Automate marketing performance reporting from approved channel exports, with source-linked metrics in a repeatable Google Sheet. It uses the role criteria, source files and approval rules you choose, then saves the filled output in a named Google Drive folder. This keeps the workflow repeatable without handing your judgment to the agent.
Turn approved channel exports and metric rows into repeatable campaign reports with source trace. The agent keeps the steps, checks and output consistent, while you keep every decision.
Picture tomorrow's handoff.
"Hello, prepare this month’s campaign performance report"
| Campaign | Spend | Result | Source | Variance | Next question |
|---|---|---|---|---|---|
| Launch week LinkedIn ads | $1,850 | 34 demo bookings ($54/booking) | Ad platform export Sep 12 | 20% under target CPA | Scale budget 20%? |
| Webinar Sep 5 | $600 | 11 demos ($55/booking) | Webinar platform + CRM | On target | Repeat monthly? |
Sample data. Your agent fills the file from the sources you approve and flags anything it cannot verify.
Three files. One complete workflow.
skill.mdThe full job, evidence rules, output checks and stop points.
setup-prompt.txtCreates the tools, named Drive folder and sample-data test.
usage-prompt.txtThe short request you reuse whenever the job comes up.
Working in three steps
It checks access, creates the folder and builds the output file.
Use Google by default, or the Microsoft or Zoho alternative.
Unknowns and next decisions are shown instead of guessed.
Where the agent stops
- It does not invent missing facts or hide weak source evidence.
- It does not send, publish, spend, schedule or make a human decision without approval.
- It flags blocked work and tells you exactly what is needed next.
Put this job on a repeatable workflow.
Instant download · Keep the files forever · One-time $19
Add the next agent when this job is working
Use the Performance Reporting Agent with your assistant
The same three files run on any assistant that reads plain text. Pick yours for the step-by-step setup - where the files go, what a run looks like, and the honest limits:
- Instinct - hand the three files to Instinct in chat - it keeps them across sessions, so the agent becomes a standing workflow you trigger with one line.
- ChatGPT - lives in a ChatGPT Project - skill.md as a Project file, the setup prompt as Project instructions, and each run starts inside that Project.
- Claude - lives in a Claude Project - skill.md as Project knowledge, the setup prompt as instructions, and each run starts in that Project.
- Gemini - lives in a Gemini Gem - the Gem’s instructions are skill.md plus the setup prompt, so the rules persist between sessions.
- Grok - lives in a Grok Skill or custom Bot with skill.md as the standing expertise - or attach the three files to a chat.
- DeepSeek - no persistent agents - upload skill.md at the start of each chat and re-paste the usage prompt per run (a well-packaged DIY prompt).
- Perplexity - lives in a Perplexity Space - upload the three files, paste the setup prompt into the Space instructions, and runs start in that Space.
- Microsoft Copilot - with Microsoft 365 Copilot it lives in a Notebook (skill.md as reference, setup prompt as instructions); in consumer Copilot, re-upload the files each session.
- Hermes - place skill.md in your Hermes workspace as the standing skill, then run the setup prompt - local-first, files stay under your control.
- OpenClaw - drop the three files into your OpenClaw workspace and point it at skill.md - setup runs over your usual chat channel.
- Town - share the three files with Town and ask it to keep skill.md as the standing rules for the job.
- Muse - give the three files to Muse and ask it to keep skill.md as the standing rules - approve the sample-data test first.
Questions people ask
What does the Performance Reporting Agent actually do?
It turns your approved channel exports into the same report every month: campaign, spend, result, source, variance and the next question, with every number traced to its source row. It prepares review-ready work and stops for your approval before anything is sent, spent, published or scheduled.
Which AI assistants work with the Performance Reporting Agent?
Any assistant that reads plain-text files: Instinct, ChatGPT, Claude, Gemini, Grok, DeepSeek, Perplexity, Microsoft Copilot, Hermes, OpenClaw, Town, Muse and others. You hand it three files - skill.md, setup-prompt.txt and usage-prompt.txt.
Is the Performance Reporting Agent $19 a subscription?
No. $19 is one-time. You download and keep the three files forever; there is no account and no renewal.
How long does setup take?
About 10 minutes: attach the files, run the setup prompt, approve the fictional-data test. It never touches real work until you approve the sample run.
Last updated 13 September 2026 · Reviewed by the AI Agent Skills team.