Coordinate five AI models to evaluate Bottie's autoresearch loop and synthesize findings.
npx skills add https://github.com/Liquilab/Bottie --skill aireview-liquilab
Please help me install this Agent Skill. Skill: aireview Source: https://github.com/Liquilab/Bottie/tree/main/.claude/skills/aireview Command: npx skills add https://github.com/Liquilab/Bottie --skill aireview-liquilab
Bottie’s autoreview workflow requires an objective, reproducible cross-review of its AI-search loop, coordinating multiple models to surface high-impact improvements.
Run a full 5-model cross-review to obtain an objective synthesis of Bottie's autoresearch results.
High-intent search queries and answers about installing and using this skill.
Cross-model AI review coordinates Claude Opus 4.6, Gemini 3.1 Pro, GPT-5.2, Codex 5.3, and Perplexity to evaluate autoresearch loops. It applies standardized criteria to identify gaps and risks, synthesizing findings into objective assessments with actionable improvement suggestions.
Multi-model synthesis aggregates evaluations from multiple AI models into a unified assessment. It quantifies findings, identifies risks and opportunities in AI search loops, and delivers concrete improvement suggestions traceable to relevant code, data, and logs.
Cross-model evaluation supports regression checks and traceability by mapping synthesized findings directly to relevant code, logs, and hypotheses. This ensures objective improvement recommendations remain grounded in verifiable system data.
Multi-model AI review applies standardized criteria to automated research workflows to identify gaps, risks, and opportunities. It quantifies findings where possible to produce objective system reviews that drive concrete, actionable improvements.
Coordinating multiple AI models produces an objective, reproducible cross-review by balancing individual model biases. This multi-model synthesis surfaces high-impact improvements that a single model assessment might miss.
Multi-model synthesis requires coordinating five separate AI models, which introduces dependency on each model's availability and response consistency. The evaluation is limited to the standardized criteria applied and the quality of the provided code, logs, and data.
chrishuffman5Modify machine learning training code and evaluate models in a keep/discard loop.
LeKayRun a test-fix-retest loop with static checks to improve AI skills.
SimHackerSystematically debug issues by hypothesizing, testing, and tracking evidence.
LetPeopleWorkEvaluate code plans and implementations against structured review criteria with severity levels.
