메뉴
引導使用者建立、更新、審查或最佳化高品質 Agent Skill 定義檔 (SKILL.md)，包含官方規格、description 觸發語、references/scripts/assets/evals 結構，以及 5 種核心設計模式。
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use this skill when an AI agent is executing software development, code generation, refactoring, debugging, or system architecture tasks to enforce strict harness principles, self-verification gates, non-destructive editing, context collapse defense, and human-in-the-loop boundaries.
Use this skill when the user asks to create, draft, review, format, or generate a Pull Request (PR) title and description, specify target or source branches for a repository, or convert git branch diffs into concise, high-impact, non-AI-slop PR content.
Use this skill when explaining OpenTelemetry concepts, choosing telemetry signals, planning or reviewing Collector architectures and declarative configuration, operating or troubleshooting telemetry pipelines, securing telemetry data, evaluating zero-code instrumentation, or planning Prometheus, OpenCensus, or OpenTracing interoperability and migration. Do not use it to write language SDK/API instrumentation code or custom Collector components.
Use this skill when designing, evaluating, or implementing Agent workflows, prompt chains, routing, planning, reflection, multi-agent collaboration, memory management, or other framework-agnostic LLM orchestration patterns.
Use this skill when the user asks to improve AI-assisted development reliability, AGENTS.md, skills, tests, CI, hooks, review loops, agent workflow governance, loop engineering, agent automations, worktree isolation, maker/checker separation, or external state design for long-running agents. It designs feedforward guides, feedback sensors, verification gates, human decision points, and loop architectures from repository evidence.
Use this skill when the user wants to design, implement, review, or refactor software systems conforming to Clean Architecture principles. It structures code into Domain, Application, Infrastructure, and Presentation/API layers, enforcing inward-only dependencies. It advocates rich domain models, CQRS, and the Result pattern, operating on technology-neutral concepts without database or framework bindings.
| name | generate-skill |
| description | 引導使用者建立、更新、審查或最佳化高品質 Agent Skill 定義檔 (SKILL.md)，包含官方規格、description 觸發語、references/scripts/assets/evals 結構，以及 5 種核心設計模式。 |
.agents/skills/generate-skill/reference/AgentSkillsOfficialReference.md first. Treat it as the source of truth for SKILL.md frontmatter, directory structure, progressive disclosure, description triggering, scripts, references, assets, evals, and client implementation considerations..agents/skills/generate-skill/reference/SkillCategory.md to understand 5 core design patterns:
.agents/skills/generate-skill/templates/ (including SKILL.md, evals.json, eval_queries.json, and pep723.py) to provide standard, high-quality boilerplate content to the user..agents/skills/generate-skill/reference/ReAct_vs_CLI.md when the skill involves local exploration, CLI behavior, autonomous debugging, cross-file analysis, CI/CD assistance, or another agentic operating-system workflow.SKILL.md versus references/, scripts/, assets/, and evals/. Keep SKILL.md concise and load detailed material only when needed.description, identify likely should-trigger and should-not-trigger prompts, and plan output quality checks for important or shareable skills.name)description)SKILL.md whose first line is ---.name is valid and matches the skill directory.references/, scripts/, and assets/.evals/evals.json, eval_queries.json, and non-interactive scripts) based on the loaded templates..agents/skills/generate-skill/reference/AgentSkillsOfficialReference.md, especially frontmatter validity, description trigger quality, progressive disclosure, resource paths, script safety, and eval recommendations.