
rpg
Build an RPG: stats and leveling, inventory and equipment, quests, branching dialogue, save/load, and combat. Use for an RPG/JRPG, or designing stat, inventory, quest, or combat systems.
- Installs
- 6.7K
- Last 24h
- +337
- Trending rank
- #892
- Security
- Pass
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/gamedev-skills/awesome-gamedev-agent-skills --skill rpg- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads rpg automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
Security audits
Independent scans of the skill's instructions and bundled files.
SKILL.md
The instructions your agent reads when the skill is triggered.
RPG
A playbook for role-playing games — stats and progression, inventory/equipment, quests, dialogue, and combat. This is a compositional skill: it ties data-driven content, dialogue, and saving together. It does not re-teach those primitives; it defines the systems that make growth and choice feel meaningful, and points to the skills that implement each.
When to use
- Use when building an RPG/JRPG/action-RPG: the player has stats that grow, an inventory, quests, dialogue, and persistent progress.
- Use when designing a leveling curve, a damage formula, an inventory/equipment model, or a quest state machine.
When not to use: permadeath dungeon runs with no persistent character → roguelike.
Pure conversation/branching story → visual-novel. Open-world needs/crafting/base-building →
survival-crafting. For the dialogue engine itself, use dialogue-systems.
Core loop
Explore → encounter (fight / talk / solve) → earn rewards (XP, loot, story) → grow (level up, gear up, unlock) → take on harder content. The fantasy is getting stronger and shaping who your character is; every system should feed that growth-and-choice loop.
Must-have systems
- Stats + leveling — base attributes, derived combat stats, XP curve, level-up gains.
- Inventory + equipment — data-defined items, stacking, slots, stat modifiers.
- Combat — turn-based or action; damage formula, status effects, win/loss.
- Quests — objectives, state machine (available→active→complete→turned-in), rewards.
- Dialogue — branching lines, conditions on game state, choices that matter.
- Save/load — persist character, inventory, quest progress, world flags, with versioning.
- Economy + progression gating — gold/shops; gate power behind level/quest/region.
- UI — HUD, inventory, quest log, dialogue box, character sheet.
Design knobs
| Knob | Effect | Notes |
|---|---|---|
| XP curve shape | pacing of power | Fast early, slow late (see refs). |
| Stat→derived scaling | build diversity | One attribute shouldn't dominate. |
| Damage formula | tactical feel | Subtractive vs. ratio mitigation (refs). |
| Random variance / crit | swinginess | ±10% and ~1.5× crit are safe defaults. |
| Drop rates / economy | reward cadence | Avoid trivializing shops with loot. |
| Power gating | difficulty gating | Level/region/quest locks. |
| Reversible modifiers | buff/gear correctness | Layer mods; never edit base stats. |
| Choice consequence | role-play weight | Quest/dialogue flags should branch outcomes. |
Patterns
1. Derived stats from base attributes (recompute, never store as truth)
# Pseudocode. Base attributes are the only "truth"; combat stats are derived each time.
def derive(base, mods):
s = apply_modifiers(base, mods) # base + flat adds + percent, then clamp
return {
"max_hp": 20 + s["VIT"] * 8,
"attack": s["STR"] * 2,
"defense": s["VIT"] + s["AGI"] * 0.5,
}
# Equipping pushes a modifier; unequipping pops it. HP/attack recompute automatically.
2. XP curve + level-up
# Pseudocode. Quadratic curve: fast early levels, long late ones.
def xp_to_next(level, base=100): return base * level * level
def gain_xp(actor, amount):
actor.xp += amount
while actor.xp >= xp_to_next(actor.level):
actor.xp -= xp_to_next(actor.level)
actor.level += 1
actor.base["STR"] += 2; actor.base["VIT"] += 2 # grant gains / skill points
on_level_up(actor) # heal, unlock, notify
3. Quest objective update driven by game events
# Pseudocode. Game events advance matching objectives; completion grants rewards.
def on_event(kind, data):
for q in active_quests:
if q.state != "active": continue
for obj in q.objectives:
if obj.event == kind and matches(obj, data) and not obj.done:
obj.count = min(obj.count + 1, obj.needed)
if obj.count >= obj.needed: obj.done = True
if all(o.done for o in q.objectives):
q.state = "complete" # turn-in grants xp/gold/items once
Pitfalls / failure modes
- Editing base stats for buffs/gear → values drift and corrupt on save/reload. Keep a modifier layer; push/pop it (Pattern 1).
- Storing derived stats as truth → desync after a stat change. Recompute from base.
- Runaway XP/damage numbers → either an exponential curve with no cap or a subtractive formula at huge values. Pick a curve and a formula family deliberately (refs).
- Stacked buffs explode → percent modifiers multiplied together. Sum percents within a layer unless a rule says otherwise (refs §1).
