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

boss-design

Skill13 starsChanged 24 days agoMITView on GitHub

Use when a boss or major encounter needs a clear exam, phase/state structure, authored risk/readability policy and recoverable transitions without copying a shipped encounter or forcing universal phase rules.

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

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 project role first: duel, puzzle-gate, hunt, raid, spectacle, 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

Boss design

Ask the project role first: duel, puzzle-gate, hunt, raid, spectacle, hybrid, or existing.

Contract

Publish:

  • stable boss_encounter_id and revision
  • exam/goal statement
  • phase or state graph with stable state IDs
  • entry/exit/fail/retry policy
  • authored risk/readability policy
  • arena dependencies and required taught verbs
  • resource/reset rules owned by their respective systems

Ownership

Boss design owns encounter composition and state transitions. attack-tell owns warning contracts, enemy-kit-balance owns move-kit tuning, difficulty-design owns difficulty policy, and camera/combat/resource skills retain their own truth.

Rules

  1. Telegraph/readability is authored from threat, pacing, player capability and accessibility needs; there is no universal damage-to-windup formula.
  2. A phase may change space, goals, move combinations, resources, presentation or another authored dimension; it does not need to fit one template.
  3. Required tools/verbs must have a recoverable availability path or an explicit fail/retry path.
  4. Story placement, optionality and relative difficulty are project progression decisions, not boss invariants.
  5. Phase transitions are idempotent and use stable transition identity so duplicate callbacks cannot advance twice.

Acceptance

Given the same boss revision and starting state, a reviewer can identify the intended exam, legal state transitions, risk/readability policy, recovery path and which external skills own timing, targeting, resources and presentation.

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.