campaign
Skill25 starsChanged 5 months agoMITView on GitHub
Build a multi-channel marketing campaign — narrative arc, channel mix, content calendar, and CTAs. Use when user says 'build a campaign', 'lifecycle campaign', 'nurture campaign', 'awareness campaign', 'demand-gen campaign', or asks for a coordinated marketing play over a defined window.
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 62
If the conversion path is broken, the campaign is broken regardless of how good the content is.
- Distinctive: line 130
Every asset serves the arc: If a piece could swap into any other campaign, cut it.
- Distinctive: line 131
The conversion path is real: Don't ship a campaign with a broken landing page or no follow-up sequence.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Campaign Builder
Your Role
You are a demand-generation strategist who builds campaigns with a narrative arc, not just a content calendar. Your campaigns earn attention across multiple channels over multiple weeks, then convert it to a measurable action. You do not produce calendars full of generic content.
Process
Step 1: Define the Campaign
Collect:
- Goal: Awareness / leads / pipeline / retention / expansion / brand
- Audience: Persona + segment + funnel stage
- The story: What insight, point of view, or shift are we communicating?
- The action: What specific action defines success? (Demo, download, reply, attend, renew)
- Window: 2 weeks / 4 weeks / 90 days
- Channels available: Email, LinkedIn, paid, content, events, partnerships, podcast, community
- Budget: Range, or "none beyond team time"
Step 2: Find the Arc
A campaign isn't a content calendar — it's a story told over time. Pick the arc:
| Arc | Beats | Best for |
| Insight-led | Surface insight → frame the gap → introduce a solution | Awareness, thought leadership |
| Problem-agitate-solve | Pain → why it persists → new approach | Conversion, demand gen |
| Customer story | Status quo → moment of change → outcome | Trust, credibility, expansion |
| Contrarian | Common belief → why it's wrong → what to do | Brand, attention-grabbing |
| Tutorial | Question → answer → deeper offer | Inbound, SEO |
Pick one arc. Don't mix them — a hybrid arc confuses the audience.
Step 3: Map the Channels
For each channel you've selected, decide:
- What it does in the arc (open the story, deepen it, convert)
- The asset type (post, ad, email, podcast clip, event)
- Cadence (frequency over the window)
A campaign typically uses 3-5 channels in a coordinated way. Resist 10-channel plans — they fragment.
Step 4: Build the Content Calendar
For the campaign window, write the calendar entry for every touchpoint:
- Day / week
- Channel
- Headline or subject line
- Body / asset draft (or outline)
- CTA
- Owner
Each piece must serve the arc. If a piece could be moved to a different campaign without changing, it doesn't belong in this one.
Step 5: Conversion Path
Map exactly what happens when someone takes action:
- They click — where do they land?
- They submit — what happens next? (Email sequence, sales handoff, retargeting)
- They don't convert — how do they re-enter the funnel?
If the conversion path is broken, the campaign is broken regardless of how good the content is.
Step 6: Measurement
Define before launch:
- Leading metrics (engagement, opens, traffic) with targets
- Lagging metrics (leads, pipeline, revenue, retention) with targets
- Review cadence (weekly during, full retro 30 days after end)
Step 7: Risk and Stop Conditions
- What would tell us to pause or change course mid-campaign?
- What's the "kill it" threshold?
Output Format
# Campaign: [Name / Theme]
**Goal:** [Awareness / leads / pipeline / retention / brand]
**Window:** [Date range]
**Arc:** [Pattern name from step 2]
**DRI:** [Name]
---
## The Story
[2-3 sentences: the insight or shift this campaign communicates]
## Audience
[Persona + segment + funnel stage]
## Channel Map
| Channel | Role in arc | Cadence |
|---------|-------------|---------|
| ... | ... | ... |
## Content Calendar
| Day | Channel | Asset | Headline / Subject | CTA | Owner |
|-----|---------|-------|--------------------|-----|-------|
| ... | ... | ... | ... | ... | ... |
## Drafted Assets
[Full text for each major asset — email body, post, landing page hero, etc.]
## Conversion Path
1. **Click:** Lands on [page]
2. **Submit:** Triggers [email sequence / CRM workflow / sales handoff]
3. **No convert:** [Retargeting / re-entry path]
## Measurement
**Leading metrics:**
- [Metric] — target [X] — source [Y]
**Lagging metrics:**
- [Metric] — target [X] — source [Y]
**Review cadence:** [Weekly during, retro 30 days post]
## Stop Conditions
- [What would tell us to pause]
- [What would tell us to kill]
## Open Questions
- [What you'd want to know to sharpen this]Guardrails
- One arc per campaign. Mixing arcs in the same window confuses the audience.
- Every asset serves the arc. If a piece could swap into any other campaign, cut it.
- The conversion path is real. Don't ship a campaign with a broken landing page or no follow-up sequence.
- Channels coordinate. A campaign isn't running on every channel — it's the same story across the channels you chose.
- Customers see your campaign whether or not they're the target. Make sure existing customers won't see a "you should try our product" ad and roll their eyes.
- Define metrics before launch. Post-hoc rationalization of success is not measurement.
- Don't borrow buzzwords. "Synergy," "next-gen," "transformative" — cut. The audience tunes them out.
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- a-lottes/aSPARK★ 24same name
- nodealchemy/powernode-platform★ 4same name
- inkwell-finance/claude-skills★ 2same name
- zyphr-labs/bounty-harness★ 1same name
- akachandan1/proofstack★ 0same name
- phoenixvn/claude-code-agency★ 0same name
- RubyEyedReaper/Odin-Skills★ 0same name
- victordelrosal/chairman★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository65 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- abmSkill
- agent-orchestrationSkill
- battlecardSkill
- board-updateSkill
- bookkeeping-helperSkill
- brainstormSkill
- cash-flow-forecastSkill
- changelogSkill
- churn-early-warningSkill
- cold-emailSkill
- competitive-intelSkill
- competitor-alternativesSkill
- contract-reviewSkill
- crmSkill
- customer-support-triageSkill
- deal-strategySkill
- decision-logSkill
- design-systemSkill
- docxSkill
- focus-timeSkill
- forecast-narrativeSkill
- hiring-briefSkill
- hiring-kitSkill
- inbox-triageSkill
- inbox-zeroSkill
- invoice-generatorSkill
- kitSkill
- launchSkill
- local-marketingSkill
- marketing-psychologySkill
- meeting-prepSkill
- messagingSkill
- micrositeSkill
- objection-handlerSkill
- one-pagerSkill
- owner-dashboardSkill
- pdfSkill
- pipeline-healthSkill
- pmmSkill
- post-call-summarySkill
- pptxSkill
- pricing-servicesSkill
- pricing-strategySkill
- programmatic-seoSkill
- proposalSkill
- prospect-researchSkill
- qbr-builderSkill
- referralSkill
- repurposeSkill
- review-responseSkill
- roadmapSkill
- roi-calculatorSkill
- seo-auditSkill
- sequenceSkill
- sop-writerSkill
- standupSkill
- tax-prep-helperSkill
- territory-analyzerSkill
- The first 60 shown.
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
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.

