Individual skill
competitor-kol-radar
竞品红人营销打法拆解（营销总监视角）——抓取竞品近 N 个月在 TikTok / Instagram / YouTube（国内小红书为实验功能）上的红人与 UGC 内容，判断它是"买量型""自来水型"还是"联盟铺量型"，统计博主量级、内容量、播放中位数、主打选题与卖点、销售转化渠道，对标库定位，输出带"对我们意味着什么 + 建议动作"的网页报告和明细 CSV。只要用户想研究某个品牌/竞品怎么做红人营销、KOL 投放、海外社媒种草、出海内容打法、博主合作、UGC 声量、"它在 TikTok/IG/YouTube 上投了哪些博主"、"竞品的红人投放怎么样"、"帮我拆一下 XX 的海外营销"，就应使用本技能，即使用户没说"竞品调研"。不用于：日常抖音竞品账号监控（用 competitor-radar）、单条视频解析、给自己找博主建联。
SKILL.md
Source commit b4bf30cb9c81ae073e17898f874b97350be45109
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Not checked yet
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 8
- Repository last updated
- Oct 26, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skill Repository topic
- claude-skill Repository topic
- competitor-analysis Repository topic
- influencer-marketing Repository topic
- kol Repository topic
- marketing Repository topic
- tiktok Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
.gitignoreasset · 92 bytesINSTALL.mddoc · 2,599 bytesLICENSEasset · 1,068 bytesREADME.mddoc · 8,210 bytesSKILL.mdcore · 7,872 bytesSKILL.mdcore · 7,872 bytesSKILL.mdcore · 7,872 bytesSKILL.mdcore · 7,872 bytesassets/brief.example.jsonasset · 1,127 bytesassets/report_template.htmlasset · 44,689 bytesdocs/styles/brand.pngasset · 472,493 bytesdocs/styles/consulting.pngasset · 333,498 bytesdocs/styles/notebook.pngasset · 381,534 bytesdocs/styles/terminal.pngasset · 402,752 bytesdocs/styles/wrapped.pngasset · 351,995 bytesexamples/flowerknows/brief.jsonasset · 1,441 bytesexamples/flowerknows/narrative.jsonasset · 6,841 bytesreferences/benchmarks.jsonasset · 815 bytesreferences/channel-signals.mddoc · 1,917 bytesreferences/fallback-agent-reach.mddoc · 3,611 bytesreferences/methodology.mddoc · 3,897 bytesreferences/pitfalls.mddoc · 2,984 bytesreferences/platforms-domestic.mddoc · 2,008 bytesreferences/platforms-overseas.mddoc · 2,111 bytesreferences/report-spec.mddoc · 4,212 bytesscripts/agent_reach_import.pyruns · 8,426 bytesscripts/analyze.pyruns · 10,846 bytesscripts/build_report.pyruns · 4,342 bytesscripts/collect.pyruns · 5,587 bytesscripts/common.pyruns · 1,346 bytesscripts/doctor.pyruns · 3,146 bytesscripts/lexicons.pyruns · 5,006 bytesscripts/normalize.pyruns · 10,441 bytesscripts/tikhub.pyruns · 1,681 bytes
Read excerpt
# 竞品红人投放雷达
用一套固定口径，把"某品牌在社媒上被谁、以什么方式、讲了什么、导向哪里买"拆清楚，并以营销总监能直接拿去开会的方式交付。
价值不在抓数据，在**口径和判断**：分清付费、寄样、联盟和自来水，剔除噪音，知道哪些数字不能信。这些规则写在 `references/` 里，先读再动手。
## 0. 立项：先定决策问题
动手前用一两句话确认（用户已经说清的就不要再问）：
- **品牌和别名**（含中文名、各国写法、产品线名）
- **市场**：海外（默认）/ 国内（小红书，实验）/ 内外对比
- **时间窗**：默认近 90 天
- **这份调研要支撑什么决策**：对标学习、进入新市场、定预算、找可复制打法、做内容选题……决策问题决定报告的"建议动作"往哪写。用户没说就默认"我们能借鉴什么"。