'opus' 검색 결과

Compare estimated AI model costs for a task using its complexity and expected text volume. Get a suitable low-cost recommendation, a cheaper but riskier alternative, and a premium option, with explicit assumptions behind the estimates.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a model for a bulk code refactor
• Comparing model costs for a security review
• Estimating costs for long-document analysis

Turn a technical choice into a structured debate between different AI model families. Assign explicit positions, launch the discussion, and summarize agreement, disagreement, and a recommendation supported by the strongest argument that survives the debate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare Redis and Memcached for session storage
• Debate monorepo versus polyrepo organization
• Examine a technical choice from opposing positions

Explore ideas and working methods through focused conversation, one question at a time. Identify recurring patterns, surprising contradictions, and distinctive approaches, then turn discoveries into named concepts and a documented session summary.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Exploring an early idea through conversation
• Explaining what makes a working method distinctive
• Naming a concept that is difficult to describe

Organize multi-step work into tasks, track dependencies and status, and save progress checkpoints. Record completed work, unfinished steps, and decision context so an agent can review the saved state and continue in a later session.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding tasks with prerequisites to a TODO list
• Saving progress at the end of the day
• Resuming interrupted work in another session

Turn a multi-step feature into an implementation plan that another engineer can follow without prior context. The plan includes exact file paths, complete code, test commands, expected results, and small, verifiable steps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a feature with multiple implementation steps
• Handing development work to another engineer or agent
• Breaking a complex refactor into verifiable tasks

Create a product requirements document for a new feature or product. Clarify users, problems, goals, and constraints, then organize prioritized requirements, acceptance criteria, implementation phases, and risks into a structured document for AI-assisted development.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Defining the scope of a new feature
• Turning a product idea into written requirements
• Documenting acceptance criteria and priorities

Assess whether a multi-agent workflow justifies its coordination costs. Examine handoffs, lost context, and distinct contributions, then compare the setup with one capable agent to recommend keeping, simplifying, or restructuring it.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a workflow before adding another agent
• Finding costly handoffs in a slow workflow
• Checking whether agent agreement adds useful evidence

Sort incoming issues and pull requests, verify their claims, and assign clear triage states. Record missing information, decisions needed, and actionable handoff notes so maintainers can see which items are ready for work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Sorting a backlog of issues and pull requests
• Reproducing a newly reported bug
• Identifying missing details in an unclear report

Read project state and roadmap files to show the current phase, progress, blockers, and suggested next actions. Summarize recent work across sessions and suggest lasting project knowledge to add to CLAUDE.md.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking project progress and the current phase
• Identifying blockers and next actions
• Reviewing recent work across sessions

Apply safeguards when analyzing external articles or posts. Validate URLs, limit fetched content, label source text as untrusted data, and clean analysis output so embedded instructions are treated as material rather than commands.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking external URLs before fetching content
• Preparing article or post analysis
• Passing untrusted text to subagents

Record the goal, success criteria, boundaries, and constraints of a complex task in a persistent document. Define human and AI responsibilities, consult the record during work, and check the final result against the original intent.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying goals before a complex task
• Defining scope and constraints
• Assigning human and AI responsibilities

Bring project Markdown documentation into line with code changes. Update factual references such as paths, versions, and counts, check consistency and document links, and reflect the documentation work in the pull request description.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Updating documentation after code changes
• Checking versions and counts across documents
• Adding release notes to CHANGELOG

Investigate reproducible bugs by recreating symptoms, testing one possible cause at a time, and checking fixes in both a simplified test case and the original scenario. Retry limits keep unsuccessful fixes from continuing unchecked.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a reproducible bug
• Checking a fix in the original scenario
• Reconsidering causes after failed fixes

Pick up where you left off from a previous session — use after context resets, compaction, or new conversations

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Run repeated rounds of code fixes, performance improvements, or other refinements with defined goals and progress tracking. Evaluate each round, stop when appropriate, and optionally use numeric measurements to keep improvements or roll back regressions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Repeat fixes and tests until all tests pass
• Improve response time toward a target
• Refine error messages against clarity criteria

Gather advice from multiple language models assigned different roles, then combine their proposals and critiques into a recommendation. Set budget and depth limits while retaining disagreements, minority views, and risks for decisions or implementation planning.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing options before a decision
• Reviewing code or strategy from several perspectives
• Preparing an implementation plan with risks

Examine an existing plan, decision, or design through one question at a time, each with a suggested answer. Clarify assumptions, contradictions, and dependencies, then summarize agreed decisions, needed changes, and unresolved blockers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Examine a plan before committing
• Untangle decisions that depend on each other
• Clarify an uncertain project scope

Finish a development branch by running tests and reviewing changes, then choose whether to create a pull request, merge locally, keep the branch, or discard it. Optional version and changelog updates support release preparation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a pull request after implementation is complete
• Merge a tested branch into the base branch locally
• Update the version and changelog before shipping

Test one risky assumption through a prototype with an agreed deadline, hypothesis, and success signal. Record observations and the source revision, then return a keep, discard, or inconclusive verdict with the status of each artifact.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Testing one uncertain assumption before implementation
• Setting a deadline and success signal for a prototype
• Deciding whether to keep or discard prototype results

Detects whether a task concerns software development or research and strategy by examining the request and project files. Workflow skills can use the result to choose agents, output formats, and review criteria suited to the work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Switching between coding and strategy work in one project
• Choosing output formats for research or implementation
• Overriding an incorrect automatic context detection

Analyze reference articles and social posts to uncover structure, persuasive techniques, and writing patterns. Turn the findings into reusable templates, opening patterns, and interview questions for planning new content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare the structure of reference articles
• Extract opening patterns from social posts
• Build a reusable newsletter template

Evaluate feedback from reviewers, CI bots, or other AI agents against the actual code and requirements. Apply valid fixes one at a time, verify each change, and explain disagreements using evidence from callers, tests, or existing conventions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assess whether a review comment requires a code change
• Respond to feedback from CI bots or AI reviewers
• Explain disagreements with evidence from the code

Write or review skills for a consistent process across runs. Check activation conditions, ordered steps, completion criteria, and reference placement, then identify unclear instructions, overlapping triggers, and content that belongs in an existing skill.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Define clear steps and completion criteria for a new skill
• Investigate inconsistent behavior across skill runs
• Check for overlapping skill activation conditions

An early-stage framework for documenting an existing product’s design and architecture. Command parsing, output setup, and metadata generation are implemented; extracting colors, components, APIs, and architecture remains in progress or planned.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Plan documentation for an undocumented application
• Define output formats for colors and spacing
• Plan component and API inventories