“thinking”的搜索结果

Operating discipline distilled from Claude Fable 5 for sessions and subagents on weaker models (Opus 4.x, Sonnet 5/4.x, Haiku 4.5) doing agentic coding. Load it at the START of any non-trivial task when not running on Fable 5: debugging, refactoring, changes across 2+ files, or unfamiliar code; and instruct a subagent on Opus/Sonnet/Haiku to read this skill with a non-trivial assignment. Triggers include "think like Fable", "fable-mode", "turn on discipline", "work carefully", dispatching a subagent on a weaker model, and repeated mistakes or rework in the session. NOT needed for trivial edits (rename, typo, one-liner) or purely conversational answers.

中文简介正在准备中。当前显示原文说明。

通过逐轮提问深入检验计划或想法，为问题附上建议答案，整理决策之间的依赖关系，确认模糊前提和待定事项，在行动前建立共同理解。

• 执行前检验计划
• 明确想法所依赖的前提
• 整理决策之间的依赖关系

审查现有代码的一个部分，从设计决策记录、实现惯例、缺失功能和技术选型四个方面整理问题，并推进计划、测试、修复及再次审查。

• 审查接手的现有代码
• 在开发途中引入ECC流程
• 添加功能前重新评估模块

检索学术与技术文献，按预设标准筛选并综合比较。记录检索过程和排除理由，梳理研究分歧与未解问题，区分证据置信度并核查引用，形成可追溯的综述。

• 了解研究主题的整体情况
• 撰写记录检索步骤的文献综述
• 整理研究分歧与未解决问题

使用统一标准审阅论文和研究计划，检查研究方法、证据、引用及文章结构，并说明评分依据、修改优先级和下一步需要修改的内容。

• 投稿前审阅论文
• 检查引用是否支持论点
• 评估研究方法与局限

将语音输入或长篇随想整理为目标、决定和待解问题，同时保留中途改变的方向与暂缓话题。单独列出智能体的推测，在开始工作前确认理解。

• 整理通过语音表达的构想
• 开始工作前确认需求理解
• 收集跨多条消息的想法

通过对话深入梳理模糊的想法，比较多个方案，形成可付诸行动的构想，并明确目标人群、成功标准、待验证假设、最小范围和不做的事项。

• 把模糊的服务或功能想法具体化
• 确定方向前比较其他方案
• 制定计划前验证假设

通过逐一提问澄清模糊需求，同时展示智能体对用户意图的推测，梳理受众、目的、成功标准、限制和不包含的内容，最终形成经用户明确确认的意图说明。

• 澄清模糊需求背后的目的
• 梳理受众和成功标准
• 确定难以兼顾的需求的优先级

Explore ideas, investigate problems, and clarify requirements in an OpenSpec project through discussion grounded in existing code and specifications. Compare approaches, sketch diagrams, and identify open questions, with planning documents saved only within an explicitly approved scope.

中文简介正在准备中。当前显示英语简介。

• Clarify the scope of a loosely defined feature idea
• Compare technical approaches using project evidence
• Revisit design choices when implementation gets stuck

Understand customer decisions and turn psychological principles into practical marketing ideas. The skill explains relevant thinking tools and behavioral patterns, then suggests ethical applications for pricing, trust, messaging, onboarding, retention, and deciding which marketing problems to address first.

中文简介正在准备中。当前显示英语简介。

• Exploring why customers hesitate to purchase
• Reviewing how prices and plans are presented
• Building trust through testimonials and evidence

Examine an early idea through focused questions from different perspectives. Test assumptions, expose weak points, and clarify decisions so you can strengthen the idea, reject it, or understand it better, with a report recording the outcome.

中文简介正在准备中。当前显示英语简介。

• Clarify an early idea and its assumptions
• Challenge an idea from buyer, competitor, or critic perspectives
• Check a proposed change against existing project materials

Assess scientific claims by examining study design, statistics, bias, and evidence quality. Use structured appraisal frameworks to identify supported conclusions, explain uncertainties, and propose practical improvements with concerns traced to specific evidence.

