'defi' 검색 결과

Evaluate a Claude Managed Agent against a written rubric, a set of checkable criteria, and guide improvements within a fixed attempt limit. After a version passes, prepare separate evaluation cases to check performance beyond the examples used for revision.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Defining checkable criteria for agent outputs
• Improving an agent within a fixed attempt limit
• Testing a passing version on unseen cases

Turn a vague intention into a concrete goal with clear scope, measurable success criteria, and evidence of completion. Check existing goals before creating one, so the agent has a specific outcome to pursue without duplicating active work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a vague intention into a measurable goal
• Define completion criteria for a bug fix
• Set performance targets and measurement methods

Build a product launch strategy from product and market research. Define marketing channels, audience messages, measurable goals, and launch milestones, then organize them into a practical 90-day roadmap with risks and decision points.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a new product launch
• Preparing to enter a new market
• Choosing marketing channels and messages

Use customer research, surveys, and usage data to define an ideal customer profile: the customers most likely to gain value, stay, and expand. Summarize their characteristics, buying behavior, goals, needs, and fit criteria to guide sales and marketing priorities.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Defining ideal customers from surveys and interviews
• Finding patterns among customers who stay and expand
• Aligning sales and marketing priorities

Review skill and agent definitions for structural issues and whether their instructions meet expected behavior. Four modes cover structure, test specifications, category criteria, and coverage reports that reveal missing specifications or checks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check one skill or all skills for structural issues
• Compare skill or agent instructions with a test specification
• Review definitions against category criteria

Develop independent solutions to a defined problem, compare them against shared requirements, and combine useful contributions into a coherent recommendation. An independent assessment and evidence checks support the selection, while unresolved tradeoffs and verification needs remain explicit.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing concrete solutions to a defined problem
• Developing rough options before choosing an approach
• Comparing architectural or product proposals

Turn a brief idea into a task brief an AI agent can execute independently. Ground it in investigation, define scope and acceptance checks, and include progress tracking and recovery instructions in a brief ready for `/goal`.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a rough idea into an executable agent brief
• Defining measurable completion criteria for development work
• Preparing a research or technology-selection assignment

Draft contracts, legal memos, court documents, and policies in Word format. Build each section with checks for defined terms, references, and citations, using CourtListener and eCFR research tools when case law or regulations are needed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Drafting contracts and nondisclosure agreements
• Preparing legal memos with case research
• Creating terms of service and privacy policies

Write and review launch prompts for agents working autonomously for hours or days. Define successful deliverables, excluded partial results, stopping rules, worker handoffs, and evidence-based review requirements so completion can be assessed against explicit criteria.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning vague requests into precise task briefs
• Defining stopping rules for long autonomous runs
• Specifying deliverables for parallel workers

Connect Solidity security analyzers to Claude Code through MCP, a tool connection interface. Combine findings into a report sorted by severity, review contract changes, and generate tests for conditions that should always hold.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Combining findings from multiple Solidity analyzers
• Reviewing security issues in contract upgrades
• Generating Foundry invariant tests

Audit Solidity contracts in Foundry projects before deployment using code analysis, randomized tests, manual review, and private key checks. Produces a JSON report with findings, remediation, test coverage, and a pass or fail deployment decision.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing Solidity contracts before deployment
• Adding fuzz and invariant tests for contracts that move funds
• Reviewing private key storage and deployment scripts

Set up recurring agent work for issues, tickets, or small fixes. The skill tests one real item first, then defines a repeatable procedure, tracks work to prevent duplicates, and holds outputs for human review.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recurring preparation of fixes for Sentry issues
• Drafting replies to Front tickets
• Preparing small performance improvement PRs

Turn a feature idea into a specification through structured questions about users, business goals, and technical constraints. Produce requirements, user stories, testable acceptance criteria, and an implementation checklist, including performance, security, and error handling.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Defining requirements for a new feature
• Clarifying vague feature requests
• Writing testable acceptance criteria

Create or review SECURITY.md guidance so Codex Security understands what to examine, which protections must hold, and what is excluded. Compare existing policies with repository evidence and preview proposed changes before writing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Define security review scope for a repository
• Document required security protections
• Check whether existing guidance matches the code

Build Web3 applications, combining blockchain contracts with a user interface, in a defined sequence. Organize directories, define interfaces, implement and test contracts, configure wallet connections, build components, and prepare deployment scripts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Planning a Web3 project's directory structure
• Defining interfaces for external protocol integrations
• Building wallet-connected contract interaction screens

Writes and reviews Lean 4 proofs, machine-checked arguments for mathematics or specifications. Follows Mathlib conventions to organize definitions and lemmas, fill proof gaps, refactor lengthy proofs, and establish automated checks for unproved claims and style.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Formalizing mathematics or specifications in Lean 4
• Filling sorry placeholders in proofs
• Splitting long proofs into reusable lemmas

Turn a major product initiative into a testable hypothesis with a clear target user and expected outcome. Define small experiments, measurable success criteria, and an evaluation timeframe before committing to full development.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarifying the expected outcome of a major initiative
• Designing small experiments before full development
• Defining measurable success criteria and deadlines

Create and maintain a reusable skill that records metric definitions, trusted data sources, and analytical caveats. Preserve supporting evidence and unresolved conflicts so future Data Analytics work can consult and cite the same documented context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Save shared metric definitions for future analyses
• Document trusted sources and conflicting definitions
• Update or repair an existing semantic layer

Create or review SECURITY.md guidance so Codex Security understands what to examine, which protections must hold, and what is excluded. Compare existing policies with repository evidence and preview proposed changes before writing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Define security review scope for a repository
• Document required security protections
• Check whether existing guidance matches the code

Predict the structure and binding of one defined protein, RNA, DNA, or ligand complex with Boltz. The workflow covers cost confirmation, job submission, result downloads, and summaries of structure and binding metrics.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Predicting the structure of a defined molecular complex
• Docking one ligand to a protein
• Assessing protein–protein binding

Create and manage prediction markets on Solana, where participants trade YES or NO outcome tokens. Support includes direct peer bets, social media metrics, custom result authorities, market settlement, and redemption of winning positions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a prediction market around social media metrics
• Build direct peer-to-peer betting markets
• Let an AI agent determine market outcomes

Audit custom subagents, the specialized assistants used by Claude Code and Codex. Check whether definitions load, identify overlapping roles, review model choices and tool access, and receive scores with prioritized fixes and optional confirmed edits.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking agents when joining a project
• Reviewing newly added or imported agents
• Investigating delegation to the wrong agent

Locate function and class definitions, usages, and relevant files with ripgrep, using text patterns and file filters. Search Git history to see when text appeared or disappeared and investigate who changed specific lines.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding function or class definitions
• Locating usages of a particular function
• Narrowing searches by file type or path

Develop a vague research interest into a specific question and plan. Use 5W1H prompts, literature reviews, and analysis of unanswered questions to define hypotheses, required evidence, suitable methods, and a concrete next step.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Exploring research ideas with 5W1H prompts
• Reviewing literature to find unanswered questions
• Defining hypotheses and evidence requirements