Not in the top 1,000 by GitHub stars

waynefu2020/competitor-kol-radar

红人投放雷达— 站在营销总监的角度拆解竞品在 TikTok / Instagram / YouTube / 小红书上的红人营销打法。分析博主量级、播放、选题卖点、转化渠道，输出带建议网页报告。

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Network or broad shell → After Network or broad shell

b4bf30cb9c81 → b4bf30cb9c81

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → b4bf30cb9c81

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit b4bf30cb9c81ae073e17898f874b97350be45109

7GitHub stars

0stars in 7 days

1skill in this repository

4commits in 30 days

Heat

1.4

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

competitor-kol-radar /

How it works

competitor-kol-radar

When your agent uses it

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。

What it loads into context

Frontmatter

261 tokens

Always available to the agent

SKILL.md

2,278 tokens

When the skill is activated

Reference documents

9,249 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

0. 立项：先定决策问题
1. 写 brief
2. 成本预估 → 采集
3. 抽查（不可跳过）
4. 渠道与规模研究
5. 分析
6. 写结论（总监视角）
7. 出报告
8. 更新对标库
国内市场（实验）
参考文件

Scripts executed separately

scripts/agent_reach_import.py
scripts/analyze.py
scripts/build_report.py
scripts/collect.py
scripts/common.py
scripts/doctor.py
scripts/lexicons.py
scripts/normalize.py
scripts/tikhub.py

Files

.gitignoreasset92 bytes
INSTALL.mddoc2,599 bytes
LICENSEasset1,068 bytes
README.mddoc8,210 bytes
SKILL.mdcore7,872 bytes
SKILL.mdcore7,872 bytes
SKILL.mdcore7,872 bytes
SKILL.mdcore7,872 bytes
assets/brief.example.jsonasset1,127 bytes
assets/report_template.htmlasset44,689 bytes
docs/styles/brand.pngasset472,493 bytes
docs/styles/consulting.pngasset333,498 bytes
docs/styles/notebook.pngasset381,534 bytes
docs/styles/terminal.pngasset402,752 bytes
docs/styles/wrapped.pngasset351,995 bytes
examples/flowerknows/brief.jsonasset1,441 bytes
examples/flowerknows/narrative.jsonasset6,841 bytes
references/benchmarks.jsonasset815 bytes
references/channel-signals.mddoc1,917 bytes
references/fallback-agent-reach.mddoc3,611 bytes
references/methodology.mddoc3,897 bytes
references/pitfalls.mddoc2,984 bytes
references/platforms-domestic.mddoc2,008 bytes
references/platforms-overseas.mddoc2,111 bytes
references/report-spec.mddoc4,212 bytes
scripts/agent_reach_import.pyruns8,426 bytes
scripts/analyze.pyruns10,846 bytes
scripts/build_report.pyruns4,342 bytes
scripts/collect.pyruns5,587 bytes
scripts/common.pyruns1,346 bytes
scripts/doctor.pyruns3,146 bytes
scripts/lexicons.pyruns5,006 bytes
scripts/normalize.pyruns10,441 bytes
scripts/tikhub.pyruns1,681 bytes

Read SKILL.md


# 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"。

View the complete source on GitHub

Skills included

competitor-kol-radar

Repository facts

License: MIT
Created: Oct 26, 2026
Last pushed: Oct 26, 2026
Forks: 0
Open issues: 0
Project activity: Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 3 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
58 network referencesin 12 files: scripts/agent_reach_import.py:66 examples/flowerknows/narrative.json:119 scripts/normalize.py:126 and 9 more
No hidden or obfuscated text
No instruction overrides
9 executable scriptsin 9 files: scripts/agent_reach_import.py:1 scripts/analyze.py:1 scripts/build_report.py:1 and 6 more
14 references to secretsin 7 files: scripts/agent_reach_import.py:4 scripts/tikhub.py:12 references/fallback-agent-reach.md:9 and 4 more
No requests to vote in Hot

Show all 81 signals by file

`.gitignore`

Access to secretsline 4
```
[Credential-related source omitted]
```

`INSTALL.md`

Network accessline 14

DEST=~/.claude/skills/competitor-kol-radar   # 按上表换成你的目录 if [ -d "$DEST/.git" ]; then git -C "$DEST" pull --ff-only; else git clone https://github.com/waynefu2020/competitor-kol-radar.git "$DEST"; fi

