From file to useful result
How to ask with this skill installed
Installing the skill gives your AI a method. Your request still has to provide the case-specific facts, constraints and expected output.
1Name the real task
Describe the decision or deliverable, not just the topic.
2Provide the evidence
Add source material, audience, limits and known facts.
3Define done
Set format, quality criteria and checks.
Source example
Replace the brackets with your case
Mistakes to avoid
- Tracking too many metrics. A dashboard with 50 metrics tells you nothing. A dashboard with 5 well-understood metrics drives action. Choose <10 KPIs that your entire team can memorize.
- Ignoring churn. Most founders track acquisition but forget churn. A startup growing 20% MoM with 15% monthly churn is barely growing. Track churn from day one.
- Vanity metrics over actionable metrics. "Total registered users" is a vanity metric if most of those users never came back. "Daily active users who completed a core action" is actionable.
- No baseline before experiments. You can't measure improvement without a baseline. Make sure your tracking is solid before running growth experiments.
- Not tracking CAC by channel. If you can't distinguish CAC between Google Ads and LinkedIn outreach, you can't optimize your marketing spend. Tag every lead source from day one.
- Assuming correlation is causation. More users who used Feature X retained better — but did Feature X cause retention, or did retained users naturally use Feature X more? Distinguish between leading indicators and correlating behaviors.
- Not adjusting for seasonality. Spanish retail has Black Friday/Cyber Monday spikes. Tourism-related businesses have summer peaks. If you're comparing MoM metrics in August vs. September, you'll get misleading signals.
- Dashboard without decisions. A dashboard that nobody looks at is worthless. Define a meeting cadence (weekly is minimum) to review metrics and make decisions based on them.