agentleFS
MSiccDevMSiccDev/ai-context-kit/skills/create-checkpoint/SKILL.md

create-checkpoint

Skill12 starsChanged 4 months agoMITView on GitHub

Capture the current session state as a checkpoint artifact per spec section 4.4. Use when the user signals session end or explicitly requests a checkpoint. Do not use mid-session or without user approval.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user signals they are ending the session and want to resume later.

    line 14
  2. Distinctive:

    When the user explicitly requests a checkpoint.

    line 15
  3. Distinctive:

    Do not create checkpoints silently or mid-session without the user's explicit request.

    line 16
  4. Distinctive:

    Write the file only after the user explicitly approves.

    line 31
  5. Distinctive:

    Always require explicit user confirmation before writing the file.

    line 45
  6. Very specific:

    If a field value is unknown or not yet established, use null.

    line 46
  7. Distinctive:

    Never include sensitive information such as credentials, API keys, or private client content.

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Create Checkpoint

Purpose

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

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, output_style, tone, and interaction_mode (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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.