发现 Skills

Kotlin testing frameworks, assertions, mocks, and coroutine testing.

Japanese translation: This file requires a Japanese translation for llm-trading-agent-security.

Open-source pipeline: fork, sanitize, and package private projects for safe public release. Chain three agents (Forker, Sanitizer, Packager). Triggers: '/opensource', 'open source this', 'make this public', 'prepare for open source'.

Quarkus project verification loop: build, static analysis, coverage-enabled testing, security scanning, native compilation, and differential review before production or before a PR.

Search existing skills in local, marketplace, GitHub, and the web before creating a new skill. Used when creating, building, forking, or searching for skills.

Audits the quality of Claude skills and commands. Supports a quick-scan mode (only changed skills) and a full stocktake mode, using sequential sub-agents to evaluate skills in batches.

Use when managing an Uncloud cluster — deploying services, configuring Caddy ingress, adding static proxy routes for non-cluster devices, publishing ports, scaling, inspecting logs, or managing machines and volumes with the `uc` CLI.

Build a persistent multi-agent operating system on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without an external database.

Tracks and reports Claude Code token usage, spending, and budgets from a local cost-tracking database. Use this when asking about costs, spending, usage, tokens, budgets, or cost breakdowns by project, tool, session, or date.

Japanese translation: This file needs a Japanese translation for make-interfaces-feel-better.

Japanese translation: This file requires a Japanese translation for the product-capability.

Automate Composio Search tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Parsehub tasks via Rube MCP (Composio). Always search tools first for current schemas.

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.

Firebase gives you a complete backend in minutes - auth, database, storage, functions, hosting. But the ease of setup hides real complexity. Security rules are your last line of defense, and they're often wrong. Firestore queries are limited, and you learn this after you've designed your data model. This skill covers Firebase Authentication, Firestore, Realtime Database, Cloud Functions, Cloud Storage, and Firebase Hosting. Key insight: Firebase is optimized for read-heavy, denormalized data.

Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.

Expert guidance for distributed NoSQL databases (Apache Cassandra, ScyllaDB, Amazon DynamoDB). Focuses on mental models, query-first modeling, single-table design, denormalization, and avoiding hot partitions in high-scale systems.

Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent behavior.

Schedule reminders and recurring tasks.

Master authentication and authorization patterns including JWT, OAuth2, session management, and RBAC to build secure, scalable access control systems. Use when implementing auth systems, securing APIs, or debugging security issues.

Capture architecture decisions made during Claude Code sessions as structured Architecture Decision Records (ADRs). Automatically detect decision moments and record the context, considered alternatives, and rationale. Maintain an ADR log so future developers understand why the codebase was built the way it is.

Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.

Used to retrieve Jira tickets, analyze requirements, update ticket status, add comments, or perform issue transitions. Provides Jira API patterns via MCP (mcp-atlassian) or direct REST calls.

JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in Spring Boot.