Results for “reasoning”

Use when two or more agents produce conflicting outputs, recommendations, or decisions. This skill provides a structured process for resolving disagreements between agents, ensuring conflicts are resolved fairly with clear reasoning and documented decisions.

Assesses NumPy code for cuPyNumeric migration readiness by analyzing source code against an API support manifest and GPU-scaling idioms, producing a structured verdict with per-finding reasoning.

Analyzes a website's current design and user intent to produce a structured redesign specification, including product and design documents, a design system JSON, and a reasoning trace.

Benchmarks large language models on symbolic music understanding and instruction following using text-based ABC notation, covering syntax parsing, error detection, segment-level reasoning, and sequence-level musical analysis.

Recommends the optimal Claude model tier (Opus, Sonnet, or Haiku) for a given task by analyzing reasoning depth, blast radius, domain expertise, output length, and correctness cost, and suggests parallelization opportunities.

Provides a persona that applies Elon Musk's engineering and management principles, including first principles reasoning, the 5-step algorithm, and physics-based analysis, to problem-solving and decision-making.

Benchmarks long-context language models across 20 sub-tasks spanning 3k–200k tokens, covering retrieval, reasoning, summarization, and instruction understanding, with exact-match accuracy as the primary metric.

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.

Interact with openLesson tutoring API for Socratic learning: generate learning plans as directed graphs, start audio-based tutoring sessions, analyze reasoning gaps, and manage tutoring workflows. Use when users want personalized tutoring, learning plan generation, or Socratic dialogue-based education.

Benchmarks systems on the Abstraction and Reasoning Corpus (ARC) by requiring inference of abstract transformation rules from few input-output grid demonstrations and application to novel test cases, reporting the fraction of tasks solved.

Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.

Break a stuck or complex problem into the smallest sub-question that, if answered, unlocks the next step — then answer it and repeat until the path forward is clear. Load when a problem feels genuinely stuck, when reasoning keeps circling, or when deep-thinking diagnoses a Socratic frame. Also triggers on "I keep going in circles", "what is the real question here", "help me reason through this step by step", "unstick my thinking", "recursive questioning", "what is the root question". Based on the recursive Socratic questioning method (EMNLP 2023) which outperforms CoT and Tree-of-Thought on complex reasoning tasks.

Configure and use Honcho memory with Hermes -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall, and dialectic settings.

Configure and use Honcho memory with Hermes -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall, and dialectic settings.

Scans codebases for security vulnerabilities by reasoning about code context, data flow, and component interactions, covering injection flaws, secrets exposure, authentication issues, and weak cryptography across multiple languages.

Provides domain knowledge on the Causal Dynamics Architecture (CDA), an alternative AI computing architecture based on causal graphs and Hamiltonian dynamics, with references for deep dives.

Benchmarks LLM agents fine-tuned with the Agent Data Protocol across software engineering, web browsing, OS/database tool use, and reasoning tasks, reporting unit test pass rates and task success rates.

Delivers a daily DeFi regime verdict (RISK-ON/NEUTRAL/RISK-OFF) from five named inputs, top TVL movers with causal reasoning, and a sustainable-vs-incentive yield split to distinguish real product-market fit from emissions-pumped APY.

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

Maximally Endowed Graph Architecture — λ-calculus over bounded n-SuperHyperGraphs with grounded uncertainty, conditional self-duality, and autopoietic refinement. Use when (1) simple graphs insufficient (η<2), (2) multi-scale reasoning required, (3) uncertainty is structured not stochastic, (4) knowledge must self-refactor. Pareto-governed: complexity added only when simpler structures fail validation.

Capture an Architecture Decision Record — what was decided, why, what alternatives were considered, and when to revisit. Writes a numbered ADR file to docs/adr/ in the active repo, with consistent formatting that downstream skills (improve-codebase-architecture, refactor-plan) can read. Use right after deciding something non-obvious so the reasoning isn't lost.

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.

Resolves an approved article comment task into a publishable AI markdown reply by fetching article context from a local HTTP API (with sf-cli fallback), reasoning with the selected quote and full article content, and writing the final reply to a backend-provided local result file path.

