Save current progress to memory-keeper to prevent work loss.
Automatically saves your current progress to memory-keeper every 5-10 tool calls to prevent work loss from context exhaustion. Triggers during implementation, task switches, or when explicitly requested via `/checkpoint`.
/plugin marketplace add barnent1/quetrex-claude/plugin install quetrex-claude@quetrexThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Automatically checkpoint current progress to memory-keeper to prevent catastrophic work loss when context is exhausted.
/checkpointCollect the following information:
context_save(key: "current-task", value: "<task description>", category: "progress", priority: "high")
context_save(key: "files-modified", value: "<comma-separated file list>", category: "progress")
context_save(key: "implementation-progress", value: "<percentage or phase>", category: "progress")
context_save(key: "next-action", value: "<exact next step>", category: "progress", priority: "high")
context_checkpoint(
name: "checkpoint-<timestamp>",
description: "Task: <task>, Progress: <progress>, Files: <count>, Next: <action>"
)
context_prepare_compaction()
| Activity | Checkpoint Frequency |
|---|---|
| File creation/modification | After every file |
| Running tests | After each test run |
| Research/exploration | Every 10 tool calls |
| Debugging | After each hypothesis tested |
| Multi-step implementation | After each step |
| Key | Description | Priority |
|---|---|---|
current-task | What you're currently working on | high |
files-modified | All files touched this session | normal |
implementation-progress | How far along (%, phase) | normal |
next-action | Exact next step to take | high |
blockers | Current issues/blockers | high |
todo-state | Serialized todo list | normal |
After checkpointing, confirm with:
Checkpoint saved:
- Task: <current task>
- Progress: <progress>
- Files modified: <count>
- Next action: <next step>
If context is lost, use /recover to restore state from checkpoints.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.