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 26-thought-leadership-contentgit 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/26-thought-leadership-content)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/26-thought-leadership-content"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/26-thought-leadership-content/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/26-thought-leadership-content"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/26-thought-leadership-content.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 | $0.00216 | $0.05680 |
| Opus 5 | $0.00108 | $0.02840 |
| Sonnet 5 | $0.00043 | $0.01136 |
| Haiku 4.5 | $0.00022 | $0.00568 |
Grade A, and why
26-thought-leadership-content 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 13d 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 — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thought Leadership Content — Long-form Personal Brand
Long-form text de mua trust va build authority — KHAC ad copy ban hang (skill 05). Skill nay khong ban hang truc tiep, ma xay vi the chuyen gia qua noi dung gia tri.
1. Cho nguoi moi (Newbie section)
Long-form la gi?
Long-form = bai viet >500 tu (LinkedIn, FB ca nhan, Newsletter) co cau truc, dan dat tu duy nguoi doc tu A den Z. Khac short-form (caption <100 tu) va ad copy (125 ky tu hook + CTA chot don).
Khac biet voi 2 dang khac
| Tieu chi | Short-form (caption) | Ad copy (skill 05) | Long-form (skill 26) |
|---|---|---|---|
| Muc tieu | Engagement nhanh | Chot don, CPMess | Build authority, mua trust |
| Do dai | <100 tu | 125-500 ky tu | 500-3000 tu |
| CTA | Comment / Like | Nhan tin / Mua ngay | Soft CTA hoac khong CTA |
| Tan suat | 5-7 bai/tuan | Theo budget ads | 2-3 bai/tuan |
| Audience | Cold + warm | Targeted ads | Organic follower |
| Do thanh cong | Reach, like | ROAS, CPA | Save, share, DM, comment co chieu sau |
Khi nao viet long-form
- Sau giai doan awareness — da co 500-1000 follower co chat luong
- Muon dinh vi chuyen gia — khong chi la nguoi ban hang ma la nguoi day
- Co kinh nghiem that — tung that bai, tung lam project lon, tung quan ly team
- Co gio rieng — 30-60 phut/bai, viet kho, hieu chinh ky
- Co audience persona ro — biet nguoi doc dang ngoi tai dau (founder? coach? creator?)
Time investment
- 30-60 phut/bai voi nguoi co kinh nghiem viet
- 2-3 bai/tuan la nhip ben vung — khong nen ep 5 bai/tuan ngay tu dau
- Batch viet — danh 1 buoi (3-4 tieng) viet 4-5 bai cho ca tuan, hieu qua hon viet le
5 loi sai pho bien
- Qua dai khong co structure — viet tran lan, paragraph 10 dong, khong co nhip
- No story — chi liet ke insight kho khan, khong co minh chung tu cuoc song that
- Ban hang qua som — paragraph 2 da chen "khoa hoc cua toi 9.9tr" → audience bo
- Copy guru — tron lan giong noi tieng Anh dich google, khong fit thi truong VN
- No hook — dong 1 chung chung "Hom nay toi muon chia se ve..." → bi luot
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.
- 13d ago First seen · 432 lines · 216 tokens per session scan A 4893e39c3105
26-thought-leadership-content is a skill published in the GitHub repository minhnv0807/ai-business-skills (572 stars, last pushed 26d ago), licensed MIT. It adds 216 tokens to every session and 5,680 once invoked, about $0.0011 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 2026-08-30.
Other skills, from other repositories
comps-analysis
Build comparable-company valuation workbooks in Excel.
mcp-oauth-remote-gateway
Manual OAuth for remote MCP servers on headless gateways.
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
honcho
Configure and troubleshoot Honcho memory for Hermes.
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
hyperframes
Render MP4/WebM videos from HTML compositions.