A lightweight RFC process for solo developers working with AI agents. Prevents premature complexity by forcing problem-first thinking before jumping to solutions. Use when the user is considering introducing new tools, libraries, architectural patterns, or infrastructure. When they're weighing a significant technical decision. Triggers on phrases like "should I add X", "I'm thinking about introducing Y", "is this overkill", "do I need X", "is X worth it", "/rfc", or when the user is about to adopt a tool/pattern without first articulating the problem it solves.
72
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Tessl evals compare success rates of agents with and without our optimized context