exploration-creator

Create exploration content for SHINOBI WAY game with node-based path navigation. Use when user wants to add new regions, locations, room layouts, intel missions, path networks, or exploration mechanics. Guides through the Region→Location→Room hierarchy with intel-gated path choices. (project)

242 stars

Best use case

exploration-creator is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Create exploration content for SHINOBI WAY game with node-based path navigation. Use when user wants to add new regions, locations, room layouts, intel missions, path networks, or exploration mechanics. Guides through the Region→Location→Room hierarchy with intel-gated path choices. (project)

Create exploration content for SHINOBI WAY game with node-based path navigation. Use when user wants to add new regions, locations, room layouts, intel missions, path networks, or exploration mechanics. Guides through the Region→Location→Room hierarchy with intel-gated path choices. (project)

Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.

Practical example

Example input

Use the "exploration-creator" skill to help with this workflow task. Context: Create exploration content for SHINOBI WAY game with node-based path navigation. Use when user wants to add new regions, locations, room layouts, intel missions, path networks, or exploration mechanics. Guides through the Region→Location→Room hierarchy with intel-gated path choices. (project)

Example output

A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.

When to use this skill

  • Use this skill when you want a reusable workflow rather than writing the same prompt again and again.

When not to use this skill

  • Do not use this when you only need a one-off answer and do not need a reusable workflow.
  • Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/exploration-creator/SKILL.md --create-dirs "https://raw.githubusercontent.com/aiskillstore/marketplace/main/skills/cesaraugustusgrob/exploration-creator/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/exploration-creator/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How exploration-creator Compares

Feature / Agentexploration-creatorStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Create exploration content for SHINOBI WAY game with node-based path navigation. Use when user wants to add new regions, locations, room layouts, intel missions, path networks, or exploration mechanics. Guides through the Region→Location→Room hierarchy with intel-gated path choices. (project)

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Exploration System Creator

Create exploration content for SHINOBI WAY: THE INFINITE TOWER following the node-based navigation system with intel-gated path choices.

## Core Hierarchy

```
REGION (e.g., Land of Waves)
├── LOCATION × 10-15 (e.g., The Docks, Fishing Village)
│   ├── ROOM × 10 per location (1→2→4→2→1 branching)
│   │   ├── Rooms 1-9: Random activities (combat, event, merchant, etc.)
│   │   └── Room 10: INTEL MISSION (always elite fight)
│   └── PATHS (connections to other locations)
└── BOSS (final destination)
```

## Key Mechanics

| Mechanic | Description |
|----------|-------------|
| **Forward-Only** | Cannot backtrack to previous locations (roguelike style) |
| **Path Choice** | With intel: choose path. Without: random destination |
| **Intel Mission** | Room 10 elite fight. Win = intel. Skip = random path |
| **Loops** | Special paths back to earlier locations (discovered via intel) |
| **Secrets** | Hidden locations unlocked by intel, items, karma, or story |

## Workflow

### Step 1: Design Region

Define the region's identity:

```typescript
const region: Region = {
  id: 'region_id',
  name: 'Region Name',
  theme: 'Narrative theme description',
  description: 'Atmospheric description',
  entryPoints: ['location_1', 'location_2'],  // 1-2 starting locations
  bossLocation: 'boss_location_id',
  lootTheme: {
    primaryElement: ElementType.WATER,
    equipmentFocus: ['speed', 'dexterity'],
    goldMultiplier: 0.8
  }
};
```

See [region-system.md](references/region-system.md) for complete region structure.

### Step 2: Plan Locations (10-15)

Map locations with danger progression:

| Column | Stage | Danger | Location Count |
|--------|-------|--------|----------------|
| 0 | Entry | 1-2 | 1-2 locations |
| 1 | Early | 3-4 | 2-3 locations |
| 2 | Mid | 4-5 | 3-4 locations |
| 3 | Late | 5-6 | 2-3 locations |
| 4 | Boss | 7 | 1 location |

**Location Types:**

| Type | Combat | Merchant | Rest | Focus |
|------|--------|----------|------|-------|
| `settlement` | Low | Yes | Yes | Story, social |
| `wilderness` | Medium | No | Maybe | Exploration |
| `stronghold` | High | Maybe | No | Heavy combat |
| `landmark` | Medium | Maybe | Maybe | Balanced, story |
| `secret` | Varies | Rare | Rare | Unique rewards |
| `boss` | BOSS | No | No | Final encounter |

See [location-system.md](references/location-system.md) for location data structure and terrain types.

### Step 3: Define Room Activities

Each location has 10 rooms in a 1→2→4→2→1 branching structure. Player visits 5 rooms per location.

**Activity Weights (Rooms 1-9 only):**

| Activity | Weight | Description |
|----------|--------|-------------|
| `combat` | 40% | Fight enemies from location pool |
| `event` | 25% | Atmosphere event with choices |
| `merchant` | 10% | Buy/sell (max 1 per location) |
| `rest` | 8% | Recover HP/Chakra (max 1 per location) |
| `treasure` | 8% | Loot chest |
| `training` | 5% | Permanent stat upgrade |
| `story_event` | 4% | Narrative from story tree |

**Room 10 is ALWAYS an Intel Mission** - elite fight or boss.

See [room-system.md](references/room-system.md) for room layout and connections.

