Implements a specific two-phase heuristic algorithm (Backward Phase followed by Forward Phase) to minimize total weighted tardiness for a single machine scheduling problem.
Analyzes sentences to identify subject-verb agreement errors and other grammatical errors, classifying the result into specific categories based on a defined decision matrix.
Performs deep, expert-level analysis of technical concepts (specifically AI/ML architectures) by decomposing them into components, associating them with existing research/theory, evaluating pros/cons and readiness, and synthesizing a final conclusion.
Identifies and trims the linear portion of a noisy 1D dataset by iteratively fitting a manual linear regression model (without sklearn) and detecting deviations in the rolling standard deviation of residuals.
Implement physics-based ramp alignment and control for a Unity hoverboard, including dynamic height adjustment, pitch alignment, speed modification based on incline, and physics property tuning.
Навык описывает процесс использования языковой модели для реверс-инжиниринга, где модель работает как denoising автоэнкодер, итеративно улучшая код C++ на основе ассемблера и предоставленных метаданных (типы, имена функций).
Arduino Nano, QTR sensörler ve MZ80 engel algılayıcı kullanarak siyah zemin üzerinde beyaz çizgiyi takip eden robot için C++ kodu yazar, PID parametrelerini ayarlar ve hız kontrolü sağlar.
Interactive post-onboarding tour with adaptive pathways based on available data
A skill that uses GLM-V native grounding capabilities for coordinate conversion, bounding-box visualization, and more. GLM-V native grounding can locate any target specified by the prompt in an image and output relative coordinates normalized to 0-1000 based on image size. Coordinate formats include 2D bounding box (default), 2D points, and 3D bounding box. GLM-V also supports spatiotemporal localization and tracking of multiple prompt-specified targets in videos, outputting 2D bounding boxes per second.
Builds AI-native products using OpenAI's development philosophy and modern AI UX patterns. Use when integrating AI features, designing for model improvements, implementing evals as product specs, or creating AI-first experiences. Based on Kevin Weil (OpenAI CPO) on building for future models, hybrid approaches, and cost optimization.
Activate ATLAS pattern recognition mode. Identify repeated patterns, extract essential characteristics, and create reusable abstractions from concrete examples.
Multi-model consensus council. Spawns parallel judges with Codex session agents when available. Modes: validate, brainstorm, research. Triggers: "council", "get consensus", "multi-model review", "multi-perspective review", "council validate", "council brainstorm", "council research".
Reverse-engineer a product into a feature catalog, code map, and specs. Uses RPI-style loop with verification gates. Triggers: “reverse engineer”, “catalog features”, “feature inventory”, “code map”, “docs to code mapping”, “binary analysis”.
Full validation phase orchestrator. Vibe + post-mortem + retro + forge. Reviews implementation quality, extracts learnings, feeds the knowledge flywheel. Triggers: "validation", "validate", "validate work", "review and learn", "validation phase", "post-implementation review".
Multi-model consensus council. Spawns parallel judges with configurable perspectives. Modes: validate, brainstorm, research. Triggers: "council", "get consensus", "multi-model review", "multi-perspective review", "council validate", "council brainstorm", "council research".
Reverse-engineer a product into a feature catalog, code map, and specs. Uses RPI-style loop with verification gates. Triggers: “reverse engineer”, “catalog features”, “feature inventory”, “code map”, “docs to code mapping”, “binary analysis”.
Full validation phase orchestrator. Vibe + post-mortem + retro + forge. Reviews implementation quality, extracts learnings, feeds the knowledge flywheel. Triggers: "validation", "validate", "validate work", "review and learn", "validation phase", "post-implementation review".
Provides custom Python metrics for configuring Vertex AI Gen AI Evaluation to measure Trajectory Precision, Recall, and Order Match.
