agentleFS
minhnv0807minhnv0807/fullstack-mkt-skills/skills/en/02-campaign-brief-global/SKILL.md

02-campaign-brief-global

Skill644 starsChanged 6 months agoMITView on GitHub

Use when a specific campaign needs a brief the whole team can execute from — context, objective, audience, core message, creative direction, channels, deliverables, week-by-week timeline, approval gates, and risks. Trigger on 'campaign brief', 'creative brief', 'launch brief', 'brief the team on this campaign', 'we are running a promo next month', 'what is the plan for this campaign'. Also use when the user describes a promotion out loud and asks for something the team can actually run. Not for — the whole period plan, see `00-marketing-plan-global`; the list of design files needed, see `41-campaign-asset-list-global`; assigning work to one person, see `64-team-brief-global`; a new product launch sequence, see `59-go-to-market-global`.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Before writing the brief, read .agents/product-marketing-context-global.md to load:

    line 30
  2. Very specific:

    If the file is missing, ask the user to run product-marketing-context-global first.

    line 37
  3. Distinctive:

    Ask the user up to 4 questions before starting:

    line 43
  4. Distinctive:

    Verify the insight is actually an insight and not just an observation:

    line 131
  5. Distinctive:

    Rule: Must pass at least 4 / 5. Otherwise it is an observation, not an insight.

    line 141
  6. Distinctive:

    Before delivering the brief, verify:

    line 373

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Global Campaign Brief

9-section creative brief: Context, Objectives, Target, Core Message, Creative Direction, Channel System, Timeline, Deliverables, Risks. Auto-triggers downstream skills (script, calendar, ad copy, UGC brief).


Step 0 — Read context file

Before writing the brief, read .agents/product-marketing-context-global.md to load:

  • Product, USP, pricing
  • Target region and currency
  • Brand voice & visual identity
  • Existing campaigns and lessons learned

If the file is missing, ask the user to run product-marketing-context-global first.


Information gathering

Ask the user up to 4 questions before starting:

  1. Campaign type? Product launch / seasonal / brand awareness / clearance sale / re-launch?
  2. Primary goal? Revenue [amount] / followers [count] / leads [count] / brand awareness [reach target]?
  3. Budget and timeframe? Total budget, campaign duration (in weeks), start date.
  4. Existing assets? Brand assets (logo, brand guide)? Testimonials / UGC? Existing customer database? Landing page?

Section 1 — Context

1.1 Overview

ItemDetail
Campaign name[name]
TypeLaunch / Seasonal / Awareness / Sales / Re-launch
Brand[brand name]
Product / service[short description]
Reason for running[why now? what is the trigger?]

1.2 Market situation

FactorDescription
Industry trend[current trend]
Customer behaviour this season[what shifted?]
What competitors are doing[notable competitor activity]
Opportunity to capture[market gap]

1.3 Lessons from previous campaigns

Previous campaignResultLesson
[name][KPI hit / missed][what worked / didn't]

Section 2 — Objectives

2.1 SMART goals

TypeGoalMeasured byDeadline
Business[e.g., $50K revenue in 4 weeks]Revenue, GMV[date]
Marketing[e.g., 5,000 messages, CPMess <$5]Message count, CPMess, ROAS[date]
Brand[e.g., reach 2M, +3K followers]Reach, follower, mentions[date]

2.2 Detailed KPIs

KPITargetIndustry benchmarkGap
CPMess[amount][region benchmark — see foundation skill]
ROAS[Nx]>3x
CPL[amount][benchmark]
Reach[count]
Engagement rate[%]
Orders[count]

Region note: Benchmarks vary by market. CPMess in the US is typically 3–5x higher than SEA. See product-marketing-context-global for region-specific benchmark tables.


Section 3 — Target audience

3.1 Customer profile

AttributePrimarySecondary
Age range[range][range]
Gender[male / female / all]
Region[country / region]
Income[bracket]
Occupation[role]
Primary pain[biggest problem]
Desire[what they want]
Barrier[why they have not bought]
Channels used[TikTok / Meta / LinkedIn / etc.]
Influencers[who / what they trust]

3.2 Customer insight

Call skill 09-customer-insight-global to mine deeper insight.

Core insight: [insight statement]

3.3 Insight validation checklist

Verify the insight is actually an insight and not just an observation:

CriterionPassFail
Specific — Specific to this audience, not generic?[ ][ ]
Hidden — Customer would not say it spontaneously?[ ][ ]
Actionable — Can be turned into messaging / creative?[ ][ ]
Emotional — Hits emotion, not only logic?[ ][ ]
True — Backed by data / observation, not assumption?[ ][ ]

Rule: Must pass at least 4 / 5. Otherwise it is an observation, not an insight. Mine again.

Distinguish:

  • Observation: "Women 25–35 care about skincare" — everyone knows this, nothing new.
  • Insight: "They buy serum not to have better skin — they buy a moment of self-care after an exhausting day." — emotional, actionable for creative.

