prompting
PROACTIVE: This skill SHOULD BE USED AUTOMATICALLY when writing prompts, system prompts, crafting instructions for LLMs, or optimizing AI interactions. Triggers on: write prompt, system prompt, prompt engineering, optimize prompt, better prompt, prompt template, instruction design, context engineering, SKILL.md description, agent instructions. Use for CRAFTING LLM PROMPTS. Model-agnostic best practices for coding agents.
What this skill does
# Prompting - Model-Agnostic Best Practices (Late 2025)
Optimal prompt standards for coding agents. Applies to all models (Claude, GPT, Gemini, Grok).
**Paradigm**: Context Engineering > Prompt Engineering. Focus on designing information systems, not "perfect wording". API-level configs (effort, reasoning_effort, thinking_level) are separate from prompt text.
## Quick Reference (Use First)
Before writing/reviewing any prompt, verify:
```
[ ] Structure: Clear XML/Markdown sections (context → task → constraints → output)
[ ] Order: Long context BEFORE query (+30% quality)
[ ] Task: ONE atomic, explicit action
[ ] Output: Format defined (JSON schema, structure)
[ ] Positive: "Do X" instead of "Don't Y"
[ ] Reasoning: Zero-shot for reasoning models (no manual CoT)
[ ] Examples: Few-shot ONLY for format, not logic
[ ] Caching: Static content first, dynamic last
[ ] Simplicity: Start simple, add complexity only if needed (Stanford 8-word)
```
## Decision Flow
```
Task Type?
│
├─ Simple (1 step) ────────────► Direct instruction, no CoT
│
├─ Complex reasoning
│ ├─ Reasoning model (o3/o4/GPT-5/Claude thinking)
│ │ └─► Zero-shot + explicit goal only
│ └─ Standard model
│ └─► Structured prompt + optional CoT
│
├─ Code generation ────────────► Define: language, framework, style
│ Provide: context files, dependencies
│ Specify: output format, tests
│
└─ Multi-step workflow ────────► Break into atomic tasks
Use Orchestrator-Worker pattern
Include verification steps
```
## Core Structure Template
```xml
<context>
[Background, project details - place LONG documents here]
</context>
<task>
[ONE specific action required]
</task>
<constraints>
[Boundaries, limitations]
</constraints>
<output_format>
[Exact format: JSON schema, markdown structure]
</output_format>
```
For **system prompts** (coding agents):
```xml
<role>[Expert domain]</role>
<capabilities>[Tools, what agent CAN do]</capabilities>
<constraints>[Security rules, boundaries]</constraints>
<workflow>[Step-by-step process]</workflow>
<output_standards>[Code style, testing requirements]</output_standards>
```
## Key Principles
| Principle | Do This | Avoid This |
|-----------|---------|------------|
| **Structure** | XML/Markdown sections | Wall of text |
| **Context** | Long docs BEFORE query | Query before context (-30%) |
| **Specificity** | "Dashboard with filtering, export, real-time" | "Create dashboard" |
| **Instructions** | "Return only JSON" | "Don't add explanations" |
| **Reasoning models** | Zero-shot, explicit goal | Manual "think step-by-step" |
| **Examples** | Few-shot for FORMAT only | Few-shot for logic (hurts reasoning) |
| **Caching** | Static first, dynamic last | Dynamic content first |
## Technique Selection
| Technique | Use When | Avoid When |
|-----------|----------|------------|
| **Extended Thinking** | Complex math, multi-step planning | Pattern recognition, simple tasks (can HURT -36%) |
| **Atom of Thoughts** | Parallelizable problems | Creative writing |
| **Tree of Thoughts** | Multiple valid paths | Simple queries |
| **ReAct** | Tool use, external data | Pure reasoning |
| **Self-Consistency** | High-stakes decisions | Speed-critical |
| **Role Reversal** | Need +40% accuracy | Quick drafts |
See details: `references/techniques.md`
## Context Stack (Priority Order)
1. System Instructions (role, rules) - **cached**
2. Long-Term Memory (preferences)
3. Retrieved Documents (RAG)
4. Tool Definitions - **cached**
5. Conversation History
6. Current Task - **last for recency**
## Security
- Separate system/user content with XML tags
- Validate user inputs before embedding
- Validate OUTPUT, not reasoning (CoT hijackable 94-99%)
- Mark sensitive context with explicit boundaries
## References
Load as needed for detailed guidance:
- `references/techniques.md` - AoT, ToT, ReAct, Self-Consistency, Role Reversal, Extended Thinking
- `references/anti-patterns.md` - Full list of what to avoid with explanations
- `references/agentic-patterns.md` - Orchestrator-Worker, Reflexion, Plan-Execute, Tool Orchestration
- `references/memory-patterns.md` - CoALA Framework: Procedural, Semantic, Episodic memory
- `references/meta-prompting.md` - LLM self-optimization workflow
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.