跳到正文
cccskills
免费在 GitHub 公开

campaign-brief-generator

Generate a complete marketing campaign brief from a launch goal, ICP, and product context. Pure reasoning skill. Outputs channel plan, messaging angles, content types, timeline, and success metrics. Designed for seed/Series A founders and small GTM teams who aren't professional marketers but need to run focused campaigns. No scripts — pure reasoning.

中文简介正在准备中。当前显示原文说明。

集成工具SlackLinkedIn

实测评分 未实测

查看安装方法

包含的文件(2)

  • SKILL.md7.8 KB
  • skill.meta.json268 B

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Campaign Brief Generator

Pure reasoning skill. Takes a campaign goal, ICP, and product context — and produces a complete, actionable campaign brief a small team can actually execute.

Built for: Founders doing their own marketing. First marketing hires. GTM teams without a dedicated strategist. The output should be opinionated and specific, not a generic template.

When to Use

  • "Help me plan a campaign for [launch / feature / segment]"
  • "We're targeting [ICP], what channels and content should we run?"
  • "I need a 30-day campaign plan"
  • "We're launching [product/feature] — help me plan the GTM"
  • "Write me a campaign brief for [goal]"

Phase 0: Intake

Ask all questions in one go, grouped cleanly. This is a fast skill — don't make it feel like a form.

Campaign Context

  1. Goal — What does success look like in 30/60/90 days? (e.g., "50 signups from developer audience", "10 demos booked with Series B startups", "3 media mentions")
  2. Trigger — What's prompting this campaign? (product launch, new feature, new segment, funding, competitive threat, slow quarter)
  3. Timeline — How long should the campaign run? When should it start?

Audience

  1. ICP — Who exactly are you targeting? (Title, company type, stage, geography)
  2. Where do they hang out? — Channels they actively use (LinkedIn, Slack communities, specific newsletters, Twitter/X, etc.)
  3. What's their current pain? — The specific problem your product solves for them right now

Product & Positioning

  1. What are you promoting? — Specific product, feature, or offer (free trial, case study, webinar, etc.)
  2. Core value prop — In one sentence: what do you do and why does it matter?
  3. Social proof available — Customer logos, case study metrics, review quotes, press mentions
  4. What are you NOT — Key competitor or alternative you want to differentiate from

Constraints

  1. Team size — Who's executing this? (founder only, 1 marketer, SDR+marketing, etc.)
  2. Budget — Rough range for paid/sponsored channels (or "zero — organic only")
  3. Existing assets — What do you already have? (blog posts, case studies, demo video, email list)

Phase 1: Channel Strategy

Based on intake answers, recommend 2-4 primary channels. For seed/Series A, resist suggesting more than 4 — execution quality beats channel breadth.

Channel Selection Criteria

ChannelBest ForMinimum Resource
Founder LinkedInThought leadership, top-of-funnel awareness3 posts/week, 30 min/day
Cold email (outbound)Direct pipeline from ICP listSDR or founder time + Smartlead
LinkedIn adsTargeted awareness with limited list$1,000+/month budget
Community engagementSlack/Discord communities where ICP is active1 hour/day, no budget
Content SEOLong-term inbound, compounding2 posts/week, 2-3 month horizon
Newsletter sponsorshipReaching existing engaged audiences$500-5,000/newsletter
Product HuntDeveloper/startup audience, launch moment2 weeks prep, launch day hustle
Event/conferenceHigh-intent networking, deal accelerationAttendance + budget
Partner co-marketingShared audiences, low-cost reachPartnership agreement

For each recommended channel, specify:

  • Primary role: Awareness / Consideration / Conversion
  • Expected output: What does success look like on this channel?
  • Estimated effort: Hours per week + budget
  • Who owns it: Which team member

Phase 2: Messaging Architecture

Define 3 core messages for the campaign — the angles you'll repeat across channels.

Message Structure

For each core message:

Message: [1-sentence core claim]
Evidence: [proof point — metric, case study, quote]
For: [which ICP segment this resonates with most]
Channel fit: [best channel(s) to deploy this message]

Messaging Hierarchy

LevelMessageExample
Primary (use everywhere)Core positioning statement"The only [category] built for [ICP]"
Secondary A (proof-driven)Customer outcome story"[Customer] 3x'd pipeline in 30 days"
Secondary B (contrast)Differentiation from status quo"Unlike [category], we [differentiator]"

Phase 3: Content Plan

Map specific content pieces to the channel plan. Be concrete — give working titles, not just "write some blog posts."

