Create Checkpoint

Create Checkpoint

Purpose

Capture the active session state as a structured Markdown checkpoint artifact so the session can be restored in a future conversation.

How to Invoke

Load or attach this file's contents into your AI session to activate the workflow (paste, upload, or reference with #file:skills/create-checkpoint/SKILL.md in VS Code Copilot Chat). In Claude Projects, add it to project knowledge. See [Invoking Skills](../../README.md#invoking-skills) in the README for full platform guidance.

When To Use

• When the user signals they are ending the session and want to resume later.
• When the user explicitly requests a checkpoint.
• Do not create checkpoints silently or mid-session without the user's explicit request.

Required Inputs

• Current active values for: project, role, phase, outputstyle, tone, and interactionmode (if established).
• Open tasks or confirmed next steps from this session.
• Key decisions made during this session that affect future work.
• File paths actively referenced or modified this session.

Workflow

1. Collect the current values for all required schema fields from active session state.
2. List all open tasks — items in progress or confirmed next steps.
3. List key decisions made this session that would affect future work.
4. List file paths actively referenced or modified.
5. Draft the checkpoint artifact using the schema in references/checkpoint-schema.md.
6. Present the full draft to the user for review and approval before writing anything.
7. Write the file only after the user explicitly approves.
8. Suggest saving as checkpoint-YYYY-MM-DD.md in the project root or a checkpoints/ folder if one exists. Let the user decide the exact path.

Output Expectations

• A Markdown file with YAML frontmatter containing all required schema fields.
• Human-readable summary paragraph below the frontmatter is optional but encouraged.
• The file must not be written without explicit user approval.
• Sensitive data (credentials, private client content) must never be included.

Resources

• references/checkpoint-schema.md for field definitions, constraints, and an example artifact.

Constraints And Safety

• Checkpoint artifacts must be stored outside the instruction layer — never inside AGENTS.md or user context files.
• Always require explicit user confirmation before writing the file.
• If a field value is unknown or not yet established, use null.
• Never include sensitive information such as credentials, API keys, or private client content.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: MSiccDev
• Source: MSiccDev/ai-context-kit
• License: MIT

Install and usage instructions live in the source repository linked above.