发现 Skills

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.

List the contents of an npm package tarball before publishing. Use when the user wants to see what files are included in an npm bundle, verify package contents, or debug npm publish issues.

How to add or modify Next.js experimental feature flags end-to-end. Use when editing config-shared.ts, config-schema.ts, define-env-plugin.ts, next-server.ts, export/worker.ts, or module.compiled.js. Covers type declaration, zod schema, build-time injection, runtime env plumbing, and the decision between runtime env-var branching vs separate bundle variants.

Implement comprehensive evaluation strategies for LLM applications using automated metrics, human feedback, and benchmarking. Use when testing LLM performance, measuring AI application quality, or establishing evaluation frameworks.

Design a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features

Telegram 生态开发全栈指南 - 涵盖 Bot API、Mini Apps (Web Apps)、MTProto 客户端开发。包括消息处理、支付、内联模式、Webhook、认证、存储、传感器 API 等完整开发资源。

HIPAA-compliant implementation, security controls, audit logging, and data protection strategy.

Japanese translation: This file requires a Japanese translation for netmiko-ssh-automation.

Forge a complete "lobster soul" plan for the OpenClaw AI Agent. Based on user preferences or random gacha draws, output identity positioning, a soul description (SOUL.md), role-based baseline rules, a name, and avatar raw-image prompt. If the current environment provides an approved raw-image skill, the system can automatically generate a unified-style avatar image. Use this when a user needs to create, design, or customize an OpenClaw lobster soul. Not suitable for: fine-tuning an existing SOUL.md, role design for non-OpenClaw platforms, or purely tool-like agents without personality. Trigger words: lobster soul, shrimp soul, OpenClaw soul, shrimp-raising soul, lobster character, lobster positioning, lobster murder-mystery character, lobster game character, lobster NPC, lobster personality, lobster backstory, lobster SOUL, gacha.

Japanese translation: This file requires a Japanese translation for production-audit.

Japanese translation: This file requires a Japanese translation for 'quality-nonconformance'.

A decision framework for choosing between regular expressions and large language models for parsing structured text — start with regular expressions and add LLMs only for low-confidence edge cases.

Visualize whether skills, rules, and agent definitions are actually being followed — automatically generate scenarios at three prompt-strictness levels, run agents, classify their action sequences, and report compliance rates for the complete tool-call timeline.

Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.

Prevent silent decimal-mismatch bugs across EVM chains. Covers runtime decimal queries, chain-aware caching, precision drift of bridged tokens, and safe normalization for bots, dashboards, and DeFi tools.

Japanese translation: This file needs a Japanese translation for the motion-patterns project.

gget: a CLI and Python workflow for quick queries of genome reference databases, sequence searches (BLAST-style), enrichment checks, and reproducible bioinformatics evidence logs.

A skill that can retrieve A2UI UI JSON schematics and UI templates that best show the response. This skill is essential and must be used before generating A2UI (Agent-to-UI) JSON responses.

Fetch all GitHub issues via gh CLI and use AI agents to deeply analyze, cluster, and prioritize issues

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

This skill should be used when the user asks to "pentest AWS", "test AWS security", "enumerate IAM", "exploit cloud infrastructure", "AWS privilege escalation", "S3 bucket testing", "metadata SSRF", "Lambda exploitation", or needs guidance on Amazon Web Services security assessment.

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with a features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.