1 (cau hoi), 4 (tinh huong), 3 (gay tranh cai)
  • MOFU: Uu tien hook 5 (ket qua truoc), 2 (con so)
  • BOFU: Uu tien hook 2 (con so), 5 (ket qua truoc)

Read the full file on GitHub · 496 lines

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. 6d ago Changed bb2e13710cef
  2. 7d ago Changed · +1 lines 72b5637211eb
  3. 2mo ago First seen · 495 lines · 154 tokens per session scan A 6549011f0a06

Subscribe to this mod's changes

04-script-video is a skill published in the GitHub repository minhnv0807/ai-business-skills (641 stars, last pushed 2d ago), licensed MIT. It adds 154 tokens to every session and 7,606 once invoked, about $0.0006 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.

Claude CodeCreative and mediaMarketing and SEOagent-skillsai-agentsanthropicchatgptclaude-plugin
Related

04-script-video compared with skills from other repositories

04-script-video next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
04-script-videominhnv0807/ai-business-skillsSkill6412d agoMITA154Claude Code
anatomyNousResearch/hermes-agentSkill261kyesterdayMITA15Claude Code, Codex
ascii-videoNousResearch/hermes-agentSkill261kyesterdayMITA17Claude Code, Codex
creative-ideationNousResearch/hermes-agentSkill261kyesterdayMITA14Claude Code, Codex
drug-discoveryNousResearch/hermes-agentSkill261kyesterdayMITA19Claude Code, Codex
subagent-driven-developmentNousResearch/hermes-agentSkill261kyesterdayMITA17Claude Code, Codex
claude-apiasgeirtj/system_prompts_leaksSkill71k2d agoCC0-1.0A294Claude Code, Codex