ap-adversaries
This skill should be used when the GM needs to create Apocrypha adversaries, build adversary keyword blocks, design Fear abilities, determine stress thresholds, set adversary tier and difficulty, track adversary stress during encounters, or reference adversary templates and examples for minor, standard, and major tier adversaries.
What this skill does
# Apocrypha Adversary Creation Skill
Create adversaries using the keyword system. Adversaries are defined the same way as player characters: by keywords with modifiers. This skill provides templates, tier guidelines, and examples.
**Authoritative Source**: For complete rules, use the `ap-rules` skill. For combat procedures, use the `ap-combat` skill.
## Adversary Structure
Every Apocrypha adversary is defined by:
1. **Keywords**: Same as player characters. Natural-language phrases with modifiers.
2. **Stress threshold**: Total stress the adversary can absorb before defeat.
3. **Fear abilities**: Special capabilities the GM activates by spending Fear tokens.
4. **Tier**: Minor, standard, or major, determining keyword count, threshold, and Fear ability budget.
## Tier Reference
| Tier | Keywords | Stress Threshold | Fear Abilities | Typical Difficulty |
|------|----------|-----------------|----------------|------------|
| Minor | 2-3 | 2-3 | 0-1 (cost 1 each) | 10-14 |
| Standard | 3-4 | 4-6 | 1-2 (cost 1-2 each) | 14-17 |
| Major | 4-6 | 8-12 | 2-4 (cost 1-3 each) | 17-20 |
### Stress Tracking by Tier
- **Minor**: Aggregate stress pool. Single counter toward threshold. GM narrates which capability degrades.
- **Standard and major**: Per-keyword tracking. Stress is allocated to specific keywords, each degrades independently, and total across all keywords counts toward the threshold.
## Creating an Adversary: Step by Step
### Step 1: Define the Concept
What is this adversary? What role does it play in the story? What makes it interesting or threatening?
### Step 2: Choose Tier
| Tier | Use When |
|------|----------|
| Minor | Thugs, wild animals, minor obstacles. Defeated quickly. |
| Standard | Rivals, monsters, meaningful threats. A real fight. |
| Major | Bosses, dragons, nemeses. A defining encounter. |
### Step 3: Write Keywords
Adversary keywords follow the same rules as player keywords:
- Natural-language phrases with modifiers (+1 to +3)
- Each keyword describes a capability, trait, or nature
- Keywords are fixed once introduced; no inventing new capabilities mid-encounter
**Guidelines**:
- Minor: 2-3 keywords at +1 to +2
- Standard: 3-4 keywords at +1 to +3
- Major: 4-6 keywords at +2 to +3
### Step 4: Set Stress Threshold
Choose a threshold within the tier's range. Higher thresholds make the fight longer.
- Minor: 2-3 (one or two successful hits defeats it)
- Standard: 4-6 (requires sustained effort)
- Major: 8-12 (a protracted, dramatic fight)
### Step 5: Set Difficulty
The difficulty is the target number for player rolls against this adversary. The tier's typical range is a starting point; adjust based on the fiction and the specific action.
- Minor: typically 10-14
- Standard: typically 14-17
- Major: typically 17-20
### Step 6: Design Fear Abilities
Fear abilities are special capabilities the GM triggers by spending Fear tokens. The cost is defined per ability when the adversary is created.
**Design guidelines**:
- Each ability should have a clear narrative effect
- Cost should match impact: 1 Fear for tactical effects, 2-3 Fear for dramatic ones
- Abilities should create interesting choices, not remove player agency
**Good Fear abilities**:
- Inflict stress on specific keyword types
- Change the battlefield or environment
- Call reinforcements or allies
- Create narrative complications
- Force the player to react
**Avoid**:
- Effects with no counterplay
- Removing player choice entirely
- Effects that bypass the stress system
### Step 7: Record the Adversary
Write the adversary's keyword block into `world.md` when introducing a significant adversary. Minor adversaries encountered once can be narrated inline.
Use `references/adversary-template.md` for the format.
## Adversary Keyword Design
### Keyword Quality
Adversary keywords should evoke the creature's nature and suggest how it fights:
Good: "Ancient Terror of the Skies (+3)" tells you this is a flying predator that has dominated its territory for ages.
Bad: "Strong (+2)" tells you nothing about the adversary's nature or how to narrate its actions.
### Keyword Coverage
Keywords should cover the adversary's main capabilities:
- How it fights (offensive)
- How it defends (defensive or evasive)
- What makes it special (unique trait)
- What drives it (motivation, for major adversaries)
### Stressed Keyword Narration
When an adversary keyword takes stress, narrate the degradation:
- "Pack Tactics (+2)" at 1 stress: the coordination falters, wolves bumping into each other
- "Impenetrable Scales (+3)" at 2 stress: cracks appear, showing vulnerable flesh
- "Ancient Terror of the Skies (+3)" at 3 stress: one wing drags, flight is labored
## Using the Dice Tool
Adversaries don't roll in Apocrypha (player-rolls-everything), but the GM uses difficulty numbers derived from the adversary's tier. The player rolls against these difficulties.
**Player attacking a standard adversary (difficulty 14, keyword +2)**:
```json
{ "groups": [{ "n": 1, "d": 12, "label": "hope" }, { "n": 1, "d": 12, "label": "fear" }], "modifier": 2, "threshold": 14 }
```
## References
- `references/adversary-template.md` - Adversary block format
- `references/adversary-examples.md` - One example of each tier (minor, standard, major)
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.