- Content as code → every item/quest hardcoded. Define items, enemies, and quests as
data (
godot-resources/unity-scriptableobjects). - Save format with no version field → old saves break on update. Add a
versionand a migration path from day one (seesave-systems). - Choices without consequences → dialogue branches that reconverge immediately feel hollow. Set flags that actually change later quests/world state.
- Quest progress not persisted → reloading loses mid-quest state. Save quest state, not just completion.
Composition (build it from these skills)
- Dialogue:
dialogue-systems(Yarn Spinner / Ink) — branching lines, conditions, variables. - Persistence:
save-systems— character, inventory, quest flags, world state, versioning. - Content data:
godot-resources/unity-scriptableobjects— items, enemies, quests, skills as assets. - Combat AI:
game-aifor enemy behavior; for turn order reuse the scheduler idea inroguelike. - UI:
game-ui-uxfor HUD/menu layout, resolution scaling, and controller/keyboard nav;godot-ui-controlfor the concrete inventory, quest log, character sheet, and dialogue box. - World:
level-designplus your engine's tilemap/3D skill (godot-tilemap,godot-3d-essentials).
References
- For stat/damage formulas, leveling curves, turn-vs-action combat timelines, inventory/equipment
data shapes, and the quest state model, read
references/stats-combat-quests.md.
FAQ
What does the rpg skill do?
Build an RPG: stats and leveling, inventory and equipment, quests, branching dialogue, save/load, and combat. Use for an RPG/JRPG, or designing stat, inventory, quest, or combat systems.
How do I install rpg?
Run npx skills add https://github.com/gamedev-skills/awesome-gamedev-agent-skills --skill rpg in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/rpg/ (personal) or .claude/skills/rpg/ (project).
Which AI agents can use rpg?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is rpg safe to install?
Security partners have reviewed it: Gen Agent Trust Hub passed; Socket passed; Snyk passed. As with any skill, read the SKILL.md and bundled scripts before installing.
Who maintains rpg?
It is published by gamedev-skills in gamedev-skills/awesome-gamedev-agent-skills. It has 6,731 recorded installs.
More from gamedev-skills/awesome-gamedev-agent-skills
game-feel
gamedev-skills/awesome-gamedev-agent-skills
Add "juice" and game feel that makes actions satisfying — screen shake, hit-stop/freeze frames, tweened/eased motion, squash & stretch, knockback, and layered audio-visual feedback — as engine-neutral techniques that pair with the detected engine's tween, particle, and camera APIs. Use when the user mentions game feel, juice, "make it feel good/punchy", screen shake, hit stop, screen freeze, easing, squash and stretch, impact frames, or feedback/polish on hits, jumps, pickups, and deaths.
game-ui-ux
gamedev-skills/awesome-gamedev-agent-skills
Design and build game UI/UX — HUDs, menus, and overlays — that survive every screen: anchor- based responsive layout, resolution/aspect scaling and safe areas, keyboard/gamepad focus navigation, a screen/menu state stack, and event-driven (not polled) HUD updates. Engine- neutral patterns that pair with the detected engine's UI skill. Use when the user mentions HUD, health bar, main menu, pause menu, settings screen, UI layout, anchors, UI scaling, aspect ratio, safe area, controller/keyboard menu navigation, or wiring UI to game state.
level-design
gamedev-skills/awesome-gamedev-agent-skills
Design and build playable levels — the blockout/whitebox-to-playable workflow, player metrics and grid layout, pacing and flow (tension/rest curve), gating and the critical path, and encounter design. Engine-neutral practice. Use when the user mentions level design, blockout/whitebox/greybox, level layout, level pacing, encounter design, or the critical path through a level.
performance-optimization
gamedev-skills/awesome-gamedev-agent-skills
Find and fix game performance problems methodically — measure with the engine profiler first, reason about the frame-time budget, locate the CPU-vs-GPU bottleneck, then apply the right fix: object pooling, draw-call batching, fewer allocations/GC spikes, and asset budgets. Engine- neutral method that pairs with each engine's profiler. Use when the user mentions performance, optimize, low/dropping FPS, frame drops, stutter, lag, profiler, frame budget, draw calls, batching, garbage collection/GC spikes, object pooling, or "the game runs slow".
game-ai
gamedev-skills/awesome-gamedev-agent-skills
Design NPC and enemy decision-making with finite state machines, behavior trees, steering behaviors, and A pathfinding — engine-neutral algorithms that pair with the detected engine's navigation API. Use when building enemy AI, an FSM or behavior tree, steering/flocking, or pathfinding, or when the user mentions state machine, behavior tree, blackboard, A, navmesh, seek, or patrol/chase.
audio-design
gamedev-skills/awesome-gamedev-agent-skills
Implement game audio practice — bus/mixer architecture and gain in decibels, ducking (sidechain), adaptive/dynamic music via layering and re-sequencing, SFX variation, and beat synchronization. Engine-neutral. Use when the user mentions audio mixing, audio buses, adaptive/dynamic music, ducking, SFX variation, music layers, or syncing gameplay to the beat.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available