Marketplace checkpoint

Save current progress to memory-keeper to prevent work loss.

install
source · Clone the upstream repo
git clone https://github.com/aiskillstore/marketplace
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/aiskillstore/marketplace "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/barnhardt-enterprises-inc/checkpoint" ~/.claude/skills/aiskillstore-marketplace-checkpoint && rm -rf "$T"
manifest: skills/barnhardt-enterprises-inc/checkpoint/SKILL.md
source content

Checkpoint Skill

Automatically checkpoint current progress to memory-keeper to prevent catastrophic work loss when context is exhausted.

When to Use

  • Every 5-10 tool calls during implementation
  • After completing a significant piece of work
  • Before starting a large operation
  • When switching tasks
  • Before ending a session
  • When explicitly requested via
    /checkpoint

Checkpoint Actions

1. Gather Current State

Collect the following information:

  • Current task description from todo list
  • List of files modified this session
  • Implementation progress (percentage or phase)
  • Current blockers or issues
  • Next action to take

2. Save to Memory-Keeper

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")

3. Create Named Checkpoint

context_checkpoint(
  name: "checkpoint-<timestamp>",
  description: "Task: <task>, Progress: <progress>, Files: <count>, Next: <action>"
)

4. Prepare for Compaction (if context is large)

context_prepare_compaction()

Checkpoint Frequency Guidelines

ActivityCheckpoint Frequency
File creation/modificationAfter every file
Running testsAfter each test run
Research/explorationEvery 10 tool calls
DebuggingAfter each hypothesis tested
Multi-step implementationAfter each step

Key Items to Always Save

KeyDescriptionPriority
current-task
What you're currently working onhigh
files-modified
All files touched this sessionnormal
implementation-progress
How far along (%, phase)normal
next-action
Exact next step to takehigh
blockers
Current issues/blockershigh
todo-state
Serialized todo listnormal

Checkpoint Output

After checkpointing, confirm with:

Checkpoint saved:
- Task: <current task>
- Progress: <progress>
- Files modified: <count>
- Next action: <next step>

Recovery Reference

If context is lost, use

/recover
to restore state from checkpoints.