admet-prediction
Predict comprehensive ADMET (Absorption, Distribution, Metabolism, Excretion, Toxicity) properties for drug candidate molecules using GraphMVP ensemble models. Use this skill when: (1) Predicting blood-brain barrier penetration, (2) Assessing side effect profiles, (3) Estimating Caco-2 permeability, half-life, or LD50 toxicity, (4) Evaluating drug-likeness and safety of molecules.
ensemble-implement
Scan Linear for agent-ready issues in the Ensemble project, pick the highest priority one, implement it following TDD, verify with frontend and backend tests/lint, and create a PR. Use when asked to implement issues, fix bugs, or develop features for the Ensemble Tauri desktop app. Do not use for iOS projects.
Drainbrain
AI-powered Solana token rug pull detection with ML ensemble scoring and honeypot detection.
accessibility-web â référentiel WCAG 2.2 AA {{COMPANY_NAME}}
> Contenu vendorisé et condensé depuis **accessibility-agents** v6.0.0 de Community-Access / Taylor Arndt (MIT) â sous-ensemble web uniquement (10 agents spécialistes sur 80) â voir `docs/vendored-content.md`. Sources d'autorité : [WCAG 2.2](https://www.w3.org/TR/WCAG22/), [ARIA APG](https:/
untell
Rewrite text so a local ensemble of AI-text detectors stops flagging it, while semantic meaning and all citations/numbers/quotes stay intact. The core technique is a **closed loop**: score â rewrite using the per-detector scores as feedback â re-score, repeating until the hardest detector is und