Network accessline 15

if [ -d "$DEST/.git" ]; then git -C "$DEST" pull --ff-only; else git clone https://github.com/waynefu2020/competitor-kol-radar.git "$DEST"; fi

Network accessline 21

mkdir -p "$DEST" && curl -L https://github.com/waynefu2020/competitor-kol-radar/archive/refs/heads/main.tar.gz | tar -xz --strip-components=1 -C "$DEST"

Network accessline 38

- 数据来自 TikHub，注册地址 https://tikhub.io ，一次海外竞品调研大约花 $0.5–1。

`README.md`

Network accessline 76

帮我安装这个 Skill：https://github.com/waynefu2020/competitor-kol-radar

Network accessline 82

- **有 Key**：直接发给它，它会帮你安全保存。到 [tikhub.io](https://tikhub.io) 注册就能拿到，一次海外调研大约 $0.5–1。

Network accessline 101

git clone https://github.com/waynefu2020/competitor-kol-radar.git ~/.claude/skills/competitor-kol-radar

Access to secretsline 106
```
[Credential-related source omitted]
```

Network accessline 112

用 [Agent Reach](https://github.com/Panniantong/Agent-Reach) 的免费工具链（yt-dlp、xhs-cli、网页搜索）：

`SKILL.md`

Access to secretsline 30
```
[Credential-related source omitted]
```

`assets/report_template.html`

Network accessline 2

<meta name="claude:viewport-fit-sides" content="cover"> <script>document.documentElement.dataset.style = "__STYLE__";</script> <link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 3

<script>document.documentElement.dataset.style = "__STYLE__";</script> <link rel="preconnect" href="https://fonts.googleapis.com"> <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

Network accessline 4

<link rel="preconnect" href="https://fonts.googleapis.com">

Network accessline 5

<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>

`examples/flowerknows/narrative.json`

Network accessline 119

{       "title": "Beauty Independent",       "url": "https://www.beautyindependent.com/flower-knows-brings-fairytale-aesthetic-ulta-beauty-c-beauty-gains-ground/"

Network accessline 120

"title": "Beauty Independent",       "url": "https://www.beautyindependent.com/flower-knows-brings-fairytale-aesthetic-ulta-beauty-c-beauty-gains-ground/"     },

Network accessline 121

"url": "https://www.beautyindependent.com/flower-knows-brings-fairytale-aesthetic-ulta-beauty-c-beauty-gains-ground/"

Network accessline 123

{       "title": "PRNewswire / StreetInsider",       "url": "https://www.streetinsider.com/PRNewswire/Flower+Knows+Expands+U.S.+Retail+Distribution+By+Entering+Ulta+Beauty/25715380.html"

Network accessline 124

"title": "PRNewswire / StreetInsider",       "url": "https://www.streetinsider.com/PRNewswire/Flower+Knows+Expands+U.S.+Retail+Distribution+By+Entering+Ulta+Beauty/25715380.html"     },

Network accessline 125

"url": "https://www.streetinsider.com/PRNewswire/Flower+Knows+Expands+U.S.+Retail+Distribution+By+Entering+Ulta+Beauty/25715380.html"

Network accessline 127

{       "title": "界面新闻",       "url": "https://www.jiemian.com/article/13288116.html"

Network accessline 128

"title": "界面新闻",       "url": "https://www.jiemian.com/article/13288116.html"     }

Network accessline 129

"url": "https://www.jiemian.com/article/13288116.html"

`references/fallback-agent-reach.md`

Network accessline 3

[Agent Reach](https://github.com/Panniantong/Agent-Reach) 是一组免费的命令行和 MCP 工具（yt-dlp、xhs-cli、Exa 搜索、Jina 网页阅读等）。没有 TikHub Key 时用它兜底，能出报告，但**数据完整度明显更低**，报告里必须写清楚。

Access to secretsline 9
```
[Credential-related source omitted]
```
Access to secretsline 34
```
[Credential-related source omitted]
```

