Results for “reasoning”

Tested reasoning approaches for Claude prompts — 18 variants across 6 categories (Analytical, Strategic, Creative, Technical, Research, Comparative). Use when the user wants a specific reasoning template — retrieving, reviewing, customizing, or combining reasoning instructions for a prompt. Trigger on: "give me the Root Cause Diagnosis approach," "show me the reasoning template for," "I need the Evidence Synthesis method," "show me analytical reasoning options," "combine reasoning approaches for," "show me all reasoning variants." Also use when a prompt produces shallow output and the fix is a reasoning upgrade. Provides 18 tested approaches for analytical, strategic, creative, technical, research, and comparison tasks. If the user is unsure which reasoning method fits, use rootnode-block-selection first if available. Do NOT use for evaluating existing prompts — use rootnode-prompt-validation if available. Do NOT use for project-level audits — use rootnode-project-audit if available.

The English summary is being prepared. Showing the original description.

Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.

• Build agent memory that reuses past experiences
• Record and assess sequences of agent actions
• Consolidate similar experiences into reusable patterns

Send proofs, planning questions, or difficult debugging tasks to DeepSeek's reasoning model. Receive the final answer and model-provided reasoning text in separate fields, with token usage reported for reviewing responses and costs.

• Requesting a mathematical proof
• Planning work that requires several reasoning steps
• Investigating root causes of difficult bugs

Build agent memory with ReasoningBank and AgentDB. Record actions and outcomes, retrieve similar experiences, assess results, and consolidate memories into reusable patterns so agents can draw on past work when making decisions.

• Build agent memory that reuses past experiences
• Record and assess sequences of agent actions
• Consolidate similar experiences into reusable patterns

Inspect Muse Code’s saved settings and defaults, then make targeted changes when explicitly requested. Explain reasoning and display options while distinguishing persistent configuration from the settings currently active in a running session.

• Check saved settings and defaults
• Change the saved reasoning effort
• Adjust reasoning summaries and output detail

Build AI agents that retain conversation history, user preferences, and useful interaction patterns with AgentDB. The skill covers persistent storage, meaning memories survive between sessions, plus retrieval, context management, and ReasoningBank integration.

• Add conversation history to a chat system
• Remember user preferences across sessions
• Reuse patterns from successful interactions

Build AI agents that retain conversation history, user preferences, and useful interaction patterns with AgentDB. The skill covers persistent storage, meaning memories survive between sessions, plus retrieval, context management, and ReasoningBank integration.

• Add conversation history to a chat system
• Remember user preferences across sessions
• Reuse patterns from successful interactions

Meta-cognitive reasoning specialist for evidence-based analysis, hypothesis testing, and cognitive failure prevention. Use when conducting reviews, making assessments, debugging complex issues, or any task requiring rigorous analytical reasoning. Prevents premature conclusions, assumption-based errors, and pattern matching without verification.

The English summary is being prepared. Showing the original description.

Retrieve compacted ReasoningBank context for cost-analysis queries and summarize retrieved memories, reported token savings, cache hit rate, and package availability. The savings figure is an estimate from the integration, not a measured comparison against a baseline.

• Retrieve compacted context for a cost-analysis query
• Review retrieved memory counts and cache hit rate
• Inspect reported token savings and their limitations

Implements the NOWAIT technique for efficient reasoning in R1-style LLMs. Use when optimizing inference of reasoning models (QwQ, DeepSeek-R1, Phi4-Reasoning, Qwen3, Kimi-VL, QvQ), reducing chain-of-thought token usage by 27-51% while preserving accuracy. Triggers on "optimize reasoning", "reduce thinking tokens", "efficient inference", "suppress reflection tokens", or when working with verbose CoT outputs.

The English summary is being prepared. Showing the original description.

Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories, adding custom categories or topic-following rules.

The English summary is being prepared. Showing the original description.

