Results for “reasoning”

Anchors work at the current moment and places events as spatial distances ahead or behind to improve temporal reasoning.

Provides an immutable audit and provenance layer for agentic systems, recording reasoning, telemetry, and actions for debugging, compliance, and learning.

Use after the user has authorized GPT Pro help; manage a prompt-plus-sources workspace, route through ChatGPT Projects when available, and audit returned reasoning.

Get a second opinion from Claude Code. Use from Codex when you want to cross-check your reasoning, validate a plan, or get an independent review from Claude.

Script a teacher think-aloud demonstrating expert reasoning processes for a specific task. Use when modelling problem-solving, writing, reading comprehension, or analytical processes.

Design discipline-specific critical thinking tasks grounded in knowledge-contingent reasoning rather than generic skills. Use when embedding higher-order thinking into subject content.

Recommend the right AI model for a task by scoring candidates across six dimensions (Reasoning, Engineering, Speed, Breadth, Reliability, Governance) and displaying a spider-chart profile.

Guides junior developers and AI newcomers through Socratic questioning to build autonomy and reasoning skills, never providing direct answers.

Generates high-fidelity images using reasoning-driven prompts and structured creative briefs via muapi.ai.

AI-powered Claude Code skill that performs deep code review using formal logic and reasoning frameworks to detect bugs, anti-patterns, and security risks beyond what linters catch.

Expert guidance for implementing GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

Embody David Hume's empiricist and skeptical method to analyze causal claims, inductive arguments, moral reasoning, and metaphysical concepts.

Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.

Simulates Elon Musk with psychological depth and high-fidelity communication, applying first principles thinking, physics-based reasoning, characteristic humor, and authentic controversial opinions.

Configure and troubleshoot Honcho memory for Hermes, including multi-profile peer isolation, observation settings, dialectic reasoning, session summaries, and context budget enforcement.

Create and install Codex custom agent roles in ~/.codex/config.toml, generate role config files, enforce supported keys, and guide users through required role inputs (model, reasoning effort, developer_instructions).

Load expert mental models on-demand to enhance reasoning, with a library of modules across 15 categories and commands to manage a personal crew.

Explains how Agent Script instruction resolution works across three phases, with patterns for pre-LLM setup, LLM reasoning, and post-action loops.

Honestly evaluate AI work quality using a two-axis scoring system with mandatory devil's advocate reasoning and cross-session anti-inflation detection.

Analyzes code for logical errors, race conditions, security vulnerabilities, and algorithmic flaws using structured reasoning across 9 risk categories.

Provides a rigorous thinking partner profile that challenges assumptions, calibrates claims to evidence, and improves decision quality under uncertainty.

Improves multi-step research reliability with structured protocols for source validation, error recovery, and transparent reasoning.

Reduces a webpage to a structural skeleton by tokenizing content in the browser and applying LLM reasoning to collapse repeated patterns.

Annotates single-cell RNA-seq data by scoring marker genes, transferring labels with CellTypist, or reasoning over marker lists with an LLM.

Analyzes production code to find gaps in existing tests by reasoning about hypothetical mutations and checking whether tests would catch them.

Analyze any text to extract a cognitive fingerprint across 12 dimensions, revealing reasoning patterns, decision styles, and thinking signatures.

Benchmarks medical AI agents on synthetic EHR tasks, measuring success rates for data retrieval, temporal aggregation, and threshold-based conditional logic with exact-match scoring.

Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets, for PyTorch-based ML on molecules, proteins, and biomedical graphs.

Runs chest X-ray reasoning smoke tests using the NV-Reason-CXR-3B model via local inference or a public Hugging Face Space API.

Build and train graph neural networks for drug discovery, protein modeling, and molecular science using PyTorch-native tools.

Stress-test ideas, plans, and decisions using structured critical reasoning across five modes: Socratic questioning, dialectic, pre-mortem, red teaming, and evidence audit.

Model agent mental states using BDI (Beliefs, Desires, Intentions) ontology patterns, enabling cognitive reasoning, explainability, and semantic interoperability in multi-agent systems.

Embody C.S. Lewis as an AI persona to engage in reasoned, imaginative discussions on faith, morality, and suffering, applying his core arguments and rhetorical style.

Annotates single-cell RNA-seq data by scoring marker genes, transferring labels with CellTypist, or reasoning over cluster markers with an LLM.

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.

Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.