`references/platforms-overseas.md`

Network accessline 3
```
[Credential-related source omitted]
```

`references/report-spec.md`

Network accessline 44

{"type": "照搬", "title": "把包装做成值得拍的东西", "detail": "……", "priority": "高", "budget": "中", "measure": "UGC 中'包装/开箱'主题占比；3 个月"}   ],   "sources": [{"title": "Beauty Independent", "url": "https://..."}],

Network accessline 45

],   "sources": [{"title": "Beauty Independent", "url": "https://..."}],   "method_notes": ["TikTok 商业标记字段含义为样本推断。"]

Network accessline 46

"sources": [{"title": "Beauty Independent", "url": "https://..."}],

`scripts/agent_reach_import.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 4
```
[Credential-related source omitted]
```

Network accessline 66

rows = []     for q in queries:         url = 'https://www.youtube.com/results?' + urllib.parse.urlencode({'search_query': q, 'sp': 'CAI='})

Network accessline 67

for q in queries:         url = 'https://www.youtube.com/results?' + urllib.parse.urlencode({'search_query': q, 'sp': 'CAI='})         out, err = run(['yt-dlp', '--no-update', '--flat-playlist', '--playlist-end', str(20 * pages), '-J', url]

Network accessline 68

url = 'https://www.youtube.com/results?' + urllib.parse.urlencode({'search_query': q, 'sp': 'CAI='})

Network accessline 77

views=e.get('view_count'), likes=None, comments=None, ts=None, ts_unknown=True,                        text=(e.get('title') or '') + ' ' + (e.get('description') or ''), title=e.get('title'),                        url=f"https://youtu.be/{e.

Network accessline 78

text=(e.get('title') or '') + ' ' + (e.get('description') or ''), title=e.get('title'),                        url=f"https://youtu.be/{e.get('id')}", paidflag=False, shop=False, disclosed=False, source='agent-reach:yt-dlp')             if b

Network accessline 79

url=f"https://youtu.be/{e.get('id')}", paidflag=False, shop=False, disclosed=False, source='agent-reach:yt-dlp')             if browser:                 d_out, _ = run(['yt-dlp', '--no-update', '-j', '--skip-download', '--cookies-from-brows

Access to secretsline 81
```
[Credential-related source omitted]
```

Network accessline 120

break                 for it in items:                     nc = it.get('note_card') or {}

Network accessline 121

for it in items:                     nc = it.get('note_card') or {}                     if not nc:

Network accessline 122
```
nc = it.get('note_card') or {}
```

Network accessline 130

comments=cn_num(ii.get('comment_count')), ts=ts, ts_unknown=ts is None, text=nc.get('display_title') or '',                                      title=nc.get('display_title'), note_type=nc.get('type'),                                      u

Network accessline 131
```
[Credential-related source omitted]
```
Network accessline 132
```
[Credential-related source omitted]
```
Access to secretsline 145
```
[Credential-related source omitted]
```
Access to secretsline 152
```
[Credential-related source omitted]
```

`scripts/analyze.py`

Executable scriptline 1
```
Executable file
```

`scripts/build_report.py`

Executable scriptline 1
```
Executable file
```

Network accessline 14

REQUIRED = ['verdict', 'summary', 'actions'] GF = 'https://fonts.googleapis.com/css2?'

Network accessline 15

GF = 'https://fonts.googleapis.com/css2?'

`scripts/collect.py`

Executable scriptline 1
```
Executable file
```

`scripts/common.py`

Executable scriptline 1
```
Executable file
```

`scripts/doctor.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 52
```
[Credential-related source omitted]
```

Network accessline 59

else:             ok = False             print(f'❌ TikHub Key 无法使用（{err}）。到 https://tikhub.io 后台确认 Key 是否正确、是否过期，再重新保存。')

Network accessline 60

ok = False             print(f'❌ TikHub Key 无法使用（{err}）。到 https://tikhub.io 后台确认 Key 是否正确、是否过期，再重新保存。')     else:

Network accessline 61

print(f'❌ TikHub Key 无法使用（{err}）。到 https://tikhub.io 后台确认 Key 是否正确、是否过期，再重新保存。')

Network accessline 62

else:         print('⚠<U+FE0F>  没有 TikHub Key：可以先用免费兜底方案（数据少一些），或到 https://tikhub.io 注册拿 Key，'               '然后把 Key 发给 Agent 保存。')

Network accessline 63

print('⚠<U+FE0F>  没有 TikHub Key：可以先用免费兜底方案（数据少一些），或到 https://tikhub.io 注册拿 Key，'

`scripts/lexicons.py`

Executable scriptline 1
```
Executable file
```

`scripts/normalize.py`

Executable scriptline 1
```
Executable file
```

Network accessline 126

views=st.get('play_count'), likes=st.get('digg_count'), comments=st.get('comment_count'), ts=x.get('create_time'),                      text=(x.get('desc') or '') + ' ' + tags, region=x.get('region'),                      url=f"https://www.

