'improve' 검색 결과

Improve an existing agent SKILL.md through one gated cycle: select the target (default this skill), snapshot the committed baseline, diagnose against skill-design-principles plus four rubric dimensions, apply exactly one focused change, and ship only if a different agent than the author PASSes with quoted evidence. Use when the user says "improve this skill", "improve-skill", "iterate on SKILL.md", or "apply skill-design-principles to a skill". Do not use for code slop over a duration (anneal), generic timeboxed work (timeboxed-iterating), graph orchestration (workgraph), metric hill-climb on a codebase (autoresearch), or stripping slop from existing prose (catalog-deslop).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Deliberate system-improvement loop — audit your own Claude Code setup (rules / memory / skills / MCP / agents / registry), evaluate incoming tools via /vet, adopt the worthwhile ones with discipline (backup → verify), and record every decision. Use when bringing in a tool/idea/collection to improve the setup, or when doing a tooling-improvement pass. Triggers — "upgrade the workflow", "audit our setup", "let's improve the tooling", "evaluate this for us", when handed a post/repo/reel with a tool.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Webアプリの準備→要件定義→設計→実装→公開→品質ゲートを実行する内部オーケストレーター。Claude Codeの /build-app /improve-app、Codexの $build-app / $improve-app から明示的に委譲された場合、custom agent起動時、または利用者が $app-orchestrator を明示した場合だけ使用する。一般のアプリ相談から暗黙起動しない。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design a self-improvement loop for a shipped product's AI agents — production traces feed evals, evals feed improvement proposals (prompts, playbooks, retrieval configs), and a human approval gate promotes changes with rollback. Technique-agnostic: chooses per project between ACE-style evolving playbooks, GEPA/MIPROv2 offline optimization, or simple eval-driven iteration via references/techniques.md. Load when the user asks to make my product's agents self-improving, learn from production traces, add a learning loop, evolve prompts or playbooks safely, promote agent improvements, or GEPA-style optimization. NOT harness-evolution (that improves the coding agent), NOT experimentation (product A/B tests), NOT agent-run-retro (dev-phase manual retros — this skill is the production-scale continuation).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

검색엔진이 사이트를 더 쉽게 찾도록 기술 문제, 페이지 제목과 설명, 구조화 데이터, 표시 성능을 점검합니다. 페이지별 개선안을 만들고 구현을 진행합니다.

• 검색엔진에 페이지가 등록되지 않는 원인 조사
• 제목과 설명, 본문 제목 구조 개선
• 글이나 상품 페이지에 구조화 데이터 추가

AI 에이전트가 정확성·완전성·명확성·실행 가능성·간결성의 다섯 기준으로 결과물을 자체 평가합니다. 근거가 있는 점수와 평균, 우선순위별 개선안을 제공합니다.

• 여러 파일에 걸친 구현 후 자체 평가
• 여러 작업 단계를 마친 결과물 점검
• 설계 문서와 분석 보고서 평가

프롬프트, 정규 표현식, SQL, 짧은 코드를 평가 기준에 따라 반복 개선합니다. AI가 후보를 만들고 실패 사례를 바탕으로 더 나은 안을 찾습니다.

• 정답 예시를 기준으로 프롬프트 개선
• 테스트 통과율로 정규 표현식 조정
• 테스트를 통해 SQL과 코드 개선

모델을 고정한 채 AI 에이전트의 실행 기반을 조금씩 조정합니다. 격리 환경에서 후보를 테스트하고 결과를 측정하여 테스트를 통과하고 개선된 변경을 축적합니다.

