菜单
Summarize a GitHub issue and all discussion comments. Used by /kon:describe-issue (Jun). Writes sessions/<id>/issue-summary.md.
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 | github-issue-summary |
| description | Summarize a GitHub issue and all discussion comments. Used by /kon:describe-issue (Jun). Writes sessions/<id>/issue-summary.md. |
Owner: 📚 Jun (describe-issue mode)
Consumers: /kon:describe-issue
Core principles (always): follow skills/core-principles — first principles (don't hide the issue); simplest, most concise correct solution.
gh issue view <N> --json title,body,state,labels,assignees,author,createdAt,updatedAt,comments,milestone,projectItems
For URLs: gh issue view https://github.com/owner/repo/issues/N --json ...
Include every comment (issue + review discussion). Pass full thread to Jun as ISSUE_CONTEXT. Set MODE: describe-issue and ISSUE_FILE: sessions/<SESSION_ID>/issue-summary.md.
If gh fails (no auth, wrong repo), ask the user for issue text or paste — do not hallucinate comments.
Jun must write structured markdown to ISSUE_FILE and reference that path in chat output.
In issue-summary.md and echoed in chat:
# Issue: <title>
**Number**: #N
**State**: open | closed
**Labels**: …
**Author / created**: …
## Issue summary
<What the issue asks for, in plain language — 2–5 sentences>
## Discussion summary
<Chronological or thematic summary of **all** comments — who said what, decisions, disagreements>
## Consensus / decisions
<What participants agreed on, or "(none yet)">
## Open questions
<Unresolved asks, blockers, or "(none)">
## Suggested next steps
<Concrete actions for implementer or PM — optional if issue is informational only>
Chat output must include:
## Loaded memory entries
...
## Issue summary
<one-line pointer>
Written summary to `<ISSUE_FILE>`.
issue-summary.mdgh issue close or comment postingMulti-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.