Install
$ agentstack add skill-epicsagas-velith-book-game ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Game Scenario Patterns
Story architecture: Main scenario (critical path, 60%) + Side scenarios (optional, 30%) + Hidden scenarios (easter eggs, 10%). Critical path must work standalone; side scenarios enrich but never gate main progression.
Branching structure: Binary choice (A/B), multi-way (3+ options), conditional (requires item/flag), timed (deadline-based). Branch depth: ≤4 levels before convergence. Convergence types: full (all paths merge), partial (some carry forward), butterfly (small choice → big consequence later).
Quest design: Objective (clear goal) → Prerequisites (what player needs) → Steps (3-7 per quest, each with verification) → Branch points (player agency) → Resolution + Reward. Quest chains: linear (A→B→C), hub (return to base between quests), parallel (simultaneous tracks).
Dialogue system: Dialogue nodes with speaker, line, emotion tag, and next-node links. Player responses: investigate (info), persuade (relationship), action (consequence). Branch dialogue: ≤3 choices per node. Emotional tone tracking per NPC (friendly/neutral/hostile affects available options).
World-building layers: Geography (maps, regions, travel routes) → History (timeline, key events, ruins) → Culture (factions, beliefs, customs, taboos) → Economy (resources, trade, scarcity) → Ecology (creatures, environments, hazards). Each layer must be consistent and interconnected.
Character arc across routes: Core identity (consistent across all routes) + Route-specific development. NPC relationship system: trust level (0-100) with threshold gates. Companion characters: personal quest triggered by trust threshold.
Lore bible: Entry per: location, character, faction, item, event, concept. Fields: name, description, connections (linked entries), game-mechanic relevance, narrative role. Consistency check: cross-reference all entries before finalizing.
Scenario document structure: Overview (concept, tone, themes) → World bible → Character bible → Main quest line → Side quests → Dialogue trees → Cutscene scripts → Branching map (visual flowchart). Each quest has: ID, title, summary, prerequisites, steps, branches, rewards, flags set.
Format: Markdown with YAML frontmatter per quest/node. Branching maps as Mermaid flowcharts. Dialogue as structured blocks with speaker/emotion/response fields.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: epicsagas
- Source: epicsagas/Velith
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.