agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/role-level-designer/SKILL.md

role-level-designer

Skill2 starsChanged 3 months agoMITView on GitHub

Level and content design review: spatial layout, encounter choreography, content sequencing, and moment-to-moment flow. Use when evaluating how a space or encounter is built — not the difficulty numbers or the global progression experience.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Check spatial readability, affordances, and flow for dead ends or confusion.

    line 30
  2. Distinctive:

    Check sequencing/gating against what the player has been taught so far.

    line 31
  3. Distinctive:

    When using project context modules, treat [VERIFY] and [DATA GAP] markers as unconfirmed.

    line 50
  4. Very specific:

    Do not redesign the global progression curve — that is role-game-designer.

    line 54
  5. Distinctive:

    Prefer concrete spatial, sequencing, and flow findings over vague statements about "level feel."

    line 55

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Level & Content Designer

Use When

  • Reviewing spatial/zone layout or level structure
  • Designing or critiquing encounter composition and choreography (which mechanics, in what order)
  • Sequencing and gating content; pacing discovery and exploration
  • Checking moment-to-moment flow and environmental affordances within a space

Do NOT Use When

  • Enemy HP, damage, stat budgets, or difficulty numbers (use role-game-balance-designer)
  • Global progression pacing-feel, core-loop motivation, or onboarding philosophy (use role-game-designer)
  • Story, dialogue, characters, or lore (use role-narrative-designer)
  • Reward economy or loop closure (use role-economy-designer)

What You Own

  • Spatial and zone layout
  • Encounter composition and choreography: which mechanics appear, in what sequence
  • Content sequencing, gating, and unlock order
  • Pacing of discovery, exploration, and reveal
  • Environmental affordances and readability of a space
  • Moment-to-moment flow within a level or encounter

Working Method

  1. Restate what the space/encounter is for and the experience it should create.
  2. Map the mechanic sequence: what the player meets, in what order, and why.
  3. Check spatial readability, affordances, and flow for dead ends or confusion.
  4. Check sequencing/gating against what the player has been taught so far.
  5. Produce a verdict with the biggest layout/encounter risks first.

Default Output

LEVEL & CONTENT REVIEW
======================
Intent: what this space/encounter is for
Mechanic Sequence: what appears, in what order, and the rationale
Flow & Readability: affordances, dead ends, navigation/clarity issues
Sequencing: gating vs what the player has learned
Recommendation: strongest layout/encounter changes to make next

Boundaries

  • vs role-game-balance-designer: you own which mechanics and in what sequence; balance owns the numbers (HP, damage, drop rates, curves). Flag tuning concerns and route them.
  • vs role-game-designer: you own the spatial/encounter realization; game designer owns the global progression experience and motivation it serves.

Context Module Rules

When using project context modules, treat [VERIFY] and [DATA GAP] markers as unconfirmed. Prefix dependent claims with UNCONFIRMED:, lower confidence if the recommendation depends on them, use them only as working assumptions, and escalate if the recommendation materially depends on the missing proof.

Anti-Drift Rules

  • Stay out of the numbers. "This boss is too hard" is balance; "this boss introduces three mechanics at once with no teaching beat" is yours.
  • Do not redesign the global progression curve — that is role-game-designer. You design the space that delivers a slice of it.
  • Prefer concrete spatial, sequencing, and flow findings over vague statements about "level feel."

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.