### Step 4: Configure Intel Missions

Every location's Room 10 contains an Intel Mission:

```
Player reaches Room 10 → FIGHT or SKIP
├── FIGHT → Win → Intel + Loot → CHOOSE next path
├── FIGHT → Lose → Game Over
└── SKIP → No rewards → RANDOM next path
```

**Elite scaling by location type:**

| Location Type | Elite Level | Notes |
|---------------|-------------|-------|
| Settlement | 2-3 | Guards, spies |
| Wilderness | 3-5 | Beasts, bandits |
| Stronghold | 5-7 | Commanders |
| Landmark | 4-5 | Guardians |
| Secret | 4-7 | Unique elites |
| Boss | 8-10 | **Cannot skip** |

See [intel-mission-system.md](references/intel-mission-system.md) for intel rewards and boss handling.

### Step 5: Map Path Network

Define connections between locations:

**Path Types:**

| Type | Direction | Discovery | Description |
|------|-----------|-----------|-------------|
| `forward` | → | Always visible | Standard progression |
| `branch` | → | Always visible | Alternative route |
| `loop` | ← | Via intel hint | Return to earlier location |
| `secret` | → | Via intel/item/karma | Hidden location access |
| `boss` | → | Always visible | Final path to boss |

**Navigation Rules:**
1. Forward-only (except loops)
2. Visited locations are closed
3. Intel = player chooses path
4. No intel = random destination
5. Loops are one-time use
6. Boss completes region

See [navigation-system.md](references/navigation-system.md) for path data structures and loop system.

### Step 6: Validate

**Region Checklist:**
- [ ] 10-15 locations total
- [ ] 1-2 entry points (isEntry: true)
- [ ] 1 boss location (isBoss: true)
- [ ] All locations reachable from entry
- [ ] Multiple paths to boss (2-3 minimum)
- [ ] Danger curve: Entry (1-2) → Boss (7)

**Location Checklist:**
- [ ] Unique id and name
- [ ] Valid type and danger level
- [ ] 1-3 forward paths (except boss)
- [ ] Intel mission defined
- [ ] Flags match type

**Room Checklist:**
- [ ] 10 rooms per location
- [ ] Room 10 = intel_mission
- [ ] Max 1 merchant, max 1 rest
- [ ] Connections follow 1→2→4→2→1

See [types.md](references/types.md) for complete TypeScript interfaces.

## Reference Files

- [region-system.md](references/region-system.md) - Region structure and data
- [location-system.md](references/location-system.md) - Location types, terrain, flags
- [room-system.md](references/room-system.md) - 10-room layout and activities
- [intel-mission-system.md](references/intel-mission-system.md) - Elite fights and intel rewards
- [navigation-system.md](references/navigation-system.md) - Paths, loops, secrets
- [types.md](references/types.md) - TypeScript type definitions
- [example-waves.md](references/example-waves.md) - Complete Land of Waves region

## Output Format

Generate TypeScript code for new regions/locations ready to integrate into the game systems.

Related Skills

vision-exploration

242
from aiskillstore/marketplace

终局愿景探索。用户抛出一个模糊 idea,AI 主导引导,通过"追问价值 → 挖掘动机 → 推导演化 → 画终局"的链路,帮用户看到未来最远的可能性。不设限,不收敛,纯发散。

design-exploration

242
from aiskillstore/marketplace

新功能设计探索流程。当用户有模糊想法要做新功能/新模块时使用。通过"需求收敛 → 技术调研 → ASCII 批量探索 → HTML 设计稿 → 全状态覆盖 → 需求总结"的结构化流程,从模糊想法产出可交付的设计参考文档,作为 PRD 阶段的输入。

command-creator

242
from aiskillstore/marketplace

This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.

skill-creator-ms

242
from aiskillstore/marketplace

Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.

obsidian-clipper-template-creator

242
from aiskillstore/marketplace

Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.

github-issue-creator

242
from aiskillstore/marketplace

Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images/GIFs for visual evidence.

specs-creator

242
from aiskillstore/marketplace

Use PROACTIVELY this skill when you need to create comprehensive PRDs, tech specs, and ux specs based on feature description. If the user specify "Create PRD", "Create Tech Specs", or "Create UX Specs", this skill must be triggered.

skills-creator

242
from aiskillstore/marketplace

Creates and maintains Agent Skills with effective triggers and progressive disclosure. Use when user requests to create a skill, generate a SKILL.md, build custom capabilities, or mentions "create skill", "new skill", or "skill configuration".

skill-creator-agent

242
from aiskillstore/marketplace

Creates Claude Code skills where each skill is tied to a specialist agent optimized with evidence-based prompting techniques. Use this skill when users need to create reusable skills that leverage specialized agents for consistent high-quality performance. The skill ensures that each created skill spawns an appropriately crafted agent that communicates effectively with the parent Claude Code instance using best practices.

micro-skill-creator

242
from aiskillstore/marketplace

Rapidly creates atomic, focused skills optimized with evidence-based prompting, specialist agents, and systematic testing. Each micro-skill does one thing exceptionally well using self-consistency, program-of-thought, and plan-and-solve patterns. Enhanced with agent-creator principles and functionality-audit validation. Perfect for building composable workflow components.

agent-creator

242
from aiskillstore/marketplace

Creates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .claude-flow, combined with evidence-based prompting techniques and Claude Agent SDK implementation. Use this skill when creating production-ready agents for specific domains, workflows, or tasks requiring consistent high-quality performance with deeply embedded domain knowledge.

data-exploration

242
from aiskillstore/marketplace

Systematic database and table profiling for DBX Studio. Use when a user wants to understand their data, explore schema structure, or profile a dataset.