agentsclimarketplace
Sign in

Campaign postmortem

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

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

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.

SKILL.md

1.7 KB, 338 tokens by cl100k_base, 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.

What ships with it: 5 files

3.8 KB alongside SKILL.md

Gives 0 of the 12 instructions most marketing audience skills give in 338 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Said here and by no other author read

  • Confirm campaign details
  • Gather approved source material
  • Build a timeline of events
  • Compare goals to actuals
  • Separate observations from interpretations
  • Identify what worked

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.

Keep looking

Skills are one crate of 325,949. 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.