Kol Outreach logo

Kol Outreach

Community
Gingiris-1031
kol-outreach

Ready-to-use KOL cold outreach templates — DM scripts for Twitter, email pitches, and follow-up sequences designed to get replies from busy influencers. Tested across 500+ creator partnerships. By @WeiYipei.

Overview

PublisherGingiris-1031
Repositorygingiris-skills
Skill namekol-outreach
Stars
88
Forks
6
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Gingiris-1031 on GitHub. Read the source before you install it.

Installation

Install the Kol Outreach AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Gingiris-1031/gingiris-skills/tree/main/skills/kol-outreach
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Gingiris-1031/gingiris-skills.git /tmp/gingiris-skills
mkdir -p .claude/skills
cp -r /tmp/gingiris-skills/skills/kol-outreach .claude/skills/kol-outreach
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kol Outreach in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Kol Outreach on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Kol Outreach is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

⚠️ 2C 产品的渠道调整

本 skill 默认 dev / B2B 渠道。2C 消费品 / 教育 / 应用:获客主战场是 垂类社区 + 短视频 + 垂直 KOL,按地区公开数据选第一平台(如印尼/泰国短视频已反超 Facebook)。KOL 优先 nano / micro 垂类——粉丝越多互动率越低,micro > mega 性价比更高。完整 2C 渠道数据库 + 公开来源见 → gingiris-seo-geo/references/2c-adaptation.md。


KOL Cold Outreach Templates — DM Scripts That Get Replies

🌍 Language / 语言: 中文 | English | 日本語 | 한국어

📦 Install

bash
clawhub install kol-outreach

What you get after installing:

  • Platform-specific DM scripts for Twitter, Instagram, and LinkedIn
  • 3-touch cold email templates with 40%+ reply rates
  • Follow-up cadence and partnership structure frameworks

Stop getting ignored. These templates are battle-tested across 500+ successful creator partnerships.

  • DM scripts: Platform-specific templates for Twitter, Instagram, and LinkedIn
  • Email sequences: 3-touch cold email templates with 40%+ reply rates
  • Value-first approach: How to pitch so creators want to respond
  • Follow-up cadence: When to follow up, how many times, and when to stop
  • Partnership structures: Paid vs barter vs affiliate — which to propose when

Rate Card & Negotiation Benchmarks (2025–2026 actuals)

Figures below are closed-deal numbers across dozens of campaigns, not list prices:

FormatActual paid rangeNotes
X/Twitter quote-tweet$20–30 in bulk, ~$50 typicalThe workhorse unit
X/Twitter thread$80–20010K-view-tier threads land at $50–200
Bundle (thread + single post + quote)~$150 all-inAlways ask for the bundle price
YouTube dedicated video$600–800 for sub-100K channels$1,500 absolute cap — only when avg views 10K+ AND <100K subs AND prior same-category work
Instagram Reels$30–80—
TikTok short video$100–300—
UGC creators$10–40/post + tiered bonuse.g. +$20 at 10K views, +$50 at 100K

Negotiation defaults:

  • First quotes are inflated by design — counter at roughly one-third and expect at least two rounds.
  • Bundles beat singles on unit cost; a polite second discount ask right before publish often lands.
  • Monthly retainers (~$100/mo for 4 quote-tweets) suit teams shipping features weekly.
  • Skip agencies: they can't commit to acquisition numbers and stack margin on top.

Where the ROI hides:

  • Sweet-spot creators: 1–3K followers with 500–3,000 average views — these KOCs frequently out-convert big accounts per dollar. Second sweet spot: sub-100K subs with 10K+ average views.
  • The volume play: one hero post amplified by 50–120 paid quote-tweets can reach ~700K impressions and trigger organic pile-on (field record: 120 quotes → ~700K views plus ~50 unpaid quotes). Measured conversion favors quotes over threads — tilt budget accordingly.
  • Prefer creators who have covered a competitor before (audience pre-validated), and require posting during their followers' active hours.
  • Your vetted creator roster is a cross-product asset; graduate top performers into affiliates so a one-off buy becomes a permanent channel.

