Publisher: Corey Haines · Editorial profile by AI Tools Ratings · Review method
What task is this skill designed for?
Simplify a new user's path to exporting their first usable report without removing necessary permissions.
What input and output should you expect?
Input: Current post-signup screens, prerequisites, a proposed value event and aggregate cohort data with observation windows, if available.
Output: A revised first-use flow, empty-state copy and a measurement plan defining activation and later retention separately.
What does it need to run?
Agent Skills client and a flow inventory. Inspect minimum-path-to-value and activation-model references. Analytics access is optional for a design draft but required to claim measured drop-off.
The pinned publisher README declares support for Agent Skills clients including Claude Code, Codex and Cursor. Compatibility follows the publisher’s stated support.
How should you approach installation?
- Inspect the pinned SKILL.md, license and referenced files needed for your specific task before installation.
- Follow the publisher README for your actual Agent Skills client.
- Try the illustrative prompt with synthetic material in a separate workspace. Review the checklist and approve any publishing, account or external-message action separately.
Installation guide: discovery, dependencies and runtime checks
What files, accounts or data can it access?
Reads screen descriptions and aggregate usage data. Product edits, lifecycle messages and account experiments require separate implementation review. Do not upload user-level identifiers unnecessarily.
What does the skill cost?
MIT-licensed source. Agent subscriptions, model usage and optional research or analytics services have separate costs.
What are its limits and alternatives?
Completing a checklist may not predict retention. An early event is only a candidate activation measure until validated in fully observed cohorts. Removing a permission step can break the task or user expectations.
Use Signup for registration before the account exists. Use A/B Testing to design a controlled test after a concrete onboarding change is ready.
What could you ask in a small trial?
Try this with a small sample:
Redesign this synthetic report app's onboarding around one successful export. Identify required permissions, remove optional setup from the critical path and define an activation window without inventing retention data.
How would you verify the result?
- Make the first useful output reachable without optional configuration.
- Retain necessary permission and recovery steps.
- Define activation and retention denominators with complete observation windows.
Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.
Which source and license were checked?
Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder
Repository and current publisher guidance
Checked:
MIT — identified in the repository LICENSE at the pinned commit. External services and dependencies have their own terms. License evidence
Version details and review scope
Source: coreyhaines31/marketingskills/skills/onboarding
Reviewed commit: e85f3cbc2e4a79bf33b2a12e9bdd9087d414735b
SKILL.md SHA-256: 61b808c85207e6567f39e5d6b7876fdad77b5f17f5811afcd8b28cfce6dcbe31
Source-document review. This profile covers the source workflow, stated dependencies and license evidence. See our editorial methodology for how we distinguish source reviews and hands-on evaluations.