发现 Skills

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

Expert in building shareable generator tools that go viral — name generators, quiz makers, avatar creators, personality tests, and calculator tools. Covers the psychology of sharing, viral mechanics, and building tools people can't resist sharing with friends. Use when: generator tool, quiz maker, name generator, avatar creator, viral tool.

End-to-end workflow for creating complete JavaScript concept documentation, orchestrating all skills from research to final review

Premium BrandKit image generation skill for creating high-end brand-guideline boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

Create a PR for the current branch. Use when the user asks to create a pull request, submit PR, or says 'pr'.

Complete memory system combining LanceDB auto-recall, Git-Notes structured memory, and file-based workspace search. Use when setting up comprehensive agent memory, when you need persistent context across sessions, or when managing decisions/preferences/tasks with multiple memory backends working together.

Creates JavaScript classes using Bun's Zig bindings generator (.classes.ts). Use when implementing new JS APIs in Zig with JSC integration.

Writing unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages/tldraw. Covers Vitest patterns, TestEditor usage, and test file organization.

Transforms Claude Code into a fully automated agent system with persistent memory, scheduled operations, computer usage, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging Claude Code's native crons, dispatch, MCP tools, and memory. Used when a user wants continuous automated operations, scheduled tasks, or a self-directed agent loop.

FastAPI patterns for asynchronous APIs, dependency injection, Pydantic request/response models, OpenAPI documentation, testing, security, and production readiness.

Protected Health Information (PHI) compliance, HIPAA adherence, and data security.

Japanese translation: This file requires a Japanese translation for liquid-glass-design.

Use this skill to validate the “why” before building, run product diagnostics, and stress-test product direction before a request becomes an implementation commitment.

Multi-agent adversarial verification with a convergent loop. Two independent review agents must both approve before an output may be released.

Adds x402 payment execution to AI agents with per-task budgets, spend controls, and a non-custodial wallet. Supports Base via agentwallet-sdk and X Layer via OKX Payments / the OKX agent payment protocol.

C# and .NET testing patterns using xUnit, FluentAssertions, mocking, integration testing, and test organization best practices.

Security audit patterns for DeFi automated market makers (AMMs) smart contracts. Covers flash loans, slippage, sandwich attacks, price manipulation, reentrancy, and incorrect integer arithmetic.

Used to retrieve Jira tickets, perform requirements analysis, update ticket status, add comments, or transition issues. Provides Jira API patterns via MCP or direct REST calls.

Laravel-specific patterns, Eloquent ORM, middleware, and the service container.

Japanese translation: This file requires a Japanese translation for plankton-code-quality.

Implement thread-safe data persistence in Swift using actors — combining an in-memory cache with file-backed storage to eliminate data races by design.

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

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

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