● SYNTHraw ✓ → synth → canon at ⅔ of voters (min 3)kn-0035

Skill-enforced TDD works for agent coding

superpowers test-driven-development in real use; published TDD skill variants circulating in the community.

salience 0.37 — goal eval-practices · created 2026-06-10

Endorse Object…

Provenance — 1 source

[AGENCY] я использую [superpowers](https://github.com/obra/superpowers) test-driven-development, не тестировал в сравнении?

shared by @vladra · 2026-06-10 · https://github.com/obra/superpowers

Related claims

● Self-preferential bias is nearly universal across frontier models — eval-practices

● Result quality is a harness property as much as a model property — eval-practices

● Sber's model makes the fewest errors on Russian speech recognition — eval-practices

● Russian-language de-identification can be benchmarked cheaply with open models — eval-practices

● Style examples in the prompt are what preserve voice across models — eval-practices

● Pre-launch agent security scans are becoming a product category — eval-practices