Build full-stack dApps on Ritual Chain using skills and agents that generate Solidity smart contracts with async precompiles for on-chain ML inference, HTTP/LLM calls, scheduling, secrets, X402 payments; create React/Next.js frontends with wagmi hooks; set up backends, testing, debugging, and deployment workflows from idea to verification.
npx claudepluginhub ritual-foundation/ritual-dapp-skills --plugin ritual-dapp-skillsQuick diagnostic lookup for Ritual dApp debugging.
Deterministic, RPC-only debugging flow for scheduled and scheduled-async transactions.
End-to-end Ritual Chain dApp builder. Use this agent when building complete applications on Ritual Chain, from idea through implementation. <example> Context: User wants to build a dApp on Ritual user: "Help me build a verifiable AI oracle on Ritual Chain" assistant: "I'll use the ritual-dapp-builder agent to guide you through building this — starting with feature selection, then contracts, frontend, and testing." <commentary> User wants to build a complete dApp. The agent orchestrates feature selection, architecture, smart contracts, frontend, and testing. </commentary> </example> <example> Context: User describes a multi-feature dApp user: "I want an app that streams LLM responses and stores encrypted results" assistant: "I'll launch the ritual-dapp-builder agent to design and implement this streaming + privacy dApp." <commentary> Multi-feature dApp. The agent selects the right skills (streaming LLM, private outputs) and builds end-to-end. </commentary> </example>
Debugs Ritual Chain dApp issues: stuck transactions, missing callbacks, empty results, balance errors, encoding mismatches. Activates after builds, on detected issues, or on-demand. <example> user: "My HTTP call transaction is stuck in pending for 20 minutes" assistant: "Diagnosing: checking executor availability, TTL, and wallet balance via chain queries." </example> <example> user: "The job shows as settled but my contract never received the result" assistant: "Checking delivery selector, callback gas limit, and contract handler." </example> <example> user: "I'm getting an empty bytes response from my LLM precompile call" assistant: "Checking ABI encoding, model configuration, and executor capability." </example>
Backend services for Ritual dApps. Use when building event indexers, APIs, job monitors, or webhook services for Ritual applications.
Block-time estimation and block-to-time conversion guidance for Ritual dApps. Use when setting TTL, lock durations, scheduler frequency, or polling windows.
Ritual chain precompile addresses, system contracts, ABI encoding, and callback security. Use when writing Solidity contracts that call Ritual precompiles, handle async callbacks, or interact with the Scheduler and RitualWallet.
Data Availability (storage) patterns for Ritual dApps. Use when any precompile stores or retrieves external data — multimodal outputs, conversation history, agent state, FHE ciphertexts, or artifact files.
Deployment and chain configuration for Ritual dApps. Use when deploying contracts, configuring chain connection, or setting up development environment.
Ritual dApp design system — dark-mode-first color tokens, typography, Tailwind config, async lifecycle state visuals, precompile icons, and AI slop prevention. Use when styling a Ritual Chain frontend, building React/Next.js UI components, implementing async precompile status indicators, or reviewing dApp visual design for brand consistency.
On-chain Ed25519 signature verification via native precompile. Use when verifying Solana signatures, SSH keys, or any Ed25519-signed data on-chain.
Frontend development for Ritual dApps with async transaction state machines, wagmi/viem hooks, and event subscriptions. Use when building React/Next.js frontends for Ritual.
HTTP call precompile patterns for Ritual dApps. Use when building dApps that fetch external data, call APIs, or interact with web services on-chain.
Long-running HTTP precompile (0x0805) patterns for Ritual dApps. Use when building dApps with submit-poll-deliver workflows, background API jobs, multi-minute external tasks, JQ-based result extraction, or long-running (2-phase) async delivery.
Image, audio, and video generation for Ritual dApps. Use when building dApps with AI multimodal creation capabilities.
On-chain ML model inference via the ONNX precompile. Use when building dApps that run machine learning models directly on-chain with synchronous results.
High-level Ritual Chain architecture for dApp developers. Use when starting a new dApp, understanding async patterns, or getting oriented with Ritual's capabilities.
Passkey (WebAuthn / P-256) authentication for Ritual dApps. Use when building dApps with passkey login, passwordless wallets, or SECP256R1 signature verification.
Complete Ritual precompile ABI reference. Use when encoding/decoding precompile calls, understanding request/response formats, or debugging precompile interactions.
Scheduled operations for Ritual dApps. Use when building dApps with time-delayed execution, recurring tasks, or automated workflows.
Secret management and private outputs for Ritual dApps. Use when handling encrypted secrets, private execution results, or delegated access control.
Testing and debugging patterns for Ritual dApps. Use when writing tests, debugging issues, or setting up CI/CD for Ritual applications.
