dentiny/kon

understand-codebase

Map a codebase for learning — glossary, architecture, flashcards, and quiz. Produces interactive HTML (clickable terms/diagrams + side panel) and an optional PDF.

원문 언어: 영어

kon

Multi-agent software engineering workflow. Use when the user mentions /kon: commands in plain text — 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,…

원문 언어: 영어

strict-review

This skill should be used when performing code review on a diff (whether implemented by another agent or an external PR), enforcing a strict reviewer stance, applying a mandatory 7-item golden checklist, demanding evidence, and giving specific改法 instead of…

원문 언어: 영어

design-debate

Multi-agent design argument — Azusa challenges Mugi's plan, Mugi revises. Used by /kon:design after exploration and initial plan draft.

원문 언어: 영어

kon

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,…

원문 언어: 영어

memory-loading

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.

원문 언어: 영어

repo-skill

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.

원문 언어: 영어

ask-dont-guess

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.

원문 언어: 영어

interactive-session

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.

원문 언어: 영어

orchestrator-context

Keep orchestrator chat lean — artifacts hold full agent output; orchestrator routes by file pointer only. Applies to all /kon:* commands that spawn Task subagents.

원문 언어: 영어

pre-plan-gate

Mandatory understanding check after exploration and before any Mugi planning step. Orchestrator asks high-level and implementation questions; do not spawn Mugi until answers resolve material gaps. Applies to /kon:team, /kon:design, /kon:debug.

원문 언어: 영어

session-tracking

This skill should be used by the kon orchestrator at the start of every command and after every agent step, to write a JSON session file to ~/.kon/projects/<repo-name>/sessions/ that the dashboard reads.

원문 언어: 영어

teammate-flow

This skill should be used when orchestrating the full kon teammate flow — Azusa explores, Mugi plans, Yui implements, Sawako cleans, Mio reviews. Applies to /kon:team.

원문 언어: 영어

yolo-mode

This skill should be used when the user passes --yolo to any kon command. The orchestrator proceeds autonomously through all confirmation checkpoints, accepting defaults and auto-retrying failures. Stops only when genuine human judgment is required.

원문 언어: 영어

caveman

Compressed chat output mode. Strip filler prose from orchestrator and narrator responses while keeping full technical accuracy. Apply to conversational output only — narration beats, status lines, agent summaries in chat. Never apply to structured artifact…

원문 언어: 영어

narration

This skill should be used by the kon orchestrator on every /kon command, to frame the run with Ui narration at the opening, the closing, and stuck-point beats, and to enforce the emoji prefix on every mention of a kon agent or narrator.

원문 언어: 영어

orchestrator-voice

This skill should be used by the kon orchestrator on every /kon command, alongside narration, to govern the conversational conduct of the main dialogue — AskUserQuestion widget discipline and word-choice norms.

원문 언어: 영어

bug-hunt

This skill should be used for /kon:hunt — read-only bug analysis from source code with best-effort repro SQL and test suggestions. Azusa only; no fixes, no repo writes.

원문 언어: 영어

commit-message

This skill should be used when drafting a git commit message from staged or proposed changes. Produces a user-impact subject and a concise body. Deliberately avoids motivation paragraphs (those belong in the PR description, not the commit log).

원문 언어: 영어

core-principles

Kon's two highest-priority principles for design, implementation, and review — first principles (don't hide the issue) and the simplest, most concise correct solution. Applies to every agent, skill, and workflow stage.

원문 언어: 영어

external-research

When to spawn 📚 Jun for external lookup — WebSearch/docs/APIs — vs 🎸 Azusa for codebase exploration. Used by /kon:research, /kon:team, and /kon:design.

원문 언어: 영어

failure-handling

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.

원문 언어: 영어

github-issue-summary

Summarize a GitHub issue and all discussion comments. Used by /kon:describe-issue (Jun). Writes sessions/<id>/issue-summary.md.

원문 언어: 영어

memory-propose-confirm

This skill should be used by the kon orchestrator when saving memory — from

원문 언어: 영어

model-inheritance

Task subagents must use the orchestrator's model — Cursor defaults to Composer if model is omitted. Applies whenever spawning Task subagents in kon.

원문 언어: 영어

review-pr

Holistic GitHub PR review — code diff, PR description, existing review comments, and linked issues. Used by /kon:review-pr (Mio). Read-only; no gh pr merge or code edits.

원문 언어: 영어

session-retro

This skill should be used by the orchestrator at the end of pipeline commands (team, quick, design, debug, gc, address-comments) after /kon:summarize, to propose session learnings for public or repo memory with human confirmation before write.

원문 언어: 영어