发现 Skills

Generate images using nano banana.

Set reminders using natural language. Automatically creates one-time cron jobs and logs to markdown.

Use this when new translation keys are added to packages to generate new translation strings

Debug AOTInductor (AOTI) errors and crashes. Use when encountering AOTI segfaults, device mismatch errors, constant-loading failures, or runtime errors from aot_compile, aot_load, aoti_compile_and_package, or aoti_load_package.

Master systematic debugging techniques, profiling tools, and root-cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.

This skill should be used when the user asks to "calculate TAM", "determine SAM", "estimate SOM", "size the market", "calculate market opportunity", "what's the total addressable market", or requests market sizing analysis for a startup or business opportunity.

Test smart contracts comprehensively using Hardhat and Foundry with unit tests, integration tests, and mainnet forking. Use when testing Solidity contracts, setting up blockchain test suites, or validating DeFi protocols.

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for the Web and accessibility features for Web and native platforms (iOS/Android).

Designs and optimizes an AI agent's action space, tool definitions, and observation formats to improve completion rates.

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

An evidence-based automated inventory and overlap-audit workflow for ECC. Used when a user wants to know which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before applying fixes.

Playwright E2E testing patterns, page object model, configuration, CI/CD integration, artifact management, and flaky-test strategies.

GAN (Generative Adversarial Network)-style evaluation harness, image-generation pattern, and quality metrics.

Access control and authorization patterns for APIs, agents, and LLM endpoints.

Idiomatic Kotlin patterns, best practices, and conventions for building robust, efficient, and maintainable Kotlin applications, including coroutines, null-safety, and DSL builders.

Japanese translation: this file requires a Japanese translation for the motion-patterns collection.

Japanese translation: This file requires a Japanese translation for plan-orchestrate.

Weighted social-graph ranking for warm-intro discovery, bridge scoring, and network-gap analysis on X and LinkedIn. Intended for use when the user needs the ranking engine itself (rather than broader promotion or network-maintenance workflows).

Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated working trees, monitor progress, and read structured reports.

Use only when authoring/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers.

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Uses a content-engine pattern to adapt content for each platform. Does not post identical content cross-platform. Use when you want to distribute content across social platforms.

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

Hermes data import, mapping, transformation, and data integrity validation.

Kotlin coroutines and Flow patterns for Android and KMP — structured concurrency, Flow operators, StateFlow, error handling, testing.