agentsclimarketplace

Campaign postmortem

Skill zapier/gtm-cheat-codes/skills/marketing/campaign-postmortem

A field guide for go to market teams using coding agents. Installable skills for campaign planning, CRM context, customer proof, and reviewable agent workflows.

Install
npx -y skills add zapier/gtm-cheat-codes --skill campaign-postmortem

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Build sourced campaign retrospectives from goals, launch context, performance data, team feedback, and follow-up actions.

SKILL.md

1.7 KB, as published. Nobody here has run it

Campaign Postmortem

Use When

A marketing team needs to understand what happened in a campaign and turn the learning into better next-cycle decisions.

Workflow

  1. Confirm campaign name, date range, goals, channels, and audience.
  2. Gather approved source material: brief, launch plan, project notes, performance data, meeting notes, and team feedback.
  3. Build a timeline of major decisions, launch events, results, and follow-up actions.
  4. Compare goals to actual results with source references.
  5. Separate observations from interpretations.
  6. Identify what worked, what did not work, root causes, and open questions.
  7. Recommend what to repeat, change, or stop.
  8. Add an action register with owners, dates, and unresolved decisions when available.

Zapier MCP And SDK Role

  • Use Zapier MCP to gather approved campaign docs, conversations, dashboards, CRM context, meeting notes, and tracker state.
  • Use Zapier SDK for retro intake, scheduled reminders, reviewer routing, action logging, and follow-up tracking.
  • Keep metrics, claims, and broad sharing review-gated.

Output Format

  • Executive summary
  • Source list
  • Campaign timeline
  • Goal vs. actuals
  • What worked
  • What did not work
  • Root causes and caveats
  • Repeat / change / stop
  • Action register

Guardrails

  • Never invent metrics, attribution, causes, or owner commitments.
  • Label missing data and conflicting evidence.
  • Keep the retro focused on systems, decisions, and process, not personal blame.
  • Require human review before sharing broadly or updating source-of-truth records.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.