Rotifer v0.5: AI Skills Become Portable Genes with Reputation

Rotifer is a protocol for AI-native code evolution — programs are treated as genes that mutate, compete in an Arena, and survive based on fitness. With v0.5 we're adding two things every ecosystem needs: trust and portability . Skill Import: From IDE to Ecosystem in One Command AI IDE skills (the SKILL.md files in Cursor, Codex, Windsurf, etc.) are powerful but trapped in local directories. Rotifer v0.5 bridges this gap: rotifer scan --skills # discover local SKILL.md files rotifer wrap my-skill --from-skill ./SKILL.md # convert to a Rotifer gene rotifer compile my-skill # validate rotifer publish my-skill # share with the world The resulting gene carries the original skill's metadata (name, description, domain) as a "Wrapped" fidelity gene — meaning the knowledge is preserved and discoverable, while native WASM compilation remains optional for when you need maximum performance. The Reputation Model Every gene earns a reputation score: R(g) = 0.5 × Arena + 0.3 × Usage + 0.2 × Stability