compact-examples

Verification framework for Midnight claims — verifies Compact code by compiling and executing test contracts, SDK/TypeScript claims by type-checking and devnet E2E testing, ZKIR circuits by running through the WASM checker and inspecting compiled structure, witness implementations by cross-domain type-checking and execution against compiled contracts, or by inspecting source code. Multi-agent pipeline with explicit /verify command.

19 skills · 2 commands · 7 agents · hooks

Core knowledge for writing Midnight Compact smart contracts — contract structure, data types, ledger declarations, circuits, witnesses, and common patterns.

15 skills · 3 commands · 3 agents · hooks

Installs, configures, and manages the Midnight Network development toolchain — Compact CLI, compiler version switching, local devnet (node, indexer, proof server), diagnostics, and release notes for all Midnight components.

6 skills · 5 commands

Code quality tooling for Midnight Network projects — linting, formatting, type checking, testing, Git hooks, and CI workflows.

7 skills · 2 agents

Conceptual foundations for understanding the Midnight Network: architecture, data models, privacy patterns, protocols, tokenomics, and zero-knowledge proofs

6 skills · 1 agent

Fact-checking pipeline for Midnight content — extracts testable claims from any source (markdown, code, PDFs, URLs, GitHub repos), classifies them by domain (Compact, SDK, ZKIR, Witness), and verifies each claim using the midnight-verify framework. Produces structured JSON artifacts and human-readable reports.

3 skills · 2 commands · 2 agents

Collection of example skills demonstrating various capabilities including skill creation, MCP building, visual design, algorithmic art, internal communications, web testing, artifact building, Slack GIFs, and theme styling

19 skills

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

A comprehensive example plugin demonstrating all Claude Code extension options including commands, agents, skills, hooks, and MCP servers

2 skills · 1 command · 1 MCP server

Behavioral skills for AI-specific failure patterns: hidden code debt from agent generation and context compaction amnesia via behavioral self-enforcement

3 skills

A second brain for Claude Code + Obsidian inspired by Karpathy's LLM Wiki gist. Turn any LLM CLI into a disciplined wiki maintainer: incrementally ingest sources into a persistent, interlinked markdown vault; update entity/concept/source pages; flag contradictions; maintain index and append-only log. Knowledge compounds instead of being re-derived by RAG on every query. Ships 3 sub-agents (wiki-ingestor, wiki-librarian, wiki-linter), 5 slash commands (/wiki-init, /wiki-ingest, /wiki-query, /wiki-lint, /wiki-log), 8 Python tools (stdlib only: init_vault, ingest_source, update_index, append_log, wiki_search BM25, lint_wiki, graph_analyzer, export_marp), 8 reference docs, full vault templates (CLAUDE.md, AGENTS.md, cursorrules, 5 page templates), and a worked example vault. Cross-tool compatible with Claude Code, Codex CLI, Cursor, Antigravity, OpenCode, and Gemini CLI.

1 skill · 5 commands · 3 agents

Persistent memory with session tracking, compaction recovery, and Memory Protocol. Gives Claude a brain that survives across sessions.

1 skill · hooks