Network accessline 127

text=(x.get('desc') or '') + ' ' + tags, region=x.get('region'),                      url=f"https://www.tiktok.com/@{au.get('unique_id')}/video/{x.get('aweme_id')}",                      paidflag=bool(x.get('is_ads')), shop=shop, disclosed=

Network accessline 128

url=f"https://www.tiktok.com/@{au.get('unique_id')}/video/{x.get('aweme_id')}",

Network accessline 134

followers=None, views=it.get('play_count') or it.get('ig_play_count') or it.get('view_count'),                      likes=it.get('like_count'), comments=it.get('comment_count'), ts=it.get('taken_at'),                      text=(it.get('capt

Network accessline 135

likes=it.get('like_count'), comments=it.get('comment_count'), ts=it.get('taken_at'),                      text=(it.get('caption') or {}).get('text') or '', url=f"https://www.instagram.com/p/{it.get('code')}/",                      paidflag=

Network accessline 136

text=(it.get('caption') or {}).get('text') or '', url=f"https://www.instagram.com/p/{it.get('code')}/",

Network accessline 162

ts=int(datetime.datetime.fromisoformat(d['publish_date']).timestamp()),                  text=(d.get('title') or '') + ' ' + desc, clstext=(d.get('title') or '') + '\n' + rel,                  url=f'https://youtu.be/{vid}', paidflag=False,

Network accessline 164

url=f'https://youtu.be/{vid}', paidflag=False, shop=False, disclosed=False, title=d.get('title')))

`scripts/tikhub.py`

Executable scriptline 1
```
Executable file
```
Network accessline 8
```
BASE = 'https://api.tikhub.io'
```
Access to secretsline 12
```
[Credential-related source omitted]
```
Access to secretsline 13
```
[Credential-related source omitted]
```
Access to secretsline 19
```
[Credential-related source omitted]
```
Network accessline 27
```
[Credential-related source omitted]
```
Access to secretsline 27
```
[Credential-related source omitted]
```

Network accessline 30

for attempt in range(retries):         try:             with urllib.request.urlopen(req, timeout=90) as r:

Network accessline 31

try:             with urllib.request.urlopen(req, timeout=90) as r:                 return json.load(r)

Network accessline 32

with urllib.request.urlopen(req, timeout=90) as r:

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 7 facts

Contacts www.youtube.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/agent_reach_import.py:68High confidence
Contacts youtu.be, which SKILL.md, the README and the plugin manifest do not mentionscripts/agent_reach_import.py:79High confidence
Contacts www.xiaohongshu.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/agent_reach_import.py:132High confidence
Contacts fonts.googleapis.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/build_report.py:15High confidence
Contacts www.tiktok.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/normalize.py:128High confidence
Contacts www.instagram.com, which SKILL.md, the README and the plugin manifest do not mentionscripts/normalize.py:136High confidence
Contacts youtu.be, which SKILL.md, the README and the plugin manifest do not mentionscripts/normalize.py:164High confidence