Content Calendar Format

WeekChannelContent PieceFormatOwnerGoal
Week 1LinkedIn"[Working Title]"Insight postFounder500 impressions
Week 1Cold emailLaunch sequence (Touch 1)EmailSDR20 demos booked
Week 2LinkedIn"[Working Title]"Case study postMarketing200+ reactions
Week 2Blog"[Working Title]"How-to postMarketing50 organic visits
...

Content types for seed/Series A (in order of leverage):

  1. Founder insight post (LinkedIn) — personal brand + thought leadership
  2. Customer story/result (any channel) — social proof
  3. Contrarian take / hot take — engagement bait
  4. How-to / tactical guide — ICP utility value
  5. Launch announcement — news peg for outreach

Phase 4: Success Metrics

Define KPIs before the campaign starts. Split by phase:

MetricTargetHow to Measure
Awareness[N] LinkedIn impressionsLinkedIn Analytics
Consideration[N] profile visits / email opensLinkedIn, Smartlead
Conversion[N] signups / demos / repliesCRM / product analytics
Quality[N%] ICP match on conversionsManual tagging

North star for this campaign: [single most important metric]

Phase 5: Output Format

# Campaign Brief — [Campaign Name]
Created: [DATE] | Owner: [Name]

## Goal
[1-sentence goal with number and timeline]

## ICP Target
[2-3 sentences: who, what pain, why now]

## Timeline
Start: [date] | End: [date] | Review: [midpoint date]

---

## Channel Strategy

### Channel 1: [Name]
- Role: [Awareness/Consideration/Conversion]
- Effort: [hours/week + budget]
- Owner: [person]
- Success metric: [what good looks like]

### Channel 2: [Name]
...

---

## Core Messages

### Primary
> "[message]"
Evidence: [proof]

### Secondary A
> "[message]"
Evidence: [proof]

### Secondary B
> "[message]"
Evidence: [proof]

---

## Content Calendar (Weeks 1-4)

| Week | Channel | Content | Format | Owner |
|------|---------|---------|--------|-------|
...

---

## Success Metrics

| Metric | Target | Owner |
|--------|--------|-------|
...

**North star:** [metric]

---

## What We're NOT Doing
(Scope constraints to prevent scope creep)
- Not running [channel] — not enough budget/time
- Not targeting [segment] — outside ICP for this campaign
- Not launching [content type] — need [prerequisite] first

---

## Assets Needed Before Launch
- [ ] [Asset 1] — Owner: [name] — Due: [date]
- [ ] [Asset 2] — ...

Save to the current working directory or wherever the user prefers.

Tools Required

None. Pure reasoning. Works with any LLM agent.

Trigger Phrases

  • "Write a campaign brief for [launch/goal]"
  • "Help me plan a campaign targeting [ICP]"
  • "We're launching [thing] — give me a campaign plan"
  • "I have [N] weeks and [budget] — what campaign should I run?"

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Research supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.

中文简介正在准备中。当前显示原文说明。

gooseworks-ai/goose-skills12652026年10月24日 更新

Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.

中文简介正在准备中。当前显示原文说明。

gooseworks-ai/goose-skills12652026年10月24日 更新

For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.

中文简介正在准备中。当前显示原文说明。

gooseworks-ai/goose-skills12652026年10月24日 更新

The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.

中文简介正在准备中。当前显示原文说明。

gooseworks-ai/goose-skills12652026年10月24日 更新

Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the copy, on-image or on-screen text, pictures and people. Rewrites what can be fixed honestly, adds the disclosures that are needed, and flags anything that needs a human or legal review, with one pass, fixed or flag line per ad and platform. Use alone when you already have the ad text or images and know where they will run; otherwise run the playbook for the job (e.g. make-static-ads, make-content, email-lifecycle).

中文简介正在准备中。当前显示原文说明。

gooseworks-ai/goose-skills12652026年10月24日 更新

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

中文简介正在准备中。当前显示原文说明。

gooseworks-ai/goose-skills12652026年10月24日 更新

查看 gooseworks-ai 的全部技能

报告此技能的问题