AI meta-cognitive meditation for observing reasoning patterns, clearing context noise, and developing single-pointed task focus. Maps shamatha to task concentration, vipassana to reasoning pattern observation, and distraction handling to scope-creep and assumption management. Use when transitioning between unrelated tasks, when reasoning feels scattered or jumpy, before a task requiring deep sustained attention, after a difficult interaction that may color subsequent work, or when reasoning feels biased by assumptions rather than evidence.

The English summary is being prepared. Showing the original description.

Design effective reasoning processes for AI agents and optimize decision-making strategies. Use when designing agent prompts, improving decision quality, implementing specialized reasoning modes, creating reasoning traces, or debugging agent mistakes. Covers prompting, chain-of-thought, reasoning depth, and decision evaluation.

The English summary is being prepared. Showing the original description.

Apply critical rationalist epistemology (Popper, Deutsch) to evaluate reasoning, identify errors, and refine understanding. Use when the user explicitly requests help with reasoning - phrases like "help me think this through", "does this make sense", "any flaws in this", "what am I missing", "critique this", "is this reasoning sound", "stress test this idea", "devil's advocate", or any request to evaluate arguments, identify logical problems, or improve thinking. Also use when errors in reasoning are significant enough to materially affect the user's goals, even if not explicitly requested.

The English summary is being prepared. Showing the original description.

Method for choosing and auditing an agent's reasoning_effort. Use when setting or reviewing reasoning_effort, when an agent was created with high, or when asked to cut reasoning spend. NOT for changing an agent's model (use test-model-selection).

The English summary is being prepared. Showing the original description.

Implement agents that use recorded task outcomes to choose future approaches. ReasoningBank supports matching past patterns, comparing strategies, retaining experience in AgentDB, and tracking how strategy success and learning change over time.

• Choose task strategies using past outcomes
• Compare approaches to code review or bug fixing
• Match current situations to learned patterns

Review supplied writing through twelve DHDNA dimensions, a framework for describing reasoning and expression. Receive observations supported by quotations, optional scores, and comparisons between samples, with clear limits separating textual patterns from psychological traits.

• Reflect on reasoning patterns in your writing
• Compare argumentation across selected texts
• Review how a text expresses assumptions and uncertainty

Keep chat-ui model settings aligned with the HuggingFace router. Add descriptions for newly available models, check reasoning support, enable artifact panels based on model size, and remove settings for models no longer served.

• Add newly released models to chat-ui settings
• Remove settings for models no longer served
• Check reasoning support and artifact eligibility

This skill should be used when the user asks to "decide reasoning effort", "set a thinking budget", "when to use extended thinking", "tune reasoning vs cost", or "should this task use a reasoning model".

The English summary is being prepared. Showing the original description.

