菜单
This skill should be used when handling failures in pipeline command flows — Mio blocking with NEEDS_CHANGES / BLOCKED, and infinite-loop protection for repeated same must-fix. Applies to /kon:quick, /kon:team, /kon:debug.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | failure-handling |
| description | This skill should be used when handling failures in pipeline command flows — Mio blocking with NEEDS_CHANGES / BLOCKED, and infinite-loop protection for repeated same must-fix. Applies to /kon:quick, /kon:team, /kon:debug. |
Consumers: /kon:team,
/kon:quick,
/kon:debug.
Core principles (always): follow skills/core-principles — first principles (don't hide the issue); simplest, most concise correct solution.
sessions/<SID>/review.md (subagentStop hook on team/quick/debug/review).agents/Yui.md if get-task-agent has an id) — delta prompt: read review.md, fix each must-fix by number.strict-review if id exists) — delta prompt: re-read review.md, verify each prior must-fix item-by-item.See skills/teammate-flow Implementation loop — Task resume.
"Same must-fix" definition: Mio's must-fix item points to the same file + same function/section + same category of problem. Yui changing the wording or the approach but leaving the root problem in place still counts as the same item.
Multi-agent design argument — Azusa challenges Mugi's plan, Mugi revises. Used by /kon:design after exploration and initial plan draft.
Multi-agent software engineering workflow. Use this skill whenever the user types a /kon: command — including /kon:team, /kon:design, /kon:quick, /kon:debug, /kon:ask, /kon:review, /kon:review-pr, /kon:hunt, /kon:gc, /kon:research, /kon:describe-issue, /kon:begin, /kon:finish, /kon:summarize, /kon:retro, /kon:address-comments, /kon:todo, /kon:understand-codebase. Orchestrates specialized agents: Azusa (explorer), Jun (researcher), Mugi (planner), Yui (implementer), Mio (reviewer), Sawako (cleaner), Nodoka (summarizer).
This skill should be used by all kon agents at startup, before beginning work, to load relevant memory from public and repo indexes with relevance-based ordering and a 10-entry cap. Consumers: Azusa, Mugi, Mio, Jun, and any future memory-reading agent.
Convention for per-repo skill directories at ~/.kon/projects/<repo-name>/skills/<name>/SKILL.md. Each named subdirectory is one skill. Agents load all SKILL.md files as the first step before memory entries.
When requirements, code behavior, root cause, or review scope is unclear — ask the user before proceeding. Never invent facts, assumptions, or fixes. Applies to every kon stage and every agent.
Route plain-text user messages while a /kon:begin session is open. Reuse the same session JSON — never init a second session for sub-turns.