Section 4 — Core message

4.1 Message framework

LayerMessageUsed for
Tagline[5–8 words, memorable]Everywhere — consistent throughout
Key message[1–2 sentences explaining value]Website, landing page, lead ads
Supporting message #1[proof / feature]Education content
Supporting message #2[proof / feature]Persuasion content
Supporting message #3[proof / feature]Conversion content

4.2 Tone of voice

AttributeIsIs not
Voice[e.g., friendly, expert][e.g., formal, distant]
Language[e.g., simple, conversational][e.g., academic, jargon-heavy]
Emotion[e.g., confident, reassuring][e.g., anxious, pressuring]

Section 5 — Creative direction

5.1 Creative territory

ItemDetail
Visual mood[e.g., warm, natural, trustworthy — not flashy or fake]
Colour palette[primary + secondary]
Typography[heading + body fonts]
Photography style[e.g., real lifestyle, no stock]
Video style[e.g., talking head + B-roll, UGC, cinematic]
Do's[e.g., real customer photos, vertical 9:16]
Don'ts[e.g., no sad music, no rainbow fonts]

5.2 Key visual

ElementDescription
Hero image / video[main visual concept]
Thumbnail style[description]
Text overlay[yes / no, style]
Logo placement[position, size]

5.3 Creative brief by channel

ChannelFormatSizeLengthQuantity
TikTokVertical video9:16 (1080×1920)15–60s[count]
Instagram (Reels)Vertical video9:1615–30s[count]
Instagram (feed)Carousel1:1 (1080×1080)5–7 slides[count]
Facebook (feed)Video + image1:1, 4:515–30s[count]
LinkedIn (feed)Image / carousel / video1:1, 1.91:130–90s[count]
YouTubeLong video + Shorts16:9 + 9:1660–600s + 30–60s[count]
EmailBanner + body600px width--[count]
Landing pageHero + sectionsResponsive--1

Section 6 — Channel system

6.1 Channels in use

ChannelRoleStart dateBudgetKPI
TikTok (organic)Reach + awareness[date][production cost]View, follower
TikTok (ads)Message + conversion[date][amount]CPMess, ROAS
Meta (ads)Retarget + conversion[date][amount]CPMess, ROAS
LinkedIn (ads)B2B reach + lead[date][amount]CPL, lead quality
Google Ads (Search)Intent capture[date][amount]CPL, ROAS
UGC networkSocial proof[date][fees]View, trust
EmailNurture + offer[date]--Open rate
Landing pageConversion[date][build cost]Conversion rate

6.2 Paid media plan

ChannelGoalAudienceDaily budgetCreativeDuration
Meta — AwarenessReachBroad, LAL 1–3%[amount]15s hook video[weeks]
Meta — ConversionMessage / leadRetarget + Interest[amount]Video + carousel[weeks]
TikTok — ReachView + messageBroad[amount]UGC-style video[weeks]
Google — SearchIntent captureBranded + non-brand[amount]RSA + sitelinks[weeks]

Section 7 — Timeline & phases

7.1 Budget split by phase

PhaseTimeline% BudgetGoalPrimary channels
TeasingWeek 1 (pre-launch)15%Build curiosity, anticipationOrganic TikTok / IG, email teaser
Soft launchWeek 220%Test creative, gather dataPaid ads small budget, UGC
Full launchWeeks 3–440%Scale winning creative, drive ordersPaid ads at full strength, retarget
SustainWeek 5+25%Re-engage, retarget, narrow audienceRetarget, email, LINE / WhatsApp nurture

7.2 Detailed timeline

DateActivityDetailOwnerStatus
[D-14]Creative productionProduce video + image assets[name]
[D-7]UGC brief sentBrief UGC creators[name]
[D-5]Landing page liveSetup + full QA[name]
[D-3]Teasing beginsOrganic posts + stories[name]
[D-Day]Official launchAds live, blast email, broadcast[name]
[D+3]First data reviewCheck CPMess, CTR, top creative[name]
[D+7]Optimisation round 1Cut weak creative, scale winners[name]
[D+14]Mid-campaign reviewCompare vs KPI, adjust[name]
[D+21]Retarget phaseFocus on warm audience retarget[name]
[D+28]Wrap + reportSummary, lessons, next-step proposal[name]

Section 8 — Deliverables & RACI

8.1 Deliverables list

#DeliverableQuantityDeadlineProducerApprover
1TikTok video (30s)[count][date][name][name]
2Facebook video (15s)[count][date][name][name]
3Carousel (5–7 slides)[count][date][name][name]
4Ad copy (3 variants)[count][date][name][name]
5Landing page1[date][name][name]
6Email templates (welcome + offer)2[date][name][name]
7UGC briefs[count][date][name][name]
8Video scripts[count][date][name][name]
9Messenger / broadcast content[count][date][name][name]
10Final campaign report1[date][name][name]

