Automated summary

Saves context state to reduce token consumption when using Claude Code.

Strengths

Saves 40 to 70% of tokens depending on the command used.
Allows easy resumption after a /clear.
Structures important information (progress, learnings).

Limitations

Requires manual discipline to trigger checkpoints.
Does not preserve file contents or error traces.
Only works with Claude Code.

When to use it

Use this skill every 3 tasks or before switching domains to save tokens.

When not to use it

Avoid if you prefer automatic context management or if your sessions are very short.

Security analysis

Safe

Quality score85/100

The skill only reads/writes local files for checkpointing context; no network, shell, or destructive actions.

No concerns found

How this analysis is made

Examples

Save checkpoint before clearing

Save a context checkpoint now. I want to reclaim tokens before clearing the session.

Checkpoint after completing a task

I just finished fixing the login bug. Create a checkpoint summarizing what we did and what's next.

Restore from checkpoint

Read the checkpoint file and restore our session context so we can continue working.

name: checkpoint description: Save context state - auto-triggered every 5 tasks allowed-tools: Read, Write, TaskList, Grep model: sonnet user-invocable: false

Context Checkpoint

Name: Context Checkpoint
Author: Skills Guide Bot

Save critical context before /clear. Enables 50-70% token savings.

When to Checkpoint

Every 3 tasks (aggressive - preserves tokens)
Before switching feature areas
After resolving complex bugs
When response feels slow (context bloat sign)

Checkpoint Format

Write to .claude/checkpoint.md:

# Checkpoint: [TIMESTAMP]

## Sprint Status
[Sprint X: N/M complete]

## Completed This Session
- [Task]: [what was done]

## Key Learnings
- [Bug pattern]: [resolution]

## Next Priority
[Next task ID and title]

## Files Modified
- [file paths]

After Saving

Tell user:

💾 Checkpoint saved.

Run /compact now to reclaim ~40% tokens (keeps context summary).
Use /clear only at major transitions (reclaims ~70% but wipes context).

Auto-Restore

After /clear, read .claude/checkpoint.md and continue.

What to Preserve

| Keep | Skip | |------|------| | Task progress | File contents | | Learnings | Error traces | | Next priority | Tool call logs |

Token Savings

| Command | Savings | Use When | |---------|---------|----------| | /compact | ~40% | Default after checkpoint | | /clear | ~70% | Major transitions, sprint end |

Rule: /compact after every checkpoint. /clear at major transitions.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/context-checkpoint-mma3jrgh/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/context-checkpoint-mma3jrgh' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/context-checkpoint-mma3jrgh/download' --output '.skill-downloads/context-checkpoint-mma3jrgh/SKILL.md.part' && mv '.skill-downloads/context-checkpoint-mma3jrgh/SKILL.md.part' '.skill-downloads/context-checkpoint-mma3jrgh/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Write, TaskList, Grep

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/context-checkpoint-mma3jrgh/SKILL.md' && test -s '.skill-downloads/context-checkpoint-mma3jrgh/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/checkpoint' && cp -R '.skill-downloads/context-checkpoint-mma3jrgh' '.claude/skills/checkpoint'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/context-checkpoint-mma3jrgh'

openskills read 'context-checkpoint-mma3jrgh'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/context-checkpoint-mma3jrgh/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

PDF Reader

Productivity

Read and extract text from PDF files, including documents, reports, contracts, and spreadsheets. Works with local files, URLs, and WhatsApp attachments. Use whenever PDF content is needed, even if not explicitly requested.

Claude CodeCursorCodexbeginnerSafe 20,122

Skills Guide Bot