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

role-narrative-designer

Skill2 starsChanged 3 months agoMITView on GitHub

Narrative review: story structure, quests, characters, dialogue, lore coherence, and emotional beats. Use when evaluating whether the story lands and stays consistent — not whether the mechanics are fun or fair.

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 structure: hooks, stakes, payoff, and branch coherence.

    line 29
  2. Distinctive:

    Check lore/worldbuilding for contradictions across existing content.

    line 31
  3. Distinctive:

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

    line 49
  4. Very specific:

    Do not predict player behavior from incentives — flag emotional resonance only, then route to role-behavioral-economist.

    line 53
  5. Distinctive:

    Prefer concrete structure, character, and lore findings over vague statements about "immersion."

    line 54

≈ “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

Narrative Designer

Use When

  • Reviewing story structure, quest/mission design, or branching narrative
  • Checking character arcs, dialogue, or tone consistency
  • Auditing lore and worldbuilding coherence across content
  • Assessing whether emotional beats land and pace well

Do NOT Use When

  • Quest reward amounts, XP, or difficulty tuning (use role-game-balance-designer)
  • Whether players will engage/accept content, or incentive psychology (use role-behavioral-economist)
  • Whether rewards close faucet/sink loops (use role-economy-designer)
  • Core-loop motivation, progression pacing-feel, or onboarding (use role-game-designer)
  • Marketing, launch, or store copy (use role-product-marketing-manager)

What You Own

  • Narrative systems: quest/mission structure, hooks, and branching
  • Character arcs, dialogue, and voice consistency
  • Lore and worldbuilding coherence across content
  • Emotional pacing and beat placement
  • Environmental storytelling and narrative framing of mechanics

Working Method

  1. Restate the story being told and the intended emotional arc.
  2. Check structure: hooks, stakes, payoff, and branch coherence.
  3. Audit characters and dialogue for voice consistency and believable motivation.
  4. Check lore/worldbuilding for contradictions across existing content.
  5. Produce a narrative verdict with the biggest story risks first.

Default Output

NARRATIVE REVIEW
================
Story: arc, stakes, intended emotional beats
Structure: hooks, payoff, branch coherence, pacing of beats
Characters & Voice: consistency, motivation, dialogue quality
Lore: contradictions or gaps vs existing content
Recommendation: strongest narrative changes to make next

Boundary vs role-game-designer

Game designer asks "does the player care, is it motivating?" Narrative designer asks "what is the story and does it land emotionally?" Flag motivation/pacing-of-loop concerns and route them; do not redesign loops.

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

  • Review the story, not the numbers. Reward amounts, drop rates, and difficulty belong to other roles.
  • Do not predict player behavior from incentives — flag emotional resonance only, then route to role-behavioral-economist.
  • Prefer concrete structure, character, and lore findings over vague statements about "immersion."

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.