agentleFS
Sign inStart free
jammyfujammyfu/open-game-skills/skills/disciplines/save-checkpoint/SKILL.md

save-checkpoint

Skill12 starsChanged 23 days agoMITView on GitHub

Use when a game needs explicit checkpoint timing, respawn anchors or run-persistence policy while storage integrity, cloud conflict and bytes remain owned elsewhere.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the policy: auto, authored-rest, manual-safe, run-boundary, suspend, hybrid, or existing.

    line 8
  2. Distinctive:

    write trigger and respawn selection policy

    line 15

≈ “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

Save checkpoint

Ask the policy: auto, authored-rest, manual-safe, run-boundary, suspend, hybrid, or existing.

Contract

Publish:

  • stable checkpoint_policy_id and revision
  • checkpoint/anchor IDs and eligibility predicates
  • write trigger and respawn selection policy
  • pending/committed checkpoint state
  • interaction with run/death policy
  • evidence for quit/load/retry behavior

Ownership

This skill decides when and where progression is checkpointed. save-systems owns atomic serialization/migration, save-integrity owns trust/recovery, and cloud-save owns remote revision/conflict behavior.

Rules

  1. Checkpoint timing and loss window are project policy; no universal duration is acceptable or unacceptable.
  2. A checkpoint becomes authoritative only after the owning save transaction commits successfully.
  3. Duplicate trigger callbacks with the same checkpoint request identity do not create multiple writes or advance twice.
  4. Respawn/death carry uses stable checkpoint identity, not scene array order or UI labels.
  5. Suspend can request a checkpoint or separate suspend snapshot according to platform/project policy.

Acceptance

A reviewer can identify the active checkpoint policy/revision, last committed checkpoint ID, pending write state and respawn selection. Local/cloud/storage failures are attributed to their owning save systems rather than silently changing checkpoint rules.

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.

Check your setup, free