agentleFS
jammyfujammyfu/open-game-skills/skills/disciplines/ability-gate/SKILL.md

ability-gate

Skill12 starsChanged 23 days agoMITView on GitHub

Use when access depends on a capability, story predicate, or both, and the project needs a stable gate identity, deterministic predicate evaluation, unlock migration, and explicit soft-lock/recovery evidence.

The file

Files
SKILL.md

Ability gate

Ask: none | tool-gate | story-flag | both.

Ownership

The gate consumes capability/story state from their true owners. It does not own tutorials, map pins, save storage or rest-site placement.

Contract

Each gate publishes:

  • stable gate_id
  • required capability IDs and/or story predicate IDs
  • predicate version
  • open/closed/blocked result
  • optional authored feedback/reference IDs

Evaluate the gate from authoritative state. Duplicate unlock notifications are idempotent. A save or patch migration preserves stable capability/story identity rather than keying by localized text or scene index.

Soft-lock policy is project-specific: the project may require an exit, recovery point, alternate route, or intentionally irreversible commitment. Do not force every hard gate to have a rest site or every ability lesson to be nonlethal.

Acceptance

For one predicate version and authoritative state, the gate resolves deterministically. Gaining or losing relevant capability state updates only gates that depend on it, stale notifications cannot override a newer result, and a blocked player can identify the missing authored requirement without the gate inventing world truth.

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.