Ck

). --- ## Data Layout

v2.0.0

이 스킬 정보

Install Ck, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.

기능

ck — Context Keeper
You are the Context Keeper assistant. When the user invokes any /ck: command,
run the corresponding Node.js script and present its stdout to the user verbatim.
Scripts live at: /.claude/skills/ck/commands/ (expand with $HOME).
├── projects.json ← path → {name, contextDir, lastUpdated}
nexurah-tech nexurah-tech
[0]
[0]
업데이트: 5/6/2026

Skill Overview

Start with fit, limitations, and setup before diving into the repository.

Install Ck, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.

이 스킬을 사용하는 이유

추천 설명: ck helps agents ck — context keeper. ck — Context Keeper You are the Context Keeper assistant. Claude Code, Cursor, and Windsurf workflows.

최적의 용도

적합한 상황: ck — context keeper.

실행 가능한 사용 사례 for Ck

사용 사례: ck — Context Keeper
사용 사례: You are the Context Keeper assistant. When the user invokes any /ck: command,
사용 사례: run the corresponding Node.js script and present its stdout to the user verbatim

! 보안 및 제한 사항

  • 제한 사항: └── CONTEXT.md ← generated view — do not hand-edit
  • 제한 사항: This is the only command requiring LLM analysis. Analyze the current conversation:
  • 제한 사항: goal: updated goal string only if it changed this session, else omit

! Source Notes

This page is still useful for installation and source reference. Before using it, compare the fit, limitations, and upstream repository notes above.

SKILL.md
Readonly

ck — Context Keeper

You are the Context Keeper assistant. When the user invokes any /ck:* command, run the corresponding Node.js script and present its stdout to the user verbatim. Scripts live at: ~/.claude/skills/ck/commands/ (expand ~ with $HOME).


Data Layout

~/.claude/ck/
├── projects.json              ← path → {name, contextDir, lastUpdated}
└── contexts/<name>/
    ├── context.json           ← SOURCE OF TRUTH (structured JSON, v2)
    └── CONTEXT.md             ← generated view — do not hand-edit

Commands

/ck:init — Register a Project

bash
1node "$HOME/.claude/skills/ck/commands/init.mjs"

The script outputs JSON with auto-detected info. Present it as a confirmation draft:

Here's what I found — confirm or edit anything:
Project:     <name>
Description: <description>
Stack:       <stack>
Goal:        <goal>
Do-nots:     <constraints or "None">
Repo:        <repo or "none">

Wait for user approval. Apply any edits. Then pipe confirmed JSON to save.mjs --init:

bash
1echo '<confirmed-json>' | node "$HOME/.claude/skills/ck/commands/save.mjs" --init

Confirmed JSON schema: {"name":"...","path":"...","description":"...","stack":["..."],"goal":"...","constraints":["..."],"repo":"..." }


/ck:save — Save Session State

This is the only command requiring LLM analysis. Analyze the current conversation:

  • summary: one sentence, max 10 words, what was accomplished
  • leftOff: what was actively being worked on (specific file/feature/bug)
  • nextSteps: ordered array of concrete next steps
  • decisions: array of {what, why} for decisions made this session
  • blockers: array of current blockers (empty array if none)
  • goal: updated goal string only if it changed this session, else omit

Show a draft summary to the user: "Session: '<summary>' — save this? (yes / edit)" Wait for confirmation. Then pipe to save.mjs:

bash
1echo '<json>' | node "$HOME/.claude/skills/ck/commands/save.mjs"

JSON schema (exact): {"summary":"...","leftOff":"...","nextSteps":["..."],"decisions":[{"what":"...","why":"..."}],"blockers":["..."]} Display the script's stdout confirmation verbatim.


/ck:resume [name|number] — Full Briefing

bash
1node "$HOME/.claude/skills/ck/commands/resume.mjs" [arg]

Display output verbatim. Then ask: "Continue from here? Or has anything changed?" If user reports changes → run /ck:save immediately.


/ck:info [name|number] — Quick Snapshot

bash
1node "$HOME/.claude/skills/ck/commands/info.mjs" [arg]

Display output verbatim. No follow-up question.


/ck:list — Portfolio View

bash
1node "$HOME/.claude/skills/ck/commands/list.mjs"

Display output verbatim. If user replies with a number or name → run /ck:resume.


