run-campaign
anthropics/knowledge-work-plugins
How to install run-campaign
npx skills add https://github.com/anthropics/knowledge-work-plugins --skill run-campaignFull instructions (SKILL.md)
Source of truth, from anthropics/knowledge-work-plugins.
name: run-campaign description: Runs an end-to-end marketing campaign — sales analysis, content brief, Canva assets, HubSpot send. Accepts optional lookback and channel arguments. allowed-tools: Read, WebFetch, Bash
Run the full campaign pipeline by chaining three skills in order. The owner approves at each handoff — never roll past a gate without explicit confirmation.
Parse arguments:
--lookback(default90d) — how far back to look for the revenue dip--channel(defaultboth) —email,social, orboth
Step 1 — Sales analysis + content brief (content-strategy)
Trigger the content-strategy skill workflow:
- Pull sales data from QuickBooks and PayPal for the lookback window.
- Identify the revenue dip — which product/service, which time period, magnitude.
- Produce a 30-day prioritized content brief: what to push, what offer to run, what to hold.
- Present the brief to the owner. Wait for explicit "approved, build the assets" before continuing.
If the owner edits the brief, incorporate edits and re-present.
Step 2 — Asset generation + send staging (canva-creator)
After Step 1 approval, trigger the canva-creator skill workflow:
- Take the approved brief from Step 1 as input.
- Build the posting calendar matched to the brief's priorities.
- Generate on-brand Canva assets for each post (apply each on screen for owner approval before moving on).
- Draft caption copy for each post.
- Stage the scheduled send in HubSpot (do NOT send — staging only).
- Present the staged campaign to the owner. Wait for explicit "approved, send to segment X" before Step 3.
Step 3 — Audience segmentation (lead-triage)
After Step 2 approval, trigger the lead-triage skill workflow:
- Pull HubSpot contacts that match the campaign's target segment (from the approved brief).
- Score by engagement, company fit, urgency markers.
- Produce two deliverables:
- Bulk send list — the segment receiving the staged campaign from Step 2
- High-priority call list — top 5 leads the owner should call personally with talking points
- Block calendar time for the call list.
- Present both lists. Wait for explicit "send" before pushing the HubSpot campaign live.
Approval gates (must hold)
- Never auto-progress between steps. Each handoff requires explicit owner approval.
- Never send the HubSpot campaign without the owner's "send" command in Step 3.
- If any connector is unreachable (QuickBooks, PayPal, Canva, HubSpot), stop, report which connector failed, and ask whether to retry or abort.
Output
End the run with a one-paragraph recap: revenue dip identified, posts generated, segment size, calls booked. Link to the HubSpot campaign URL once sent.
Related skills
More from anthropics/knowledge-work-plugins and the wider catalog.
data-visualization
Pick the right chart and generate publication-quality Python visualizations with built-in design and accessibility best practices.
code-review
Review code changes for security, performance, and correctness. Trigger with a PR URL or diff, "review this before I merge", "is this code safe?", or when checking a change for N+1 queries, injection risks, missing edge cases, or error handling gaps.
documentation
Write and maintain technical documentation. Trigger with "write docs for", "document this", "create a README", "write a runbook", "onboarding guide", or when the user needs help with any form of technical writing — API docs, architecture docs, or operational runbooks.
build-dashboard
Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file.
task-management
Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.
memory-management
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.