campaign-deck-builder
Skill95 starsChanged 6 days agoMITView on GitHub
Use this skill whenever the user wants to create a marketing-campaign presentation, pitch deck, or launch deck for a brand. Ask the campaign questions, then run the bundled script to fill the template into a finished .pptx.
- Installs packages
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Ask for these (accept short answers.
- Distinctive: line 46
Run the bundled script to produce the finished presentation:
- Very specific: line 61
Run it as python scripts/build_campaign.py <answers.json> [output.pptx].
- Distinctive: line 71
Keep copy punchy — headlines over paragraphs.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.
Files
Turn a short interview into a charming, vibrant, highly visual 3-slide new-marketing-campaign deck by filling a bundled PowerPoint template with a bundled Python script.
Step 1 — Interview the user
Ask for these (accept short answers; anything they skip gets a tasteful default). Ask them in a single, friendly batch:
- Brand name
- Campaign name (the headline of the launch)
- Tagline — one line that makes people lean in
- Target audience — who it's for
- The big idea — the single concept the campaign turns on (one sentence)
- Three key messages / benefits (exactly three)
- Channels / activation — where it runs (e.g. TikTok, out-of-home, retail)
- Call to action — the ask
- Closing line — the sign-off
- Brand accent color (optional,
#RRGGBB) — themes the whole deck
Step 2 — Write the answers file
Save the answers as JSON. All keys are optional; messages is a list of three.
{
"brand_name": "Vela",
"campaign_name": "Taste the Quiet",
"tagline": "Botanical sparkling water for your loudest days.",
"audience": "calm-seeking millennials",
"big_idea": "A moment of quiet in every can.",
"messages": ["Zero sugar, all serenity", "Adaptogens that work", "Guilt-free fizz"],
"channels": "TikTok · Out-of-home · Sampling",
"cta": "Pop the quiet.",
"closing": "Vela — find your fizz.",
"accent_hex": "#00A6A6"
}See assets/answers.example.json for a complete example.
Step 3 — Build the deck
Run the bundled script to produce the finished presentation:
python scripts/build_campaign.py answers.json campaign-deck.pptxIt fills assets/campaign-template.pptx — replacing every {{PLACEHOLDER}}
while preserving the design, rendering the three key messages as visual cards,
and recoloring the deck to the brand accent color when one is given. Missing
answers fall back to sensible defaults, so it always produces a complete
3-slide deck. Hand the resulting campaign-deck.pptx back to the user.
Bundled files
The attached .zip includes:
scripts/build_campaign.py— fills the template from a JSON answers file. Run it aspython scripts/build_campaign.py <answers.json> [output.pptx].assets/campaign-template.pptx— the 3-slide, highly visual template with{{PLACEHOLDER}}tokens.assets/answers.example.json— a complete sample brand you can copy and edit.references/design-notes.md— the slide/placeholder map and theming notes.
Requires python-pptx (pip install python-pptx).
Tone
Bold, upbeat, and brand-forward. The deck should feel like a launch, not a memo. Keep copy punchy — headlines over paragraphs.
In this repository199 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- accessibility-passSkill
- acroform-writerSkill
- action-items-todoSkill
- agent-evaluation-designerSkill
- agent-harness-explorerSkill
- agent-performance-triageSkill
- agent-red-teamSkill
- ai-demo-assistantSkill
- ai-first-process-redesignSkill
- ai-usecase-assessmentSkill
- anonymised-case-study-writerSkill
- evidence-gatherSkill
- gap-checkSkill
- readiness-packSkill
- scope-mapSkill
- b2b-outreach-suiteSkill
- blog-content-auditorSkill
- blog-post-structure-passSkill
- booth-loop-videoSkill
- brand-template-enforcerSkill
- brand-voice-passSkill
- breathing-roomSkill
- browser-uat-analystSkill
- business-osSkill
- call-for-speakers-digestSkill
- chart-builderSkill
- classic-text-adventureSkill
- clipchamp-videoSkill
- clt-hr-assistantSkill
- commenting-contentSkill
- competitive-battlecard-builderSkill
- conditional-chat-reminderSkill
- conference-session-abstract-packSkill
- contradiction-flagSkill
- insight-briefSkill
- provenance-checkSkill
- research-retrieveSkill
- trend-compareSkill
- content-quality-auditorSkill
- copilot-agent-advisorSkill
- copilot-studio-adaptive-card-builderSkill
- copilot-studio-agent-testSkill
- copilot-studio-harness-pickerSkill
- copilot-studio-knowledge-readinessSkill
- copilot-studio-mcp-readinessSkill
- copilot-studio-topic-blueprintSkill
- cowork-plugin-engineerSkill
- cowork-use-case-one-pagerSkill
- create-copilot-adoption-dashboardSkill
- context-assembleSkill
- handoff-packetSkill
- inquiry-intakeSkill
- knowledge-retrieveSkill
- resolution-draftSkill
- doc-format-converterSkill
- bom-impactSkill
- ecn-draftSkill
- ecr-ingestSkill
- standards-checkSkill
- 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.