临床诊断思维 (临床诊断思维 / 临床推理 (Clinical Diagnostic Reasoning) — 医生『怎么想病』的元学科:从症状/体征/检查到诊断结论的认知操作系统,从业者(临床医生/住院医/规培生,尤其全科/急诊/大内科等以未分化主诉为生的科室)、医学生与医学教育者、诊断安全与质量改进研究者、以及做医疗 AI 辅助诊断产品的人的视角。覆盖: (a) 第一性张力 — **直觉模式识别 (System 1: illness scripts 疾病脚本 / pattern recognition / gestalt, 『资深人一眼认出 aunt Minnie』) ⇄ 分析性推理 (System 2: hypothetico-deductive 假设演绎 / Bayesian 概率更新)** 的 dual-process 双过程理论 (Kahneman→Croskerry/Norman 谱系), 资深≠更会分析而是『脚本库更大+校准更好』; 更深层论战 — **『认知去偏可教 (Croskerry: bias awareness / cognitive forcing strategies / diagnostic timeout) ⇄ 偏倚标签是马后炮、知识结构才是主因 (Norman/Sherbino/Monteiro: debiasing 干预 transfer 证据弱, bias 是 hindsight 标签)』** — 本行最核心学术对垒; 『概率思维 (验前概率 × 似然比 → 验后概率, Pauker-Kassirer test/treatment threshold 阈值模型) ⇄ 穷尽式排查 (rule-out everything / 防御性医疗 / VOMIT)』; 『临床 gestalt ⇄ 结构化临床决策规则 (Wells/PERC/HEART)』; 『诊断简约 Occam's razor ⇄ Hickam's dictum (病人可以同时得 N 个病)』; 『床旁体格检查复兴 (Verghese Stanford 25 / McGee 循证体检) ⇄ 影像检验替代床旁』; (b) 方法论正典 — illness script theory (Schmidt/Boshuizen: enabling conditions/fault/consequences 三段结构), problem representation + semantic qualifiers 问题表征与语义限定词 (Bowen NEJM 2006, 把病人翻成 one-liner), hypothetico-deductive model (Elstein 1978《Medical Problem Solving》: 早期假设生成+定向检验), Bayesian 工具箱 (sensitivity/specificity/LR/Fagan nomogram/SnNout-SpPin), threshold model (Pauker-Kassirer NEJM 1975/1980), 认知偏倚分类学 (anchoring/premature closure/availability/confirmation/base-rate neglect/search satisficing/diagnostic momentum — Croskerry 偏倚清单), 去偏与元认知策略 (diagnostic timeout/cognitive forcing/Ely checklist/calibration), schema-based reasoning (Clinical Problem Solvers schemas: 按 pivot 症状走分支), reflective practice 结构化反思 (Mamede/Schmidt), 诊断错误科学 (NAM 2015 报告定义 / Newman-Toker Big Three / Hardeep Singh e-triggers / SAFER Dx 框架); (c) 行业结构与角色 — 医学生→实习/住院医 (晨会 morning report/查房被 pimping/汇报训练)→主治 attending→master clinician (NEJM CPC discussant/晨会大师如 Dhaliwal); 配套生态: 医学教育者 (clinical reasoning curriculum + 评估: script concordance test/key features exam/OSCE), 诊断安全研究者 (SIDM/AHRQ), 诊断辅助与 CDS 工具开发者 (DDx generator/AI); (d) 核心工作流 — 数据采集 (病史为王 + 循证体检 + 针对性检验影像) → 问题表征 (one-liner + semantic qualifiers) → 鉴别诊断生成 (schema / 解剖定位法 / VINDICATE-M 病因筛, 按『常见可能 × 致命不能漏 can't-miss』双轴排序) → 假设定向检验 (按 LR 选检查 / 阈值决策) → working diagnosis + 安全网 (red flags 交代 / test of time / test of treatment) → 反馈校准 (follow-up / M&M / diagnostic timeout); 教学工作流: 晨会渐进披露汇报 / CPC / SNAPPS / one-minute preceptor / virtual morning report; AI 增强工作流 (2023-2026: LLM 鉴别诊断头脑风暴 / OpenEvidence 检索 / ambient scribe 释放认知带宽 + 自动化偏倚 guardrails); (e) 产出物 — one-liner, problem list, prioritized DDx, assessment & plan (按问题分层), 晨会/CPC 汇报, M&M 复盘, 诊断不确定性沟通 (『最可能是 X, 但出现 Y 红旗立刻回来』); (f) 教育与评估 — script concordance test / key feature exam / EPA / 里程碑; 中国语境: 人卫《诊断学》教材 / 执业医师考试 / 规培结业临床思维考核; (g) 争议/批判 — debiasing 之争 (Croskerry vs Norman-Sherbino『knowledge is the cure』, 去偏 RCT 效果弱 / bias 标签不可证伪), 诊断错误率数字之争 (『10-15%』经典估计 / Newman-Toker 79.5 万美国年严重伤害外推方法被质疑 / 尸检符合率), dual-process 二分被批过度简化 (连续谱 / 难以实证分离), 决策规则 vs gestalt (资深 gestalt 常不输 Wells 类规则 / 算法厌恶), vignette 研究外推性 + context/case specificity (推理高度内容绑定不可通用迁移 [Norman/Eva] — 对『教推理通用课』产业的根本批判), AI 辅助诊断 2023-2026 (GPT-4 在 NEJM CPC/vignette 追平或超医生 [Kanjee 2023 JAMA / Goh 2024 JAMA Netw Open『AI alone > physician+AI』悖论] / Google AMIE / OpenEvidence 爆发 vs 自动化偏倚 / 去技能化 / 真实环境验证缺失), 防御性医疗与过度检查 (incidentaloma 瀑布 / VOMIT), 体检衰亡之争, pimping 教学法争议; (h) 流派/思想谱系 — 决策科学/Bayesian 派 (Ledley-Lusted 1959 → Elstein/Kassirer/Sox/Pauker/Eddy → Brush) vs 认知心理/双过程派 (Kahneman-Tversky → Croskerry/Graber) vs 教育认知派 (Schmidt/Boshuizen illness scripts → Norman/Eva/Mamede/Durning 情境认知) vs 诊断安全/系统派 (NAM 2015 / Newman-Toker / Hardeep Singh / Graber-SIDM: 错误=系统×认知共因) vs 床旁临床派 (Osler 传统 → Tierney aphorisms / Verghese / McGee / Dhaliwal / Saint: 病史体检为王 + 刻意练习) vs AI/计算派 (INTERNIST-1/DXplain 专家系统 → Isabel → LLM 世代 Rodman/Topol)。不含: 具体专科治疗方案与手术决策深度 (足踝外科/种植牙等另有 skill), 中医辨证 (另有 skill), EBM 文献批判性评价方法学 (相关但本 skill 聚焦诊断推理本身), 护理诊断体系 (NANDA), 影像/病理知觉型读片训练 (相邻但独立), 精神科 DSM 结构化访谈细节, 医患沟通技巧全集 (只覆盖诊断不确定性沟通), 患者自查/自我诊断指