8.2 RACI matrix

DeliverableMarketing LeadContent CreatorDesignerAds SpecialistFounder
Campaign briefRIIIA
Creative productionARRCI
Ad copyARICI
Ad setupAIIRI
Landing pageACRCI
UGC coordinationRCIII
Daily optimisationAIIRI
Final reportRCICA

RACI legend:

  • R (Responsible): Does the work
  • A (Accountable): Owns the outcome, signs off
  • C (Consulted): Gives input before the work
  • I (Informed): Receives the result

Section 9 — Risks & mitigation

9.1 Campaign risk table

RiskProbabilityImpactSeverityMitigationWarning trigger
CPMess >50% above targetHighHighCRITICALPrepare 5 backup creatives, propose a pause via rule 7 (draft block, named approver) only when the trigger is met, shift to organicSpend >= 3x target CPMess (Step 0 data check), then CPMess > 1.5x target for 7 days = change creative/audience; > 3.0x = propose pause (house heuristic ladder in 03-performance-eval-global)
Creative does not performHighHighCRITICALA/B test from day 1, 3–5 new creatives / weekCTR < 1% after 2 days
Landing page conversion lowMediumHighHIGHA/B test headline + CTA, run heatmapConversion < 10% after 1 week
UGC delivered lateMediumMediumMEDIUMBrief early, keep backup contentUGC not received by D-3
Competitor runs deal at same timeLowHighHIGHLean on USP messaging, do not race on priceCompetitor ad detected at same time
Negative feedback goes viralLowVery highCRITICALCrisis protocol: respond <2h, transparent, prepared templateMore than 5 negative comments / reviews in 1 day
Audience fatigueMediumMediumMEDIUMRotate creative every 5–7 days, expand audienceFrequency > 2.5 (heuristic, cold traffic, 7 days) with CTR falling, e.g. down 30%
Budget overrunLowMediumMEDIUMCap daily budgets, daily spend reviewSpend > 110% of plan

9.2 Plan B (fallback)

SituationAction
Budget cut 50%Shift 100% to organic + UGC, retarget only
Primary channel disrupted (ad ban, etc.)Move budget to secondary channel within 24h
Mid-campaign KPI missEmergency meeting, re-brief creative, narrow audience

Auto-trigger downstream skills

Once the brief is complete, automatically suggest running:

02-campaign-brief-global (DONE)
  |
  |-- [Next 1] (ad copy skill if available) -> Ad copy from core message
  |-- [Next 2] 04-script-video-global       -> Scripts from creative direction
  |-- [Next 3] 01-content-calendar-global   -> Calendar from timeline + channels
  |-- [Next 4] (UGC brief skill if available) -> UGC briefs from deliverables

Examples — diversified regions

Example A — US SaaS Q4 launch

  • Campaign: New AI-powered analytics module
  • Region: US, currency USD
  • Budget: $80K over 6 weeks
  • Channels: LinkedIn ads, Google Search, podcast sponsorship, email nurture
  • KPI: 500 trials, ROAS 3.5x

Example B — EU DTC perfume Black Friday

  • Campaign: Black Friday clearance + new launch combo
  • Region: DE / FR / IT, currency EUR
  • Budget: EUR 45K over 3 weeks
  • Channels: Meta + TikTok ads, Klaviyo flow, Pinterest ads
  • KPI: ROAS 4x, AOV EUR 65

Example C — SEA Lazada / Shopee 11.11

  • Campaign: 11.11 mega sale on home appliances
  • Region: Singapore + Malaysia + Vietnam, currency SGD / MYR / VND (per market)
  • Budget: SGD 25K over 2 weeks
  • Channels: TikTok ads + Shopee Live, KOL livestream, LINE / Zalo OA broadcast
  • KPI: GMV target SGD 200K, CPMess <SGD 1.50

Quality checklist

Before delivering the brief, verify:

  • All 9 sections present (Context, Objectives, Target, Core Message, Creative Direction, Channel, Timeline, Deliverables, Risks)
  • Goals are SMART — specific, measurable, deadline-bound
  • Insight passes 4 / 5 validation criteria — not just an observation
  • Core message has 3 layers: tagline + key message + supporting messages
  • Creative direction has clear Do's and Don'ts
  • Budget split across 4 phases sums to 100% (Teasing 15% + Soft 20% + Full 40% + Sustain 25%)
  • Timeline has review milestones (D+3, D+7, D+14)
  • RACI is clear — every deliverable has an R and an A
  • At least 5 risks listed, each with severity and warning trigger
  • Plan B (fallback) covers at least 3 situations
  • Region-specific benchmarks used (not blanket global numbers)
  • Tone of voice matches the brand
  • All deadlines feasible — no clashes
  • Currency consistent with .agents/product-marketing-context-global.md

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.