RitualWallet integration for Ritual dApps. Use when depositing fees, checking balances, managing lock durations, or withdrawing funds.
X402 micropayment and paid API access patterns for Ritual dApps. Use when building dApps that need automatic paid API access, micropayment flows, per-call payment for premium APIs, budget-controlled data access, shared credential management via dKMS, or metered on-chain API usage. Do NOT use for free/public API calls — use ritual-dapp-http instead.
Agent meta-kernel that activates 10 behavioral protocols governing how the agent works on Ritual Chain. Loaded automatically by the front door, builder, and debugger.
Detects when the agent's trajectory has diverged from the user's goal. Uses weighted progress markers, stall detection, and divergence heuristics. Stops before wasting budget.
Lazy goal-state variance reduction. Generates 0-5 contextual questions just-in-time based on the user's stated goal. Never presents a static questionnaire.
Defines when and how to pull the user for a decision mid-session. Only at architectural forks that are expensive to switch and not resolvable by search.
Generates contextual dApp ideas by searching for what's trending in blockchain and AI right now, then filtering for applications that maximally exploit Ritual Chain's unique precompile capabilities. Invoked by the front door when the user doesn't specify what they want to build.
Steers the agent toward autonomous resolution over interactive questioning. Search before asking. Track budget in turns. Announce standard decisions without requesting permission.
Defines how the agent interleaves build (α) and debug (β) work. Four principles for atomic verification, monotonic progress, phase-aware depth, and context-preserving handoffs.
Transforms a raw dApp idea into a Ritual-native specification by mapping every capability to the optimal Ritual precompile or system contract. Runs after intent classification, before the builder agent begins its phased protocol.
Non-interactive verification protocols for every Ritual skill. Per-skill checks, cross-skill integration checks, and unified E2E user journey verification. Load only the protocols for skills this project uses.
Ritual dApp development entrypoint. Use when the user types /ritual to get started building on Ritual Chain.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
AI image generation Creative Director powered by Google Gemini Nano Banana models. Claude interprets intent, selects domain expertise, constructs optimized prompts, and orchestrates Gemini for best results.
Qiushi Skill: methodology skills for AI agents guided by seeking truth from facts, with Claude Code, Cursor, OpenClaw, Codex, OpenCode, and Hermes guidance.
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Skills and agents that teach AI coding assistants how to build dApps on Ritual.
# Claude Code
git clone https://github.com/ritual-foundation/ritual-dapp-skills.git .claude/skills/ritual-dapp-skills
# Then tell your agent:
Read the file skills/ritual/SKILL.md and follow its instructions.
WALLET: 0xYOUR_FUNDED_WALLET_ADDRESS_DAPP_CAN_BE_DEPLOYED_FROM
Build me a chatbot that runs on-chain with streaming responses.
For Cursor, OpenClaw, Hermes, and other harnesses, see the microsite.
The system has two entry points, three skill classes, and 10 behavioral protocols running as background middleware.
You describe what you want. The agent activates its behavioral protocols, loads the right skills, builds in phases, verifies each phase, and debugs automatically.
| Entry | Who | What It Does |
|---|---|---|
skills/ritual/SKILL.md | Human | Classifies intent (build / debug / learn), runs inspiration if no idea, runs projection to map idea to precompiles, routes to the right agent |
skills/ritual-meta-bootstrap/SKILL.md | Agent | Activates 10 behavioral rules as invisible middleware for the entire session |
Ω Meta — Loaded unconditionally. 10 behavioral rules, inspiration (JIT idea generation from live trends), projection (idea-to-Ritual-spec transformation), verification (per-skill checks + 12-step E2E journey).
α Build — Feature skills loaded conditionally per the user's goal. The builder agent selects 3-6 per project. Phased execution: architecture → contracts → frontend → backend → testing → deploy.
β Debug — Diagnostic skills loaded reactively. Sequential pipeline: triage → smoke tests → quick-match 10 known root causes → systematic diagnosis → fix + verify.
| # | Rule | Purpose |
|---|---|---|
| 1 | Track Cost | Turn budget governs all thresholds |
| 2 | Distrust Priors | Ritual violates Ethereum assumptions. No Infernet. |
| 3 | Lazy Elicitation | 0-5 JIT questions, never a static form |
| 4 | Interleave Build+Debug | Verify after every irreversible action |
| 5 | Circuit Breaker | Detect trajectory divergence, stop before wasting budget |
| 6 | Search Before Asking | Exhaust 5-step resolution hierarchy first |
| 7 | Ask at Forks | Only for expensive preference-based forks |
| 8 | Anti-Slop | Dimensional decomposition for UI artifacts |
| 9 | Verify Non-Interactively | Per-skill checks + 12-step E2E journey |
| 10 | Scope to Project Directory | All writes within project root, no cross-pollution |
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim