agentleFS
jammyfujammyfu/open-game-skills/skills/disciplines/encounter-design/SKILL.md

encounter-design

Skill13 starsChanged 24 days agoMITView on GitHub

Use when a room, arena, hunt, ambush or non-boss challenge needs an explicit state/beat graph, entry/exit rules, composition goals and evidence without forcing one universal encounter shape.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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 intended role: traversal pressure, teaching, resource test, elite challenge, ambush, arena, hunt, hybrid, or existing.

    line 8

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Encounter design

Ask the intended role: traversal pressure, teaching, resource test, elite challenge, ambush, arena, hunt, hybrid, or existing.

Contract

Publish:

  • stable encounter_id and revision
  • goal and completion condition
  • state/beat graph with stable beat IDs
  • participant/spawn references
  • entry, fail, retry, reset and exit policy
  • resource assumptions and rewards only if the project uses them
  • evidence needed to prove the authored goal

Ownership

Encounter design composes existing systems. spawn-wave owns dynamic spawn scheduling, enemy-kit-balance owns kits, difficulty-design owns scaling policy, and loot/economy systems own grants.

Rules

  1. An encounter may test one concept or several interacting concepts; composition is authored, not universally capped at one idea.
  2. HP, count, geometry, information and resource pressure are valid only when tied to the stated goal and owner contracts.
  3. Rewards are optional project data; do not require a drop to compensate a spend.
  4. Reset/retry transitions are idempotent and do not duplicate participants or grants.
  5. Record what was actually tested; a scripted setup does not prove a natural route into the encounter.

Acceptance

Given the same encounter_id, revision and starting state, a reviewer can reproduce the legal beat transitions, identify completion/failure, and distinguish encounter composition from spawn, difficulty, combat and reward ownership.

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.