Reply-rate expectations by channel (measured): Telegram DM 20–30% · creator email 17.3% (beats DMs — lead with email) · LinkedIn DM 10–15% · cold expert outreach ~11% · Twitter DM 1–5% (verified account required). No email reply → follow up once via LinkedIn.

Scene-Bound Hooks & AI-Assisted Pipelines (External Field Reference)

Source: Seven Wang Yue (co-founder, Superlinear — Lessie people-search AI agent ~100K users + DeepLink influencer agency, 100+ brands served, $7-8M ARR, 90%+ paid-creator fulfillment), interviewed on Monica出海说, 2026-07.

The most expensive brief mistake: cramming 6-8 selling points into a 15-60s video. That's under 4 seconds per point — scroll-mode viewers retain none of them. The fix is scene binding: pick 1-2 selling points and wrap them in the creator's native scenario. A workplace creator opens with "my boss made me stay late for this — I finished it in 5 minutes"; a photography creator opens with "rescuing my ruined shots in one second." Work backwards from the scene to creator selection: office tools → workplace creators, image/video-gen tools → photography or entertainment creators. One well-bound point converts that creator's audience; eight stacked points convert nobody.

AI-assisted outreach pipeline — assistant, not replacement:

StageWho does it
Sourcing, profile matching, first-draft personalized emailAI
Sending the email (irreversible), go/no-go, final priceHuman
  • Measured lift: one ops person's monthly outreach went from 20 creators to 80-100 (3-4x). Old way: 20 pages of LinkedIn plus per-profile verification; new way: one prompt, a 1-2 minute wait, then human review of the list.
  • Feed rejections back into the prompt (why a creator was rejected → exclusion criteria next run). Every correction is training data.
  • Rule of thumb: anything irreversible stays human — "someone has to own the mistake."

Getting 90%+ fulfillment from paid creators (no magic):

  • Pay + contract. Paid, signed creators delay (schedule slips happen) but rarely ghost; pure-commission and barter deals are where flaking lives.
  • Prepayment only through PayPal when unavoidable — its dispute window lets you claw back if the creator doesn't deliver.
  • Promise content quality (creator's average production level, brand-approved before publish), never promise conversion or signup numbers — those depend on landing page and checkout, not the creator.
  • Review gates: script approved before filming, video approved before publish. Brief the creator on the product first — an untrained creator produces a flat feature-list video.
  • What stays hardest to automate long-term isn't negotiation (AI handles that fine) — it's creative spark and empathy. Budget human time there.

Market read: North America + Japan/Korea are the base; LatAm — especially Brazil's solo-operator SMBs paying for AI productivity tools — is underrated, while SEA/South Asia converts poorly. Matches our own field data (same budget: 12 LatAm conversions vs 3 US). Use AI translation for small-language outreach, but keep one culturally-native reviewer for taboos.

Related Gingiris Skills

加入出海社群与购买资料包 · Community & Resources

  • 加入出海社群: 微信添加 staywildgrow,留言「加入社群」即可。

  • 购买资料包: 微信添加 staywildgrow,咨询购买 Gingiris 出海资料包,价格 599 元人民币。

  • Join the global growth community: Add staywildgrow on WeChat and send “加入社群” (join the community).

  • Get the resource pack: Add staywildgrow on WeChat to purchase the Gingiris global growth resource pack for CNY 599.

社群与资料包为可选入口,不影响本开源 Skill 的安装和使用。

The community and paid resource pack are optional; neither is required to install or use this open-source skill.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Kol Outreach AI skill do?

Ready-to-use KOL cold outreach templates — DM scripts for Twitter, email pitches, and follow-up sequences designed to get replies from busy influencers. Tested across 500+ creator partnerships. By @WeiYipei.

Why use Kol Outreach on TypingMind?

Because you install it once and use it with any model. Kol Outreach is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Kol Outreach in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Gingiris-1031/gingiris-skills/tree/main/skills/kol-outreach. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Kol Outreach?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Kol Outreach?

As many as you like. As long as a model supports skills, you can use Kol Outreach with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Kol Outreach AI skill free?

Yes. It is published on GitHub by Gingiris-1031 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