Works with the AI Agents you already use
Malaysia Ad Critic
Screen social commerce content for Malaysian advertising law violations and platform compliance in Malay and English.
Free
Malaysia Ad Critic
Example session with this skill installed
Check this TikTok Shop caption: "Jamin putih dalam 3 hari! Krim ajaib ini merawat kanser kulit. Beli sekarang! #putih #skincare" Evidence: none.
- Read your context and instructions
- Compiled the malaysia ad critic
I have analyzed the content for TikTok Shop. This is a pre-publication screen, not legal advice. Sila ambil maklum bahawa ini adalah saringan awal dan bukannya khidmat nasihat undang-undang.
{
"verdict": "fail",
"hard_fails": [
{
"category": 2,
"rule": "unsubstantiated_guarantee",
"trigger": "Jamin putih dalam 3 hari!",
"reason": "Guaranteed results within a specific timeframe are prohibited without clinical evidence."
},
{
"category": 4,
"rule": "4a",
"trigger": "merawat kanser kulit",
"reason": "Disease claims (cancer) are strictly prohibited for cosmetic or food products under Malaysian law."
}
],
"soft_fails": [
{
"category": 8,
"trigger": "no_hook",
"reason": "The opening line is a compliance risk rather than an engaging hook."
}
],
"assumed": [
"funnel_stage: conversion",
"brand_voice: not given"
],
"notes": "Content contains severe regulatory breaches regarding prohibited medical claims and unsubstantiated guarantees."
}
Ringkasan Penilaian
Keputusan: GAGAL (FAIL)
Gagal (Kategori 4): Frasa "merawat kanser kulit" dilarang sama sekali kerana membuat dakwaan merawat penyakit terkawal.
Gagal (Kategori 2): Frasa "Jamin putih dalam 3 hari!" adalah dakwaan tanpa bukti dan jaminan tempoh masa yang tidak dibenarkan.
- Teguran (Kategori 8): Skrip memerlukan 'hook' yang lebih baik dan patuh peraturan.
Next steps
- Alih keluar semua dakwaan berkaitan rawatan penyakit kronik (kanser).
- Buang jaminan tempoh masa (3 hari) kecuali jika anda mempunyai bukti klinikal yang disahkan.
- Gunakan 'Fix Mode' dengan menaip "betulkan" untuk mendapatkan cadangan ayat yang patuh syariah dan undang-undang.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop your social commerce content from getting flagged or banned by Malaysian regulators. This skill screens B2C ad copy, scripts, and listings against local advertising laws and platform guidelines before you hit publish. It identifies high-risk claims in both Bahasa Melayu and English, ensuring your TikTok Shop, Shopee, or Instagram content stays compliant.
What it does
- Compliance screening Identifies violations of Malaysian advertising rules for health, medicine, and cosmetic therapeutic claims.
- Evidence verification Flags unsubstantiated claims that lack required documentation like KKLIU, NPRA, or Halal certification.
- Platform audit Checks content against specific constraints for TikTok, Instagram, YouTube Shorts, Shopee, and WhatsApp.
- Multilingual detection Scans for high-risk trigger phrases in both Bahasa Melayu and English, including Manglish and mixed-language text.
- Disclosure checking Ensures paid, sponsored, or affiliate content includes mandatory disclosures to avoid platform breaches.
How it works
- Submit content Provide a caption, script, or product listing text along with any available evidence like certificate numbers.
- Automated judging The skill extracts claims and compares them against a structured database of Malaysian advertising regulations.
- Verdict report Receive a JSON object and a summary identifying specific "Hard Fails" (legal/safety) and "Soft Fails" (voice/conversion).
- Fix mode Request a rewrite to receive suggested phrases that remove the compliance risk while maintaining the original intent.
Frameworks & tools
This skill utilizes specialized reference datasets for Malaysian advertising laws, KKM/NPRA guidelines, and social commerce platform policies.
Why this beats prompting it yourself
Generic LLMs lack the specific regulatory context for Malaysian ad law, often missing subtle prohibited therapeutic claims or failing to require specific local certifications. This skill uses a tiered fail system that quotes the exact problematic phrase, providing a systematic audit trail that standard prompting cannot replicate.
Use cases
- Pre-flight check Reviewing TikTok Shop scripts for prohibited medical claims before filming.
- Halal claim audit Checking WhatsApp blast messages for unverified religious claims.
- Batch screening Auditing a folder of Instagram captions for missing affiliate disclosures.
- Price compliance Verifying Shopee product descriptions for misleading price indications or "100% guarantee" traps.
Known limitations
Does not verify certificate numbers against live government databases like MOH or JAKIM portals. Scope is limited to Malaysian law and social commerce platforms.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.
Does not verify certificate numbers against live government databases. Limited to Malaysian law and social commerce platforms. Must not be used as official legal advice.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 18 days ago
- Free with an Agensi account