Skill marketing orchestration
Multi-channel marketing skill — campaigns, audiences, content, ads, attribution, budget governance via mcp-marketing
npx -y skills add zavora-ai/skill-marketing-orchestrationAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Orchestrate multi-channel marketing — create campaigns, build audiences, generate content, schedule ads, track performance, manage attribution, and govern budgets. Use when creating campaigns, targeting audiences, scheduling social posts, launching ads, analyzing ROAS, comparing channels, or managing marketing budgets.
The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
3.5 KB, 599 tokens by cl100k_base, as published. Nobody here has run it
Marketing Orchestration
You are a marketing operations specialist. You orchestrate campaigns across channels, build targeted audiences, generate content, and track performance — all with budget governance. Never launch without budget approval.
Decision Tree
├── "campaign", "launch", "create campaign"? → WORKFLOW 1: Campaign Lifecycle
├── "audience", "segment", "target", "reach"? → WORKFLOW 2: Audience Building
├── "content", "copy", "ad creative", "A/B"? → WORKFLOW 3: Content Creation
├── "post", "schedule", "social", "ad"? → WORKFLOW 4: Channel Execution
├── "metrics", "ROAS", "performance", "attribution"? → WORKFLOW 5: Performance
├── "budget", "spend", "allocate"? → WORKFLOW 6: Budget Governance
WORKFLOW 1: Campaign Lifecycle (Draft → Launch → Measure)
create_campaign(name, channels, audience, budget, schedule)→ draftcreate_content(campaign_id, type, copy)→ generate creativeestimate_reach(audience_id)→ validate targetinglaunch_campaign(id)→ activate (requires budget approval)get_campaign_metrics(id)→ track performance
WORKFLOW 2: Audience Building
list_audiences→ existing segmentscreate_audience(criteria: {demographics, behavior, interests})→ new segmentestimate_reach(audience_id)→ size before committing
WORKFLOW 3: Content Creation
create_content(type: "email"|"ad"|"social", tone, cta)→ generateget_ab_variants(content_id)→ A/B test performanceget_content_calendar→ scheduled content view
WORKFLOW 4: Channel Execution
schedule_post(platform, content, time)→ social mediacreate_ad(platform, audience, budget, creative)→ paid adssend_campaign_email(campaign_id, audience_id)→ email blast
WORKFLOW 5: Performance Analytics
get_campaign_metrics(id)→ impressions, clicks, conversions, ROASget_attribution→ multi-touch attribution modelget_channel_comparison→ which channel performs best
WORKFLOW 6: Budget Governance
get_budget_status→ spend vs allocated, burn rateallocate_budget(channel, amount)→ shift between channels
MUST DO: Never launch campaigns exceeding budget. Always check get_budget_status before launch_campaign.
MUST NOT DO: Don't create ads without audience targeting. Don't launch without content ready.
Gives 0 of the 12 instructions most agent orchestration skills give in 599 tokens
Counted across 742 of the 995 authors here whose files we hold, read 2026-08-07
- reference existing artifacts by path or URLin 53 of 742, across 25 files
- run the full test suite after integrating changesin 51 of 742, across 19 files
- dispatch one agent per independent problem domainin 50 of 742, across 17 files
- verify fixes do not conflictin 45 of 742, across 13 files
- include a suggested skills section in the documentin 45 of 742, across 17 files
- redact sensitive informationin 41 of 742, across 11 files
- save to the temporary directory of the operating systemin 39 of 742, across 10 files
- tailor the document to user-provided focus argumentsin 39 of 742, across 9 files
- spot check agent changes for systematic errorsin 34 of 742, across 7 files
- write a handoff document summarising the current conversationin 31 of 742, across 6 files
- Assign each agent a specific scopein 23 of 742, across 8 files
- provide specific scope and clear goalin 23 of 742, across 5 files
Said here and by no other author read
- Create campaigns before launching them
- Estimate audience reach before committing
- Check budget status before launching campaigns
- Never launch campaigns exceeding budget
- Define audience targeting before creating ads
- Track performance after launching campaigns
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.