{"enrichment":{"faq":[{"a":"Autoresearch automates large-scale SKILL.md improvement by spawning multiple variants per generation, evaluating each through a programmatic harness without browser overhead, and scoring with triple-run averaging to identify the strongest performer. The engine iterates autonomously, committing improvements to git and halting when scores plateau or oscillate.","q":"What does autoresearch skill do?"},{"a":"Autoresearch generates autonomous variants of your SKILL.md file in parallel, testing each variant through a programmatic evaluation harness that requires no browser dependencies. It scores fitness across all variants using triple-run averaging to smooth results, then selects the strongest performer for the next generation of mutation and testing.","q":"How does autoresearch run parallel SKILL.md optimization?"},{"a":"Yes. Autoresearch improves skill quality at scale by running multiple generations of mutation and scoring. Each generation spawns new variants from the best prior performer, evaluates them programmatically, and advances only those that increase fitness. This iterative process continues until scores plateau or oscillate, signaling convergence.","q":"Can autoresearch improve skill quality at scale through multi-generation mutation?"},{"a":"No. Autoresearch executes programmatic skill evaluation without browser dependencies, making it lightweight and suitable for CI/CD pipelines and headless environments. The evaluation harness runs directly against your SKILL.md variants without spawning a browser instance.","q":"Does autoresearch require a browser for skill evaluation?"},{"a":"Autoresearch analyzes skill fitness across variants with triple-run averaging, running each variant three times and averaging the scores to reduce noise. This approach identifies genuinely stronger performers rather than rewarding lucky single runs, ensuring stable progression across generations of optimization.","q":"How does autoresearch analyze skill fitness across variants?"},{"a":"Autoresearch is released under the MIT license, permitting free use, modification, and distribution in both open-source and commercial projects with minimal restrictions.","q":"What license does autoresearch use?"}],"shadow_tags":["autonomous-optimization","variant-generation","fitness-scoring","parallel-evaluation","skill-mutation","programmatic-testing","iterative-improvement","multi-run-averaging","orchestration-engine","skill-evolution"],"summary_rewrite":"Autoresearch automates large-scale SKILL.md improvement by spawning multiple variants per generation, evaluating each through a programmatic harness without browser overhead, and scoring with triple-run averaging to identify the strongest performer. The engine iterates autonomously, committing improvements to git and halting when scores plateau or oscillate."},"files":[{"bytes":3457,"path":"vibes-desktop/build/stable-macos-arm64/VibesOS.app/Contents/Resources/vibes-plugin/skills/autoresearch/SKILL.md","sha256":"05738c2f051325d22f39019f8d5fc6fa696cb3de15665f4f9ff39b49c788e12d","url":"https://skillfed.io/files/popmechanic/VibesOS/autoresearch/abedece1/SKILL.md"}],"id":"popmechanic/VibesOS/autoresearch","links":{"html":"https://skillfed.io/popmechanic/VibesOS/autoresearch","md":"https://skillfed.io/popmechanic/VibesOS/autoresearch.md","repo":"https://github.com/popmechanic/VibesOS"},"meta":{"agents_supported":[],"first_seen":"2026-07-28","forks":6,"language":"HTML","last_updated":"2026-07-27","license":"MIT","name":"autoresearch","publisher":"popmechanic","stars":134},"relations":{"similar":[{"id":"popmechanic/VibesOS/upload-dmg"},{"id":"popmechanic/VibesOS/vibes"},{"id":"popmechanic/VibesOS/launch"},{"id":"popmechanic/VibesOS/riff"},{"id":"popmechanic/VibesOS/sell"},{"id":"popmechanic/VibesOS/cloudflare"},{"id":"popmechanic/VibesOS/factory"},{"id":"popmechanic/VibesOS/design"},{"id":"oliver-kriska/claude-elixir-phoenix/autoresearch"},{"id":"notque/vexjoy-agent/agent-comparison"}]},"slug":{"owner":"popmechanic","repo":"VibesOS","skill":"autoresearch"},"version":"abedece1"}