agentmods.dev

03-danh-gia-hieu-suat

03-danh-gia-hieu-suat is a skill for Claude Code from minhnv0807/ai-business-skills. It costs 185 tokens per session (6,487 once invoked), scanned A, original, MIT.

A diagnostic guide for finding why marketing results are poor. It examines tracking, ad delivery, creative, landing pages, and audience quality before producing a short action plan.

In plain words
What is it for?
Use it to investigate high message or lead costs, falling return on ad spend, weak leads, missing sales, or ineffective creative across Meta, TikTok, and Google.
Why use it?
It prevents teams from guessing whether weak results come from the ads, the website, measurement setup, or the people being reached. It connects the numbers to likely causes and next actions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

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

not rated 641repo +1 changed 7d ago A scan SkillSpector: pass 185 tokens original MIT

Good fit Use it to investigate high message or lead costs, falling return on ad spend, weak leads, missing sales, or ineffective creative across Meta, TikTok, and Google.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/minhnv0807/ai-business-skills/03-danh-gia-hieu-suat
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 03-danh-gia-hieu-suat
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 03-danh-gia-hieu-suat

README.md
[![agentmods](https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/03-danh-gia-hieu-suat/github.svg)](https://agentmods.dev/skills/minhnv0807/ai-business-skills/03-danh-gia-hieu-suat)
Your own site
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/03-danh-gia-hieu-suat"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/03-danh-gia-hieu-suat/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 03-danh-gia-hieu-suat

Your own site · 80×15
<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/03-danh-gia-hieu-suat"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/03-danh-gia-hieu-suat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 185 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,487 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 $0.00185 $0.06487
Opus 5.5 $0.00074 $0.02595
Sonnet 5.5 $0.00037 $0.01297
Haiku 4.5 $0.00018 $0.00649

Measured 7d ago against content hash 99caa900685b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

03-danh-gia-hieu-suat 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 7d 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/03-danh-gia-hieu-suat/SKILL.md · 406 lines

How it starts

The opening of the file, as written. The whole thing — 406 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Danh Gia Hieu Suat

Quy tac van hanh chung: skills/vi/references/quy-tac-van-hanh.md (dac biet quy tac 2, 3, 7).

Thu thap thong tin

Hoi user toi da 4 cau truoc khi bat dau:

  1. Kenh nao can audit? Meta Ads / TikTok Ads / Google Ads / Organic TikTok / Facebook / Email / Tat ca?
  2. So lieu hien tai? Cung cap data: Spend, Impressions, Click, CTR, CPMess/CPL, So mess/lead, ROAS, thoi gian chay.
  3. Van de dang gap? CPMess tang / ROAS giam / Lead chat luong kem / Khong co don / Creative khong hieu qua?
  4. Muc tieu la gi? KPI muc tieu ban dau la bao nhieu? (CPMess, ROAS, so lead/don/thang)

Auto-pull data qua MCP (neu co ket noi)

Neu user da setup MCP server, pull data tu dong thay vi yeu cau paste. Xem huong dan: skills/vi/references/mcp-ads-integration.md Meta Official MCP: https://mcp.facebook.com/ads — setup 5 phut qua claude.ai/settings/integrations

Nen tang MCP khuyen dung Data pull
Meta Ads Meta Official MCP (mcp.facebook.com/ads) Liet ke tool luc ket noi — so tool doi theo ban beta; xem nhom tool ben duoi
Meta Ads (alt) Pipeboard (mcp.pipeboard.co/meta-ads-mcp) Liet ke tool luc ket noi — targeting research manh hon
Google Ads Google Official MCP GAQL query — cost, clicks, conversions, impression share
TikTok Ads TikTok Ads MCP Campaign/ad group performance reports
Nhieu nen tang Adspirer ads-mcp 222 metrics, cross-platform unified

Meta Official MCP co the GHI (khong chi doc), nen moi de xuat thay doi tu data MCP di theo quy tac 7 (nhap truoc, ghi sau) — khong tu y sua campaign.

Meta Official MCP — Tools dung cho Danh gia hieu suat:

DIAGNOSTIC (chan doan):
  ads_insights_anomaly_signal             ← Tim KPI bat thuong vs baseline → feed vao 5 Whys
  ads_insights_performance_trend          ← Xu huong 7/14/30 ngay → phat hien suy giam

BENCHMARK (so sanh):
  ads_insights_industry_benchmark         ← CPM, CTR, CPC cua ban vs trung binh nganh
  ads_insights_auction_ranking_benchmarks ← Quality ranking, engagement rate ranking vs doi thu
  ads_insights_advertiser_context         ← Boi canh nganh va khu vuc

OPTIMIZATION:
  ads_get_opportunity_score               ← Meta goi y co hoi toi uu → action plan
  ads_get_dataset_quality                 ← Chat luong tracking (pixel + CAPI)

Read the full file on GitHub · 406 lines

Files

What ships with it

2 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.

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. 7d ago Changed · +1 lines 99caa900685b
  2. 10d ago Changed · +5 lines · +13 tokens per session 4eb432ab284c
  3. 2mo ago First seen · 400 lines · 172 tokens per session scan A 07884b5f5013

Subscribe to this mod's changes

03-danh-gia-hieu-suat is a skill published in the GitHub repository minhnv0807/ai-business-skills (641 stars, last pushed 2d ago), licensed MIT. It adds 185 tokens to every session and 6,487 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.

Analytics and metricsClaude CodeMarketing and SEOagent-skillsai-agentsanthropicchatgptclaude-plugin
Related

03-danh-gia-hieu-suat compared with skills from other repositories

03-danh-gia-hieu-suat next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
03-danh-gia-hieu-suatminhnv0807/ai-business-skillsSkill6412d agoMITA185Claude 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