ck
Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.
About this skill
The 'ck' (Context Keeper) skill enhances Claude's capabilities by offering persistent, per-project memory for coding and development tasks. It intelligently auto-loads project context upon session start, monitors ongoing development sessions through Git activity, and stores vital project information directly to native memory. This ensures that Claude maintains relevant context across sessions, preventing the need for repeated explanations and improving efficiency. Commands executed via the 'ck' skill utilize deterministic Node.js scripts, guaranteeing consistent behavior regardless of Claude model versions. This skill is part of a larger collection of robust, production-grade development utilities designed to streamline workflows and implement best practices in software engineering within the Claude environment.
Best use case
Software development, code refactoring, debugging, project management, maintaining context across multiple coding sessions, collaborative coding where an AI needs to understand ongoing project state.
Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.
Claude will exhibit a significantly improved understanding of your project's history and current state. You can expect more relevant code suggestions, fewer redundant questions, and a more seamless development workflow, as Claude leverages its 'Context Keeper' memory to provide more informed assistance.
Practical example
Example input
/ck:list
Example output
Projects managed by Context Keeper: - my-webapp (Last updated: 2023-10-27 10:30 AM) - backend-api (Last updated: 2023-10-26 04:15 PM) - cli-tool (Last updated: 2023-10-25 11:00 AM)
When to use this skill
- Use 'ck' when working on complex software projects with Claude where maintaining consistent project context across different interactions or sessions is crucial. It's ideal for long-running development tasks, switching between projects, or ensuring Claude is always up-to-date with the latest project state based on Git activity.
When not to use this skill
- This skill might be overkill for simple, one-off coding tasks or brief interactions that do not require persistent project memory or deep context tracking. If your work with Claude doesn't involve managing ongoing software projects or if you prefer a stateless interaction for specific tasks, 'ck' may not be necessary.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ck/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ck Compares
| Feature / Agent | ck | Standard Approach |
|---|---|---|
| Platform Support | Claude | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | medium | N/A |
Frequently Asked Questions
What does this skill do?
Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts — behavior is consistent across model versions.
Which AI agents support this skill?
This skill is designed for Claude.
How difficult is it to install?
The installation complexity is rated as medium. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
SKILL.md Source
# 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 `$HOME`).
---
## Data Layout
```
~/.claude/ck/
├── projects.json ← path → {name, contextDir, lastUpdated}
└── contexts/<name>/
├── context.json ← SOURCE OF TRUTH (structured JSON, v2)
└── CONTEXT.md ← generated view — do not hand-edit
```
---
## Commands
### `/ck:init` — Register a Project
```bash
node "$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
echo '<confirmed-json>' | node "$HOME/.claude/skills/ck/commands/save.mjs" --init
```
Confirmed JSON schema: `{"name":"...","path":"...","description":"...","stack":["..."],"goal":"...","constraints":["..."],"repo":"..." }`
---
### `/ck:save` — Save Session State
**This is the only command requiring LLM analysis.** Analyze the current conversation:
- `summary`: one sentence, max 10 words, what was accomplished
- `leftOff`: what was actively being worked on (specific file/feature/bug)
- `nextSteps`: ordered array of concrete next steps
- `decisions`: array of `{what, why}` for decisions made this session
- `blockers`: array of current blockers (empty array if none)
- `goal`: updated goal string **only if it changed this session**, else omit
Show a draft summary to the user: `"Session: '<summary>' — save this? (yes / edit)"`
Wait for confirmation. Then pipe to save.mjs:
```bash
echo '<json>' | node "$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
node "$HOME/.claude/skills/ck/commands/resume.mjs" [arg]
```
Display output verbatim. Then ask: "Continue from here? Or has anything changed?"
If user reports changes → run `/ck:save` immediately.
---
### `/ck:info [name|number]` — Quick Snapshot
```bash
node "$HOME/.claude/skills/ck/commands/info.mjs" [arg]
```
Display output verbatim. No follow-up question.
---
### `/ck:list` — Portfolio View
```bash
node "$HOME/.claude/skills/ck/commands/list.mjs"
```
Display output verbatim. If user replies with a number or name → run `/ck:resume`.
---
### `/ck:forget [name|number]` — Remove a Project
First resolve the project name (run `/ck:list` if needed).
Ask: `"This will permanently delete context for '<name>'. Are you sure? (yes/no)"`
If yes:
```bash
node "$HOME/.claude/skills/ck/commands/forget.mjs" [name]
```
Display confirmation verbatim.
---
### `/ck:migrate` — Convert v1 Data to v2
```bash
node "$HOME/.claude/skills/ck/commands/migrate.mjs"
```
For a dry run first:
```bash
node "$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
{
"hooks": {
"SessionStart": [
{ "hooks": [{ "type": "command", "command": "node \"~/.claude/skills/ck/hooks/session-start.mjs\"" }] }
]
}
}
```
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 `{}`.Related Skills
workspace-surface-audit
Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the highest-value ECC-native skills, hooks, agents, and operator workflows. Use when the user wants help setting up Claude Code or understanding what capabilities are actually available in their environment.
safety-guard
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
repo-scan
Cross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports.
project-flow-ops
Operate execution flow across GitHub and Linear by triaging issues and pull requests, linking active work, and keeping GitHub public-facing while Linear remains the internal execution layer. Use when the user wants backlog control, PR triage, or GitHub-to-Linear coordination.
manim-video
Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ECC video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.
laravel-plugin-discovery
Discover and evaluate Laravel packages via LaraPlugins.io MCP. Use when the user wants to find plugins, check package health, or assess Laravel/PHP compatibility.
design-system
Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling.
click-path-audit
Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions individually work but cancel each other out, produce wrong final state, or leave the UI in an inconsistent state. Use when: systematic debugging found no bugs but users report broken buttons, or after any major refactor touching shared state stores.
canary-watch
Use this skill to monitor a deployed URL for regressions after deploys, merges, or dependency upgrades.
benchmark
Use this skill to measure performance baselines, detect regressions before/after PRs, and compare stack alternatives.
swiftui-patterns
SwiftUI 架构模式,使用 @Observable 进行状态管理,视图组合,导航,性能优化,以及现代 iOS/macOS UI 最佳实践。
swift-protocol-di-testing
基于协议的依赖注入,用于可测试的Swift代码——使用聚焦协议和Swift Testing模拟文件系统、网络和外部API。