中文简介正在准备中。当前显示英语简介。

• Check whether a paper's conclusions match its evidence
• Review study design before collecting data
• Identify statistical problems and potential biases

Explore difficult decisions, research trade-offs, or creative challenges through several simulated perspectives. Separate facts, assumptions, and values, compare competing priorities, and produce a conditional recommendation with unresolved questions, a next step, and conditions that would change the choice.

中文简介正在准备中。当前显示英语简介。

• Comparing business options with competing priorities
• Reviewing trade-offs in a research plan
• Challenging assumptions behind a preferred choice

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.

中文简介正在准备中。当前显示英语简介。

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

Use a browser whiteboard to sketch ideas, draw workflows, and add sticky notes, then share them with Copilot CLI. The agent interprets the image and text to discuss your thinking and suggest next steps.

中文简介正在准备中。当前显示英语简介。

• Discussing a workflow drawn on a whiteboard
• Organizing ideas captured on sticky notes
• Turning a sketch into a memo or checklist

Use a constructive thinking partner to review assumptions, separate evidence from interpretation, and test alternative explanations. Refine conclusions and wording so claims match the available evidence and support decisions under uncertainty.

中文简介正在准备中。当前显示英语简介。

• Checking assumptions before an important decision
• Reviewing whether evidence supports a conclusion
• Testing alternative explanations and counterexamples

Review decisions through Nassim Nicholas Taleb’s thinking about rare, severe losses and who bears their consequences. Identify hidden dependencies, compare potential gains with losses, and examine whether a strategy benefits from disruption or becomes more vulnerable.

中文简介正在准备中。当前显示英语简介。

• Examining rare events that could cause irreversible losses
• Checking whether advisers bear the consequences of their advice
• Finding dependencies that make a business fragile

Examine AI research directions and safety strategies through thinking models drawn from Ilya Sutskever’s public statements. The skill checks current facts when needed and presents a concise judgment with an everyday analogy.

中文简介正在准备中。当前显示英语简介。

• Assessing AI research directions
• Examining model scaling and data limits
• Discussing AI safety strategies

Plan mobile app screens and interactions around touch, performance, offline use, and platform conventions. The skill guides design decisions and implementation checks for React Native, Flutter, and native iOS or Android apps.

中文简介正在准备中。当前显示英语简介。

• Planning screens for one-handed use
• Reviewing slow lists and animations
• Designing loading, error, and offline states

Apply psychology and behavioral science to marketing decisions. The skill selects relevant thinking models, explains customer behavior, and suggests ethical changes to pricing, messaging, purchase journeys, and campaign priorities.

中文简介正在准备中。当前显示英语简介。

• Understand why customers hesitate to buy
• Review pricing plans and how prices are presented
• Simplify signup and purchase journeys

Configure Claude Code and improve how you assign coding tasks. This guide provides a CLAUDE.md template, practical prompting examples, debugging approaches using logs, and a workflow for making and checking small changes.

中文简介正在准备中。当前显示英语简介。

• Set up project guidelines in CLAUDE.md
• Write clearer requests for coding tasks
• Investigate unexpected agent behavior using logs

After explicit opt-in, captures original ideas in the user's exact words and identifies people and companies mentioned in conversations. Stores them in linked knowledge pages with sources, dated facts, and a brief capture log.

中文简介正在准备中。当前显示英语简介。

• Preserving ideas expressed during conversations
• Adding context to people and company pages
• Connecting ideas with related people and concepts

Trace how one idea developed across stored notes and records. Identify its earliest documented mention, clearest expression, changes of stance, contradictions, abandoned branches, and current form, with dated evidence and explicit gaps where sources are missing.

中文简介正在准备中。当前显示英语简介。

• Trace an idea to its earliest documented mention
• Review changes and contradictions in your thinking
• Clarify your current view on a topic

Explore product problems, generate alternative solutions, and challenge the assumptions behind an idea through conversation. It helps product managers compare directions, identify weak points, and choose questions or experiments to investigate before committing to development.

中文简介正在准备中。当前显示英语简介。

• Exploring the user problem behind a feature request
• Generating alternatives to an initial product idea
• Testing the assumptions that could undermine an idea