# 李哈利Harry (@harryleemedia) on tiktok

- id: koinon:creator:tiktok_harryleemedia
- url: https://koinonlink.com/kol/tiktok/harryleemedia
- schema_version: 1.4

## Identity
- platform: tiktok
- handle: harryleemedia
- platform_url: https://www.tiktok.com/@harryleemedia
- country: United States
- entity_type: creator
- person_id: Cross-platform identity not resolved for this creator.

## Reach
- followers: 16001
- following: 4
- posts_observed: 37
- verified: false
- size_tier: koc

## Engagement
- status: not_collected
- status_note: Engagement has not been collected for this creator yet. This is a gap in our collection, NOT a statement that the creator has no engagement. Follower count is known, so it is measurable.
- unit_note: engagement_rate and peak_post_engagement_rate are ratios (0-1); avg_interactions_per_post and best_post_interactions are absolute counts. Read status before reading any number: a null rate has several different causes and status says which one applies here.

## Content
- category: software
- subcategory: ai_tools
- category_confidence: 0.95
- category_source: derived_from_recent_content
- topics: Claude Code與Skills安裝使用, MCP工具整合與多代理系統, AI影片生成與動畫工作流, 開源AI工具與免費替代方案, AI網站UI設計與元件庫, 多模型串接與本地算力優化

## Audience (inferred)
- status: present
- description: Developers and content creators using AI tools like Claude Code and MCP, primarily technical AI practitioners
- roles: dev
- seniority: practitioner
- pain_points: Repeatedly writing long prompts, unable to install and reuse skills directly, Chaotic switching between multiple AI tools and terminal management, lacking unified control, High cost and long production cycles for high-quality AI ads and videos, with limited budgets, Too many open-source AI tools to choose from, but difficult to integrate and consistently maintain output style
- posts_analysed: 40
- confidence: 0.75

## Commercial (inferred)
- audience_buyer_fit: 0.9
- promotion_intent: 0.9
- open_to_collaboration: false
- contact: Koinon does not publish creator contact details.

## Quality signals
- authenticity_score: 47
- authenticity_basis: profile_shape_only
- credibility_score: 47
- flagged_for_review: false
- koinon_bd_grade: B — measures Koinon partner-outreach fit, not creator quality
- interpretation: Signals for triage, not verdicts. A flag means the profile is worth a manual check.

## Evidence
- [tiktok_harryleemedia#92201327] 廣告製作週期長，錯過最佳推廣時機。 預算有限，無法投入大量資金製作高品質廣告。 廣告效果不佳，卻不知道問題出在哪裡。 告別傳統，擁抱AI廣告新時代！ 我們致力於為中小企業提供全方位的AI廣告製作解決方案。利用先進的AI技術，我們可以為您： 快速產生創意文案和視覺素材：只需提供您的產品資訊和目標受眾，AI能在很短時間內為您量身打造多個廣告方案。 大幅縮短製作週期：從創意到成品，只需短短幾天，讓您迅速抓住市場熱點。 顯著降低成本：告別高昂的團隊費用，用更少的預算獲得專業級的廣告效果。 智慧優化廣告表現：透過數據分析，AI能預測哪些廣告效果更好，並提供優化建議 (https://www.tiktok.com/@harryleemedia)
- [tiktok_harryleemedia#b6157440] original sound - harryleemedia
- [tiktok_harryleemedia#b81e1990] And Behold
- [tiktok_harryleemedia#2e983c49] It is a becoming a big trend on TikTok now! Click here: ai廣告
- [tiktok_harryleemedia#735d60fc] Check out 李哈利Harry’s video! #TikTok >
- [tiktok_harryleemedia#e6006e44] 很多人問 AI 問題時，只得到一個答案，然後直接照做。但問題是，AI 往往傾向配合你的想法，而不是主動挑戰它。 這個 Council Skill 的有趣之處在於，它會把你的問題交給多個 AI 顧問一起分析。 其中一位專門找致命漏洞，一位負責質疑前提假設，一位檢查你是否在解決真正的問題，其他顧問則從不同角度提出反對意見與風險評估。最後再由「主席」整合所有觀點，給出最終建議。 這種方式很像把一個想法丟進董事會，而不是只問

## Provenance
Every inferred field below carries how it was produced. Facts stay facts; inferences stay inferences.

- audience.description: source_type=ai_inferred, confidence=0.75, freshness_days=56, method=llm_persona_from_recent_content
- audience.roles: source_type=ai_inferred, confidence=0.75, freshness_days=56, method=llm_persona_from_recent_content
- audience.seniority: source_type=ai_inferred, confidence=0.75, freshness_days=56, method=llm_persona_from_recent_content
- commercial.audience_buyer_fit: source_type=ai_inferred, confidence=0.6, freshness_days=56, method=llm_scorer — Relative signal within Koinon indexing, not a market-wide score.
- commercial.promotion_intent: source_type=ai_inferred, confidence=0.6, freshness_days=56, method=llm_scorer
- quality.anomaly_flags: source_type=heuristic, confidence=0.5, freshness_days=56, method=profile_snapshot_and_engagement_ratio_heuristic — Means "worth a manual check", NOT confirmed fraud. Flags can be wrong and are not a verdict about the person.
- quality.authenticity_score: source_type=heuristic, confidence=0.25, freshness_days=56, method=Profile-shape heuristic from a single snapshot (follower count, following ratio, account age, posting volume, verification), reduced for engagement red flags where post engagement was collected. Where only a follower count is available the score saturates at 58. — The input set differs by platform; do not compare this score across platforms.
- quality.koinon_bd_grade: source_type=ai_inferred, confidence=0.5, freshness_days=56, method=llm_partner_fit_classifier + fit_score >= 0.6 AND authenticity >= 60 => A; fit_score >= 0.4 AND authenticity >= 45 => B; else C. authenticity < 30 or a promotional-pattern flag => quarantine. — Koinon partner-outreach fit, not creator quality.
- reach.followers: source_type=observed, confidence=0.95, freshness_days=56, method=platform_profile

## Freshness
- profile_checked_days_ago: 56
- content_analysed_days_ago: 56
- audience_updated_days_ago: 56

## AI retrieval
- indexing_requests: 9
- user_triggered_requests: 0
- note: Being indexed in bulk is not the same as being retrieved to answer a question.

## This profile
- Claim or correct: https://koinonlink.com/claim?k=tiktok_harryleemedia
- Request removal: https://koinonlink.com/claim?k=tiktok_harryleemedia
- Terms: https://koinonlink.com/for-ai