Full-stack Claude Code skills for building dApps on the XL1 blockchain. Covers XYO primitives, XL1 chain operations, toolchain config, and prescriptive design patterns (commit-reveal, indexing, prediction markets).
XL1 blockchain development (XYO Layer One). The top skill layer — covers the XL1 chain, datalakes, gateway (generic, browser, and Node), and building dApps. Activates when building on XL1, working with @xyo-network/xl1-* packages, or developing blockchain-backed applications.
Prescriptive design patterns for XL1 dApps. Covers browser UX, chain data indexing, commit-reveal schemes, in-page datalakes, prediction markets, atomic exchange (multi-party escrow), inscription substrates, fungible tokens, and headless dApp verification. Activates when building application-level features on XL1 that require structured data access, multi-party fairness, atomic asset exchange, client-side chain queries, ownable artifacts, token protocols, headless verification of browser dApps, or dApp UI conventions.
Bootstrap a new XL1 application — a single React dApp, a single xl1-service backend, a plain Node.js service/CLI, or a full-stack pnpm monorepo with React + xl1-service + a shared TypeScript library. Activates when the user wants to create, start, bootstrap, initialize, or scaffold a new XL1 project. Do NOT activate for work in an existing project.
Core development standards for TypeScript, Git workflow, testing principles, and development workflow. Activates when writing code, running builds, performing git operations, or completing features.
XY Labs development toolchain (@xylabs packages). Covers @xylabs/toolchain CLI, ESLint flat config, TypeScript config variants, and Vitest. Activates when setting up projects, running builds, configuring linting, or writing tests in XY/XYO/XL1 projects.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Claude Code plugin marketplace for XL1 blockchain and XYO protocol development.
Six skill layers that cascade top-down:
| Layer | Skill | Covers |
|---|---|---|
| 6 | xl1-scaffold | Bootstrap new XL1 apps (React dApp, Node service, monorepo) |
| 5 | xl1-patterns | Commit-reveal, chain data indexing, in-page datalakes, prediction markets |
| 4 | xl1-knowledge | XL1 chain, datalakes, gateway, browser wallet |
| 3 | xyo-knowledge | XYO payloads, bound witnesses, modules, identity |
| 2 | xy-toolchain | @xylabs/toolchain, ESLint flat config, TypeScript config, Vitest |
| 1 | xy-development | TypeScript, Git workflow, testing, dev conventions |
Skills use progressive loading — each SKILL.md is a lightweight router that directs Claude to read sub-files on demand based on task context.
Install the skills from GitHub — no need to clone the repo.
# Add the marketplace
/plugin marketplace add XYOracleNetwork/xl1-skills
# Install the XL1 skill stack
/plugin install xl1-skills
Add to your project's .claude/settings.json so the marketplace is available for all team members automatically:
{
"extraKnownMarketplaces": {
"xl1-skills": {
"source": {
"source": "github",
"repo": "XYOracleNetwork/xl1-skills"
}
}
}
}
Then each team member runs /plugin install xl1-skills once.
For contributors editing skill files, there are three ways to load the plugin from a local checkout.
Load the plugin for a single session — no installation required:
claude --plugin-dir ./plugins/xl1-skills
Register the local checkout as a marketplace so the plugin persists across sessions:
# Inside a Claude Code session:
/plugin marketplace add ./
/plugin install xl1-skills
Add a directory-based marketplace to your .claude/settings.json (project or user level):
{
"extraKnownMarketplaces": {
"xl1-skills": {
"source": {
"source": "directory",
"path": "/absolute/path/to/xl1-skills"
}
}
}
}
Then run /plugin install xl1-skills in your next session.
xl1-scaffold skill)The xl1-scaffold skill invokes a compiled CLI bundled under plugins/xl1-skills/skills/xl1-scaffold/scripts/scaffold/. That directory is generated from the TypeScript source at packages/xl1-scaffold/; it is not hand-authored. Before testing the scaffold skill locally, build it at least once:
corepack enable # first time only — ensures pnpm 10.x is available
corepack pnpm@10 install
corepack pnpm@10 -w run build
The build chain (clean → tsc → copy-templates → sync-to-plugin) compiles the TS source, mirrors the raw template files, and writes the resulting runtime into the skill directory.
Rebuild after any change to packages/xl1-scaffold/src/ or packages/xl1-scaffold/templates/. CI fails the PR if committed source drifts from the synced runtime (git diff --exit-code plugins/xl1-skills/skills/xl1-scaffold/scripts).
Claude Code loads skill content at startup. After editing any skill file, you must reload for changes to take effect:
SKILL.md or sub-file in plugins/xl1-skills/skills//reload-plugins in your Claude Code sessionThere is no file watcher — /reload-plugins is required after every edit.
Each skill is a directory under plugins/xl1-skills/skills/ containing a SKILL.md router and topic sub-files:
plugins/xl1-skills/skills/
├── xy-development/
│ ├── SKILL.md ← router (frontmatter + table of contents)
│ ├── typescript.md
│ ├── git.md
│ ├── testing.md
│ └── workflow.md
├── xy-toolchain/
│ ├── SKILL.md
│ └── ...
└── ...
SKILL.md files require YAML frontmatter with a description field. Claude uses this to decide when to activate the skill:
---
description: When and why Claude should activate this skill.
---
The body is a table of contents linking to sub-files with guidance on when to read each one. Claude loads sub-files on demand, not all at once.
After starting Claude Code or running /reload-plugins:
/help — skills appear as /xl1-skills:<name> (e.g., /xl1-skills:xy-development)Reloaded: 1 plugins · 5 skills · .../xl1-skills:xl1-patternsThe CI workflow validates marketplace and plugin manifests. Run locally:
jq empty .claude-plugin/marketplace.json
jq empty plugins/xl1-skills/.claude-plugin/plugin.json
npx claudepluginhub xyoraclenetwork/xl1-skills --plugin xl1-skillsFull-stack agent skills for building dApps on the XL1 blockchain. Covers XYO primitives, XL1 chain operations, toolchain config, and prescriptive design patterns (commit-reveal, indexing, prediction markets).
Full-stack agent skills for building dApps on the XL1 blockchain. Covers XYO primitives, XL1 chain operations, toolchain config, and prescriptive design patterns (commit-reveal, indexing, prediction markets).
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Payload Development plugin - covers collections, fields, hooks, access control, plugins, and database adapters.
TypeScript/JavaScript full-stack development with NestJS, React, and React Native
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).