Signal confidence: 67 facts

Network access in code of documentationINSTALL.md:14Low confidence
Network access in code of documentationINSTALL.md:15Low confidence
Network access in code of documentationINSTALL.md:21Low confidence
Network access in prose of documentationINSTALL.md:38Low confidence
Network access in code of documentationREADME.md:76Low confidence
Network access in prose of documentationREADME.md:82Low confidence
Network access in code of documentationREADME.md:101Low confidence
Access to secrets in prose of documentationREADME.md:106Low confidence
Network access in prose of documentationREADME.md:112Low confidence
Access to secrets in prose of the SKILL.mdSKILL.md:30Low confidence
Network access in prose of documentationreferences/fallback-agent-reach.md:3Low confidence
Access to secrets in prose of documentationreferences/fallback-agent-reach.md:9Low confidence
Access to secrets in code of documentationreferences/fallback-agent-reach.md:34Low confidence
Network access in prose of documentationreferences/platforms-overseas.md:3Low confidence
Network access in code of documentationreferences/report-spec.md:44Low confidence
Network access in code of documentationreferences/report-spec.md:45Low confidence
Network access in code of documentationreferences/report-spec.md:46Low confidence
Executable script in prose of a file that runsscripts/agent_reach_import.py:1Low confidence
Access to secrets in prose of a file that runs: a variable, placeholder or call, not a stored valuescripts/agent_reach_import.py:4Low confidence
Network access in code of a file that runsscripts/agent_reach_import.py:66High confidence
Network access in code of a file that runsscripts/agent_reach_import.py:67High confidence
Network access in code of a file that runsscripts/agent_reach_import.py:68High confidence
Network access in code of a file that runsscripts/agent_reach_import.py:77High confidence
Network access in code of a file that runsscripts/agent_reach_import.py:78High confidence
Network access in code of a file that runsscripts/agent_reach_import.py:79High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/agent_reach_import.py:81Low confidence
Network access in code of a file that runsscripts/agent_reach_import.py:120High confidence
Network access in code of a file that runsscripts/agent_reach_import.py:121High confidence
Network access in code of a file that runsscripts/agent_reach_import.py:122High confidence
Network access in code of a file that runsscripts/agent_reach_import.py:130High confidence
Network access in code of a file that runsscripts/agent_reach_import.py:131High confidence
Network access in code of a file that runsscripts/agent_reach_import.py:132High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/agent_reach_import.py:145Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/agent_reach_import.py:152Low confidence
Executable script in prose of a file that runsscripts/analyze.py:1Low confidence
Executable script in prose of a file that runsscripts/build_report.py:1Low confidence
Network access in code of a file that runsscripts/build_report.py:14High confidence
Network access in code of a file that runsscripts/build_report.py:15High confidence
Executable script in prose of a file that runsscripts/collect.py:1Low confidence
Executable script in code of a file that runsscripts/common.py:1High confidence
Executable script in prose of a file that runsscripts/doctor.py:1Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuescripts/doctor.py:52Low confidence
Network access in code of a file that runsscripts/doctor.py:59High confidence
Network access in code of a file that runsscripts/doctor.py:60High confidence
Network access in code of a file that runsscripts/doctor.py:61High confidence
Network access in code of a file that runsscripts/doctor.py:62High confidence
Network access in code of a file that runsscripts/doctor.py:63High confidence
Executable script in prose of a file that runsscripts/lexicons.py:1Low confidence
Executable script in prose of a file that runsscripts/normalize.py:1Low confidence
Network access in code of a file that runsscripts/normalize.py:126High confidence

and 17 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

waynefu2020/competitor-kol-radar

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

competitor-kol-radar

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

.gitignore

INSTALL.md

README.md

SKILL.md

assets/report_template.html

examples/flowerknows/narrative.json

references/fallback-agent-reach.md

references/platforms-overseas.md

references/report-spec.md

scripts/agent_reach_import.py

scripts/analyze.py

scripts/build_report.py

scripts/collect.py

scripts/common.py

scripts/doctor.py

scripts/lexicons.py

scripts/normalize.py

scripts/tikhub.py

How the signals fit together

Works with

You might also use

smixs/creative-director-skill

ScrapeCreators/social-media-research-skills

aaron-he-zhu/aaron-marketing-skills

fseixas/chatgpt-ads-builder

op7418/guizang-social-card-skill

feitangyuan/onetake

`SKILL.md`

`.gitignore`

`INSTALL.md`

`README.md`

`SKILL.md`

`assets/report_template.html`

`examples/flowerknows/narrative.json`

`references/fallback-agent-reach.md`

`references/platforms-overseas.md`

`references/report-spec.md`

`scripts/agent_reach_import.py`

`scripts/analyze.py`

`scripts/build_report.py`

`scripts/collect.py`

`scripts/common.py`

`scripts/doctor.py`

`scripts/lexicons.py`

`scripts/normalize.py`

`scripts/tikhub.py`