Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
TypeScript SDK Reference
Provides detailed TypeScript SDK documentation for Anthropic's Claude Agent SDK, covering functions, configuration options, and tool interfaces. Includes practical code examples for querying Claude, creating MCP tools, and managing agent interactions programmatically.
context-resume
A sophisticated workflow orchestration skill that provides robust context resumption for plugin development with clear delegation patterns and comprehensive error handling.
1k-i18n
Internationalization and translation guidelines for OneKey. Use when adding text strings, using translations, or working with locales. Triggers on i18n, translation, locale, intl, formatMessage, ETranslations, language, text.
biome-js
Provides specific BiomeJS configuration patterns for JavaScript/TypeScript projects, with examples for extending shared configs, monorepo setups, and Git hooks. Focuses on practical patterns from real projects rather than generic documentation.
payment-integration
This skill provides structured guidance for integrating multiple payment gateways (Stripe, PayPal, Square, Razorpay, Braintree) with a strong focus on PCI DSS compliance, fraud prevention, and secure transaction flows. It outlines a clear workflow from requirements analysis to implementation, covering webhooks, error handling, and multi-currency support.
coding-agent
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
java-coding-standards
Java coding standards for Spring Boot services: naming, immutability, Optional usage, streams, exceptions, generics, and project layout.
orchestration
This skill orchestrates forensic investigations of GitHub repositories by coordinating multiple specialized agents. It manages evidence collection from GH Archive, GitHub API, Wayback Machine, and local git repositories, then forms and validates hypotheses through iterative loops. The workflow produces verified forensic reports with timelines, attribution, and impact analysis.
project-session-management
Track progress across sessions using SESSION.md with git checkpoints and concrete next actions. Converts IMPLEMENTATION_PHASES.md into trackable session state. Use when: resuming work after context clears, managing multi-phase implementations, or troubleshooting lost context.
mcp-cli-scripts
Build CLI scripts alongside MCP servers for terminal environments. File I/O, batch processing, caching, richer output formats. Templates for TypeScript scripts and SCRIPTS.md. Use when: MCP companion scripts, batch processing, saving results to files, CLI API wrappers. Troubleshoot: context too large, no file access, batch input.
using-pmo-team
A highly specialized PMO team skill with excellent governance frameworks, clear role distinctions, and strong enforcement of specialist dispatch patterns.
add-review-comment
Add a review comment to a GitHub pull request.
Plugin Settings
Documents a pattern for storing plugin configuration in .claude/plugin-name.local.md files using YAML frontmatter and markdown. Provides bash examples for reading settings from hooks, commands, and agents with atomic updates and graceful error handling.
libfuzzer
Coverage-guided fuzzer built into LLVM for C/C++ projects. Use for fuzzing C/C++ code that can be compiled with Clang.
raffle-winner-picker
This skill picks random winners from lists, CSV files, Excel spreadsheets, or Google Sheets for giveaways and contests. It uses cryptographically secure random selection, prevents duplicate winners, and provides transparent results with timestamps. Supports weighted selection and runner-up picking.
claudemem-orchestration
This skill coordinates multiple Claude agents to share claudemem analysis results, avoiding redundant computation. It provides concrete patterns for parallel execution, session management, and feedback consolidation. The approach reduces claudemem indexing overhead by running it once per investigation.
systematic-debugging
A structured four-phase debugging methodology that enforces root cause analysis before fixes. Provides concrete steps for investigating bugs, analyzing patterns, testing hypotheses, and implementing solutions. Includes specific checklists, red flags, and common scenario guides to prevent symptom-focused patches.
integrations
A comprehensive integration skill that automates third-party service setup with clear triggers, structured file generation, and practical guidance for developers.
clarify
A structured tool for transforming vague user requests into precise specifications through iterative questioning. It provides a clear protocol with before/after comparison, saves clarified requirements to files, and handles common ambiguity categories like scope, behavior, and constraints.
multi-agent-coordination
Provides concrete patterns for coordinating multiple Claude agents in workflows, focusing on parallel vs sequential execution. Explains the 4-message pattern for true parallelism and file-based delegation to avoid context pollution. Includes agent selection logic and anti-pattern warnings.
sales-comp-plan-designer
Generates sales compensation plans with base/variable splits, accelerators, and quota methods. Provides structured markdown output with recommendations and templates for sales leaders designing incentive programs.
neon-js
A comprehensive skill for setting up Neon's unified JavaScript SDK with excellent documentation, clear use cases, and strong framework support for full-stack applications.
cloudflare-durable-objects
Build stateful Durable Objects for real-time apps, WebSocket servers, coordination, and persistent state. Prevents 20 documented errors. Use when: implementing chat rooms, multiplayer games, rate limiting, session management, WebSocket hibernation, or troubleshooting class export, migration, WebSocket state loss, boolean binding, RPC streams, or binding errors.
cloudflare-turnstile
Add bot protection with Turnstile (CAPTCHA alternative). Use when: protecting forms, securing login/signup, preventing spam, migrating from reCAPTCHA, integrating with React/Next.js/Hono, implementing E2E tests, or debugging CSP errors, token validation failures, Chrome/Edge first-load issues, multiple widget rendering bugs, timeout-or-duplicate errors, or error codes 100*/106010/300*/600*.