• 모델을 고정한 채 실행 기반 조정
• 계획·문맥·재시도 정책의 변경 비교
• 테스트 없이 오프라인으로 흐름 확인

Implement features, design APIs, and improve existing code with an emphasis on readability and maintenance. The workflow covers requirements, interface design, tests written before implementation, performance improvements, and error handling.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Implement a new feature from requirements
• Refactor existing code while preserving behavior
• Design an API and document its usage

Create and improve agent skills by defining tasks, writing instructions, and testing realistic requests. Compare outputs, success rates, time, and token use, then refine the skill and its description so it triggers appropriately.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a recurring workflow into a reusable skill
• Improve an existing SKILL.md using test feedback
• Compare results with and without a skill

Write or improve marketing pages, from headlines and body text to buttons that prompt action. Preserve an existing brand voice, explain product benefits clearly, and keep claims grounded in the evidence provided.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Drafting landing page copy
• Improving headlines and action buttons
• Rewriting copy while preserving brand voice

Improve existing marketing copy while preserving its message and voice. The skill reviews clarity, evidence, specific details, and prompts to act, refreshes outdated content, and replaces formulaic AI phrasing with language grounded in available facts.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review landing page and product copy
• Make AI-written drafts sound more natural
• Refresh outdated page content

Audit App Store or Google Play listings across six areas, including text, visuals, and reviews. Get a weighted score, specific copy and image recommendations, optional competitor comparisons, and prioritized changes tailored to the store and brand maturity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing an app listing from its store URL
• Improving app titles and descriptions
• Reworking screenshots and preview videos

Organize repeated experiments to improve models, prompts, or agent systems against measurable goals. The skill records hypotheses and lessons in a persistent tree, isolates trials, and compares promising candidates using evaluation data kept separate from development.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare repeated experiments to improve model training
• Improve an agent system's measured success rate
• Test prompt changes against a fixed evaluator

Improve an existing AI agent by analyzing execution records, user feedback, and performance metrics. Refine prompts and workflows, compare original and revised versions through tests, and plan staged releases with monitoring and rollback when results worsen.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating recurring agent failures and user corrections
• Refining prompts, examples, and output formats
• Comparing original and revised agents with A/B tests

Turn recurring tasks into reusable agent skills, or improve skills you already have. Draft instructions, compare test outputs with and without a skill, review quality and resource use, and refine descriptions so skills trigger for appropriate requests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a recurring workflow into a reusable skill
• Improve an existing skill using test results
• Compare output quality, runtime, and token use

Review CLAUDE.md files, which provide project instructions to Claude Code. Receive a scored quality report covering commands, structure, and outdated guidance, then approve focused edits that keep the instructions concise and useful.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Auditing project instructions for Claude Code
• Updating outdated build and test commands
• Reviewing instructions across multiple packages

Create or improve skills for Codewhale by defining their scope, writing clear activation descriptions and workflows, organizing supporting files, and checking discovery. It also helps decide when an external integration or automatic event handler is more appropriate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a Codewhale skill for a recurring workflow
• Improve when an existing skill activates
• Choose between a skill, MCP, hooks, and a plugin

Rank problems and proposed fixes using four scored criteria: expected benefit, implementation cost, deployment ease, and risk. The skill produces a sorted priority table with scoring rationales and explains why the top three items should come first.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prioritize fixes from audit findings
• Rank improvement actions after a retrospective
• Sequence risk mitigation measures

Review and improve .NET/C# code against project conventions. Cover public API documentation, dependency injection for supplying services to classes, asynchronous operations, tests, configuration, logging, and input validation, including guidance for Semantic Kernel integrations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review C# code against project conventions
• Improve XML documentation for public APIs
• Review asynchronous operations and dependency injection

Review AWS infrastructure code and deployed resources against the six Well-Architected pillars. Produce risk-ranked findings, remediation examples, and an architecture diagram, then create GitHub issues for tracking improvements after user confirmation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review AWS infrastructure code and deployed resources
• Prioritize findings by risk
• Prepare infrastructure code remediation examples

Review module relationships and change history to identify structural improvements in a codebase. Receive ranked candidates with file references, suggested changes, and risks, plus a recommendation for where to start, without modifying code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing architecture after a batch of changes
• Investigating changes that touch too many files
• Prioritizing structural improvements