'skill-router' 검색 결과

當 Codex 任務需要依小型、中型、大型或 Goal 模式選擇正確 SKILL、逐階段重新路由，或尊重使用者指定 SKILL 與輔助能力同意時使用。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Route authorized reverse engineering, security analysis, CTF challenge, and defensive testing requests to specialist skills in a local repository. This Codex adapter selects the relevant workflow and checks the task scope before target actions begin.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Selecting a specialist skill for reverse engineering
• Starting security analysis with a defined scope
• Routing CTF challenge tasks to a suitable workflow

Route reverse engineering and security tasks to a specialist skill based on the target, purpose, and available tools. Establish the case scope and authorization status, then prepare supported tools before handing off the work.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choose a specialist skill for an unfamiliar analysis task
• Route work spanning several security disciplines
• Record case scope and authorization before analysis

The index of every pro-workflow skill and command, grouped by job, with when to reach for each and whether it is human-run or auto-triggered. Use when you are not sure which skill fits, want the full map, or ask "what can this do", "which skill for X", "list the workflow".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Repo-aware recommendation manager for ctx. Scans the active repository, identifies stack and workflow signals, recommends a capped set of skills, agents, and MCP servers, and unloads helpers that no longer match the current work after user confirmation. Harnesses are recommended by the custom-model onboarding flow or loop adapters and then attach to the same recommendation layer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Alive skill router — reads the current project's stack and loads/unloads skills dynamically. Invoke at session start or when project context changes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Routes reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, and security tasks to the appropriate specialist skill. Use when a task spans modules or the correct reverse-skill entrypoint is unclear.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Meta-enforcement layer that routes EVERY agent action through the correct skill. MUST check this routing table before ANY response involving code, files, or technical decisions. Default: route to rune:cook for code tasks. Prevents rationalization, enforces check-before-act discipline.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Gingiris growth toolkit 主入口。当用户问"怎么做增长"、"怎么发 PH"、"SEO 掉了"、"写篇博客"、"分析对手"等出海增长问题时调用。 根据问题类型自动路由到对应子 skill（gr-seo-patrol / gr-blog-post / gr-ph-launch 等）。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when picking which analysis or project-analysis-* skill fits a request — routes by scope, framework, and symptom — even if the user just says 'analyze this' or 'dig into the codebase'.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when the user is unsure which skill to use or where to start. Interviews the user with targeted questions and recommends the best skill(s) from the installed library for their goal.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.