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
- Claiming no competitors. This signals you haven't done research, not that you have a unique idea. Every market has alternatives — including "do nothing."
- Claiming too many competitors. Listing 20 competitors means you haven't identified your closest rivals. VCs want to see you can focus.
- Only analyzing product, not distribution. Most competitive defeats happen not because a competitor had a better product but because they had better distribution. Know how competitors acquire customers.
- Static analysis. The competitive landscape changes. A SWOT analysis from 12 months ago is nearly useless. Keep it updated quarterly.
- No moat story. Investors will push on this. If you can't articulate why you're defensible, they'll assume you're not. Have a moat story even if the moat isn't fully built yet.
- Underestimating switching costs. You might have a better product, but switching costs (data migration, retraining, procurement cycles) might keep customers on inferior solutions. Acknowledge this and address it.
- Copying competitor features instead of building differentiated value. The best companies don't compete on features — they compete on the specific combination of features that matters most to their target customer.
- Ignoring adjacent threats. The most dangerous competitor is often not the obvious direct competitor but an adjacent player who expands into your space (Amazon entering logistics, Stripe entering lending, etc.).