其他技能

Use when you have a written implementation plan to execute in a separate session with review checkpoints

中文简介正在准备中。当前显示原文说明。

See the difference between Chat and Cowork with a live side-by-side comparison for understanding why Cowork is built differently. Use when evaluating AI tools, for comparing chat versus agent capabilities, during an AI tool decision, when switching from ChatGPT or Claude Chat, or when the user says "what is different about cowork", "cowork vs chat", "why not just use chatgpt", "show me the difference", "compare chat and cowork", or "why should I use cowork instead of chat".

中文简介正在准备中。当前显示原文说明。

Sets up a complete per-client workspace in Cowork with isolated context, preferences, deliverable templates, running notes, decision log, and automatic status reporting. For consultants, agencies, and professional services. Useful when onboarding a new client, during engagement kickoffs, for organizing existing client relationships, and when multiple clients need isolated context. Use when the user says "set up a client", "new client project", "client system", "client context", "client workspace", or "onboard a client".

中文简介正在准备中。当前显示原文说明。

Builds a personal voice profile so Cowork writes the way you write — not like a generic AI. Use when personalizing your writing style, for capturing your communication patterns and tone, during setup after getting generic-sounding output, when training Cowork to match your voice, or when the user says "teach claude my voice", "my writing style", "output doesn't sound like me", "brand voice", "personalize output", "make it sound like me", "it sounds too formal", "it sounds too robotic", "can cowork match my tone", or "how do I get cowork to write like me".

中文简介正在准备中。当前显示原文说明。

Sets up a file-based memory system so Cowork always knows who you are, how you work, and where your projects stand. For eliminating repetitive re-introductions at session start, when building persistent context across multiple projects, or during initial Cowork onboarding. Use when the user says "claude doesn't remember me", "memory system", "persistent context", "why does it forget", "remember my preferences", "I keep re-explaining myself", or "how do I make Claude remember things".

中文简介正在准备中。当前显示原文说明。

A 15-minute guided setup that teaches Cowork who you are, how you work, and what tools you use — so every result feels tailored instead of generic. Use when setting up Cowork for the first time, for personalizing your workspace preferences, during onboarding after your first session, when configuring your tools and context, or when the user says "set up cowork", "configure cowork", "why is cowork giving me generic results", "cowork setup", "personalize cowork", "make cowork know me", "cowork feels like chatgpt", or "how do I get better results from cowork".

中文简介正在准备中。当前显示原文说明。

Think out loud about a problem, decision, or approach — Socratic friction to help you find clarity, not sympathy

中文简介正在准备中。当前显示原文说明。

Write a client update — identify what was done, what's next, and surface risks before they become surprises. End of day, start of day, or end of week.

中文简介正在准备中。当前显示原文说明。

Prepare to deliver difficult technical news to a client — a conversational prep session before the hard conversation happens

中文简介正在准备中。当前显示原文说明。

Use when you have a written implementation plan to execute inline in the current session with review checkpoints. Prefer subagent-driven-development when sub-agent dispatch is available.

中文简介正在准备中。当前显示原文说明。

Project scaffolding templates for new applications. Use when creating new projects from scratch. Contains 12 templates for various tech stacks.

中文简介正在准备中。当前显示原文说明。

A template for creating new modular and scalable agent skills.

中文简介正在准备中。当前显示原文说明。

Find one insight that eliminates multiple components - "if this is true, we don't need X, Y, or Z"

中文简介正在准备中。当前显示原文说明。

Systematically trace bugs backward through call stack to find original trigger

中文简介正在准备中。当前显示原文说明。

PowerShell Windows patterns. Critical pitfalls, operator syntax, error handling.

中文简介正在准备中。当前显示原文说明。

Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?"

中文简介正在准备中。当前显示原文说明。

Spot patterns appearing in 3+ domains to find universal principles

中文简介正在准备中。当前显示原文说明。

Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?"

中文简介正在准备中。当前显示原文说明。

Dispatch to the right problem-solving technique based on how you're stuck

中文简介正在准备中。当前显示原文说明。

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

中文简介正在准备中。当前显示原文说明。

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).

中文简介正在准备中。当前显示原文说明。

Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.

中文简介正在准备中。当前显示原文说明。

Performance profiling principles. Measurement, analysis, and optimization techniques.

中文简介正在准备中。当前显示原文说明。

Bash/Linux terminal patterns. Critical commands, piping, error handling, scripting. Use when working on macOS or Linux systems.

中文简介正在准备中。当前显示原文说明。