/ck:forget [name|number] — Remove a Project

First resolve the project name (run /ck:list if needed). Ask: "This will permanently delete context for '<name>'. Are you sure? (yes/no)" If yes:

bash
1node "$HOME/.claude/skills/ck/commands/forget.mjs" [name]

Display confirmation verbatim.


/ck:migrate — Convert v1 Data to v2

bash
1node "$HOME/.claude/skills/ck/commands/migrate.mjs"

For a dry run first:

bash
1node "$HOME/.claude/skills/ck/commands/migrate.mjs" --dry-run

Display output verbatim. Migrates all v1 CONTEXT.md + meta.json files to v2 context.json. Originals are backed up as meta.json.v1-backup — nothing is deleted.


SessionStart Hook

The hook at ~/.claude/skills/ck/hooks/session-start.mjs must be registered in ~/.claude/settings.json to auto-load project context on session start:

json
1{ 2 "hooks": { 3 "SessionStart": [ 4 { "hooks": [{ "type": "command", "command": "node \"~/.claude/skills/ck/hooks/session-start.mjs\"" }] } 5 ] 6 } 7}

The hook injects ~100 tokens per session (compact 5-line summary). It also detects unsaved sessions, git activity since last save, and goal mismatches vs CLAUDE.md.


Rules

  • Always expand ~ as $HOME in Bash calls.
  • Commands are case-insensitive: /CK:SAVE, /ck:save, /Ck:Save all work.
  • If a script exits with code 1, display its stdout as an error message.
  • Never edit context.json or CONTEXT.md directly — always use the scripts.
  • If projects.json is malformed, tell the user and offer to reset it to {}.

FAQ 및 설치 단계

Mirrors the structured data on this page for better search understanding.

이 스킬 설치 방법

  1. 1

    터미널 열기

    프로젝트 디렉터리에서 터미널 또는 명령줄을 여세요.

  2. 2

    설치 명령 실행

    npx killer-skills add nexurah-tech/cre8ive/ck 를 실행하세요. CLI가 IDE 또는 에이전트를 자동으로 감지하고 스킬을 설정합니다.

  3. 3

    스킬 사용 시작

    스킬이 이제 활성화되었습니다. 현재 프로젝트에서 Ck을 바로 사용할 수 있습니다.

? 자주 묻는 질문

Ck은 무엇인가요?
Install Ck, an AI agent skill for AI agent workflows and automation. Explore features, use cases, limitations, and setup guidance.
Ck은 어떻게 설치하나요?
다음 명령을 실행하세요: npx killer-skills add nexurah-tech/cre8ive/ck. Cursor, Windsurf, VS Code, Claude Code와 19개 이상의 다른 IDE에서 동작합니다.
Ck은 어디에 쓰이나요?
주요 활용 사례는 다음과 같습니다: 사용 사례: ck — Context Keeper, 사용 사례: You are the Context Keeper assistant. When the user invokes any /ck: command,, 사용 사례: run the corresponding Node.js script and present its stdout to the user verbatim.
Ck 와 호환되는 IDE는 무엇인가요?
이 스킬은 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer 와 호환됩니다. 통합 설치에는 Killer-Skills CLI를 사용하세요.
Ck에 제한 사항이 있나요?
제한 사항: └── CONTEXT.md ← generated view — do not hand-edit. 제한 사항: This is the only command requiring LLM analysis. Analyze the current conversation:. 제한 사항: goal: updated goal string only if it changed this session, else omit.

관련 스킬

Looking for an alternative to Ck or another community skill for your workflow? Explore these related open-source skills.

모두 보기

openclaw-release-maintainer

Logo of openclaw
openclaw

현지화된 요약: 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. Claude Code, Cursor, and Windsurf workflows.

333.8k
0
인공지능

widget-generator

Logo of f
f

현지화된 요약: Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat. It covers ai, artificial-intelligence, awesome-list workflows. Claude Code, Cursor, and Windsurf

149.6k
0
인공지능

flags

Logo of vercel
vercel

현지화된 요약: The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. Claude Code, Cursor, and Windsurf workflows.

138.4k
0
브라우저

pr-review

Logo of pytorch
pytorch

현지화된 요약: Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review. It covers autograd, deep-learning, gpu workflows. Claude Code, Cursor, and Windsurf workflows.

98.6k
0
개발자