The English summary is being prepared. Showing the original description.

Deductive and inductive reasoning, formal and informal logical structure, validity, soundness, and rules of inference. Covers propositional logic, quantified reasoning, syllogisms, common inference patterns (modus ponens, modus tollens, hypothetical syllogism, disjunctive syllogism), and the distinction between deductive certainty and inductive probability. Use when the question is not whether a premise is true but whether the reasoning from premises to conclusion is logically valid.

The English summary is being prepared. Showing the original description.

AI dynamic reasoning balance — maintaining grounded reasoning under cognitive pressure, smooth chain-of-thought coordination, and weight-shifting cognitive load across subsystems. Use at the beginning of a complex task requiring multiple coordinated reasoning threads, after a sudden context shift or tool failure, when chain-of-thought feels jerky, or when preparing for sustained focused work that requires all subsystems in alignment.

The English summary is being prepared. Showing the original description.

Guides selection of identity, reasoning, and output approaches for Claude prompts based on task characteristics. Trigger on: "help me choose an approach," "which approach fits this task," "recommend a prompt pattern," "compare reasoning methods," "map this task to the right approach," "what combination of approaches," "which identity fits," "which reasoning method." Also trigger on symptom-phrased: "my prompt feels generic," "I don't know which approach to use," "my output lacks domain depth." Covers decision-tree logic across 8 identity approaches, 18 reasoning variants, and 10 output formats. After selection, use the relevant catalog skill if available to retrieve full templates. Activate whenever approach-selection across multiple categories is the primary decision. Do NOT use when the user already names a specific approach to retrieve (use the relevant catalog skill directly if available) or for evaluating existing prompts (use rootnode-prompt-validation if available).

The English summary is being prepared. Showing the original description.

Add two or three specific follow-up questions after actionable advice, plans, estimates, or analysis. The questions help users examine facts, reasoning, and missing context before acting, with clear exclusions and a limit of once per conversation.

• Examining assumptions behind cost or timeline estimates
• Checking reasoning behind a recommended plan
• Spotting missing context in proposals or email drafts