'preferences' 검색 결과

Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a model on instruction and response examples
• Align responses using preferred and rejected answer pairs
• Build a training pipeline using human feedback

Help Claude interpret workplace shorthand by storing people, acronyms, project names, and preferences in local files. Keep frequent references in CLAUDE.md and detailed context in memory/, so requests can be understood using recorded workplace knowledge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording internal acronyms and terminology
• Linking nicknames to people and roles
• Looking up project codenames and background

Explicitly save debugging discoveries, project conventions, and working preferences to Claude's persistent project memory. The skill checks for duplicate notes, keeps entries concise, and suggests moving enforceable rules into CLAUDE.md when appropriate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserving hard-won debugging discoveries
• Recording undocumented project conventions
• Remembering tool-specific commands and pitfalls

Set up shared SEO project information in OpenSEO through a guided interview. Save website scope, goals, positioning, competitors, key pages, and writing preferences, then check connections and prepare Google Search Console data for later workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up shared information for a new SEO project
• Update goals and competitor information
• Prepare Google Search Console data

Review changed test specifications for cases where broken behavior could still pass. Report concrete gaps supported by the changes and implementation, with a minimal fix and an observable condition for resolving each advisory finding.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing whether changed tests prove their stated behavior
• Finding UI tests that bypass the interaction being tested
• Checking whether save tests observe newly saved data

Keeps work preferences, corrections, and ongoing goals in a personal Kortix folder so agents can refer to them across sessions. Users can inspect, edit, or delete the saved Markdown files and request specific details be forgotten.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Keeping response preferences across sessions
• Remembering corrections to the agent's approach
• Carrying ongoing goals and deadlines into future tasks

Guide file storage and context retention in Kortix shared folders. Identify accessible folders, save lasting outputs, keep user and team notes across sessions, and handle conflicting file copies according to the documented sharing and synchronization rules.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving outputs for use after the session ends
• Reusing user notes and preferences across sessions
• Keeping shared context for the team

Create and review GSAP code that animates webpage elements and SVG graphics. Covers movement, fades, easing that controls speed changes, staggered effects, playback controls, and adaptations for screen size and reduced-motion preferences.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding entrance animations to webpage elements
• Animating multiple items with staggered starts
• Adjusting motion for desktop and mobile screens

Read and change Superset desktop preferences through its command-line tool, without opening settings. Adjust fonts, terminals, notifications, and Git options, or create and install custom color themes from JSON files, with local operation and no login required.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Switching themes and increasing terminal text size
• Creating and installing a custom color theme
• Adjusting notification volume and sounds

Guide language model training with TRL, from learning to follow instructions to matching human preferences. Covers method selection, training data, reward models that score responses, evaluation, and adjustments for memory limits or unstable training.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train a model on instruction and response examples
• Align responses using preferred and rejected answer pairs
• Build a training pipeline using human feedback

Set up a new project by gathering context, optionally researching the domain, defining requirements, and building a roadmap. It creates planning files that record the project’s background, workflow preferences, phased structure, and ongoing state.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarify a new project idea through questions
• Define requirements and a phased roadmap
• Save project context and workflow preferences

Build a developer profile from past sessions or a questionnaire, then generate files and settings that personalize Claude's responses. Choose which outputs to create and compare changes when refreshing an existing profile.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Documenting development habits and preferences
• Building a profile through a questionnaire
• Generating settings to personalize Claude's responses

Help Claude interpret workplace shorthand by storing people, acronyms, project names, and preferences in local files. Keep frequent references in CLAUDE.md and detailed context in memory/, so requests can be understood using recorded workplace knowledge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording internal acronyms and terminology
• Linking nicknames to people and roles
• Looking up project codenames and background

Set up a litigation practice profile through an interview tailored to your role and the side you represent. Record risk preferences, writing conventions, and working context in CLAUDE.md for later litigation tasks, and check available integrations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up a litigation plugin for the first time
• Tailor practice settings to your role and litigation side
• Update risk preferences and document style

Update one part of an existing privacy practice profile through a guided conversation. Change risk preferences, contract review positions, contacts, privacy assessment formats, or personal data request procedures, with an explanation of how the change affects later outputs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Update privacy contacts and escalation routes
• Revise data processing agreement review criteria
• Change personal data request response procedures

Find a starting set of community legal skills through an interview about role, practice area, industry, and daily work. Review recommendations, install selected skills, and save preferences for trusted sources, updates, and available integrations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing legal skills for an initial setup
• Finding a starter pack matched to daily legal work
• Setting trusted sources and license preferences

Set up an intellectual property practice profile through an interview and shared documents. Capture relevant work areas, enforcement preferences, and approval arrangements for other plugin skills, then revise the setup or recheck external connections when needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up an IP practice profile on first use
• Extract working policies from existing documents
• Revise enforcement preferences or approval arrangements

Write GSAP animations for HyperFrames compositions, from element entrances to coordinated sequences. Use timelines to organize timing, control playback, adapt motion to screen size and reduced-motion preferences, and choose animation properties suited to efficient rendering.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Animate elements entering a HyperFrames composition
• Coordinate multiple elements with timelines and staggered starts
• Adjust motion for screen size and reduced-motion preferences

Change DeepChat preferences through conversation, including theme, interface language, font size, sound effects, and whether copied text includes COT details. Dedicated tools apply supported changes, while other requests open the relevant settings section with guidance.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Switch DeepChat to a dark theme
• Change the interface language or font size
• Turn off DeepChat sound effects

Recall earlier work and organize lasting preferences, project facts, outcomes, and lessons. The skill distinguishes concise memory from original records, reusable procedures that belong in skills, and recurring requests that need scheduled tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resume earlier work using remembered context
• Save lasting preferences and project conventions
• Find exact wording and evidence in past records

Coordinates a mathematical modeling competition project from planning to final checks. It records formatting and language preferences, creates a plan and task checklist, and calls dedicated skills for modeling, coding, diagrams, paper writing, and verification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting a mathematical modeling competition project
• Planning work around competition and formatting preferences
• Tracking progress across modeling and paper-writing stages

Design and refine web animations for buttons, dialogs, menus, and gestures. The skill guides timing, changes in speed, spring motion, performance, and reduced-motion preferences so transitions fit the interaction and remain responsive.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Refine dialog and menu transitions
• Adjust button press and hover feedback
• Investigate stuttering animations

Search Google images through Serper.dev and collect candidate image URLs, page links, titles, and source domains. Choose URL-only output or save raw JSON results, with country and language preferences available.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding candidate images for a topic
• Collecting links to pages containing images
• Saving image search results as JSON

Explore design options in Python when goals such as cost and performance compete. This skill guides optimization, constraint handling, and visualization of trade-offs, then helps compare candidate solutions using stated preferences.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing designs with competing cost and performance goals
• Finding solutions that meet design constraints
• Comparing optimization algorithms on benchmark problems