Multi-perspective dialectical reasoning with cross-evaluative synthesis. Spawns parallel evaluative lenses (STRUCTURAL, EVIDENTIAL, SCOPE, ADVERSARIAL, PRAGMATIC) that critique thesis AND critique each other's critiques, producing N-squared evaluation matrix before recursive aggregation. Triggers on /critique, /dialectic, /crosseval, requests for thorough analysis, stress-testing arguments, or finding weaknesses. Implements Hegelian refinement enhanced with interleaved multi-domain evaluation and convergent synthesis.

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.

Full ASVS 5.0 compliance assessment against a codebase and/or architecture diagrams. Reads all 346 controls from the companion CSV, performs targeted code analysis per control, and produces a complete matrix marked COMPLIANT / NON_COMPLIANT / NOT_RELEVANT — with per-control reasoning and evidence (code snippets, file:line references, diagram observations). Outputs a reviewed CSV matrix and a self-contained HTML evidence report.

Use for writing, reviewing, debugging, testing, or optimizing Python NumPy ndarray code. Trigger on array construction, shape/axis reasoning, dtypes and casting, broadcasting, indexing, copies/views, ufuncs, reductions, vectorization, random Generator, linear algebra, FFT, masked/structured arrays, memory layout, or NumPy interoperability. Do not use for pandas/Polars table semantics, JAX/CuPy-only arrays, symbolic SymPy, or pure Python sequences without a NumPy boundary.

Deep Confidence Harness — a thinking, planning, and execution framework that forces structured reasoning before acting. Combines Monte Carlo scenario analysis, calibrated confidence, multi-perspective debate, and optimal path planning. Use before any complex decision, build, or task. Activates on: 'deep confidence', 'think before you act', 'plan first', 'Atlas mode', 'reason through this', 'what should I do', 'think this through', 'best approach', 'reason carefully', 'plan and execute'.

Holarchic reasoning framework implementing λ-calculus over simplicial complexes. Entities (ο) transform through operations (λ) toward terminals (τ) via the universal form λο.τ. Persistent homology captures multi-scale structure; sheaf theory ensures local-to-global consistency. Use when knowledge requires: (1) homoiconic self-reference where structure mirrors content, (2) scale-invariant holonic decomposition, (3) topological invariants preserved across transformations, or (4) formal Lex-style axiom systems over property graphs.

AI Agent personality diagnosis and configuration system based on MBTI framework. Use when users want to (1) test/diagnose an Agent's personality type, (2) understand the gap between Agent's actual personality and user's desired personality, (3) generate configuration recommendations to adjust Agent behavior, (4) customize Agent's communication style, proactivity, reasoning approach, or execution patterns. Supports both free tier (quick assessment) and premium tier (full 93-question assessment with detailed diagnostics).

autonomous architecture design and refinement for mermate using iterative copilot guidance, local reasoning, repeated low-cost render validation, and final max-quality render selection. use when building, stress-testing, refining, decomposing, validating, or evolving system architectures from simple ideas, complex problem statements, markdown specifications, mermaid drafts, or ambiguous design notes. especially useful when chatgpt should act like a professional architect that thinks step by step, uses mermate repeatedly, compares intermediate diagrams, and decides when to continue refining versus when to finalize with max mode.

Knowledge-graph-augmented retrieval. Entity and triple extraction, graph construction (Neo4j, LlamaIndex PropertyGraphIndex), hierarchical community summarization (Microsoft GraphRAG), personalized PageRank (HippoRAG), multi-hop traversal retrieval, and hybrid graph + vector pipelines. USE WHEN: user mentions "GraphRAG", "HippoRAG", "knowledge graph RAG", "entity extraction", "multi-hop reasoning", "Neo4j RAG", "LlamaIndex property graph", "LangChain graph retriever", "triple extraction", "community summarization" DO NOT USE FOR: vanilla vector RAG - use `rag-patterns`; multimodal inputs - use `multimodal-rag`; production indexing ops - use `rag-production`; hallucination checks - use `rag-guardrails`

Use this skill when a user asks for SEO keyword research, keyword discovery, search volume analysis, keyword difficulty, search intent mapping, topic clusters, content opportunities, competitor keyword gaps, or a keyword strategy for a domain, URL, product, market, or seed topic. When a website is provided, crawl and interpret the site first, then use AIsa API access to DataForSEO keyword, SERP, trend, Labs, and OnPage endpoints plus AIsa LLM reasoning to find non-brand keyword opportunities. Use when: the user needs web search, research, source discovery, or content extraction.