Loading...
Loading...
Found 2,418 Skills
Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes. Also checks prerequisites when the CLI itself isn't working. Triggers on: "agent not working", "wrong answer", "agent error", "tool call failing", "debug agent", "check logs", "read traces", "broken", "500 error", "424 error", "model access denied", "command not found", "stuck in DELETING", "maxVms exceeded", "cold start diagnosis", "cold start slow", "agentcore create error", "create failed", "exit code 7", "connection refused local dev". Not for deploy failures — use agents-deploy. Not for performance tuning without errors — use agents-optimize. Not for VPC configuration — use agents-build. Not for observability setup or missing logs — use agents-optimize.
Docker and container development agent skill and plugin for Dockerfile optimization, docker-compose orchestration, multi-stage builds, and container security hardening. Use when: user wants to optimize a Dockerfile, create or improve docker-compose configurations, implement multi-stage builds, audit container security, reduce image size, or follow container best practices. Covers build performance, layer caching, secret management, and production-ready container patterns.
Review the diff between the current branch and main as a senior developer. Analyzes architecture, coding standards, security, performance, and correctness. Use when user says 'review my code', 'pre-PR review', 'review diff', 'code review before PR', 'check my changes', or 'senior review'. Do NOT use for only running tests (use a test skill), only linting (use a lint skill), or full PR preparation (use create-pr).
Account-level analysis via Longbridge — total market value, cash share, period P&L, single-stock contribution ranking, industry distribution, currency exposure, historical P/L curve. Requires longbridge login with trade scope. Triggers: "我账户表现", "我本月浮盈", "我哪只股票贡献最多", "我组合配置", "我货币暴露", "我账户行业分布", "账户全貌", "我賬戶表現", "我本月浮盈", "我哪隻股貢獻最多", "我貨幣暴露", "我賬戶行業分佈", "my account performance", "monthly P&L", "biggest contributor", "portfolio breakdown", "currency exposure", "industry mix", "account-level analysis".
Obtain announcement information of A-share listed companies (real data). Based on AkShare, fetch all announcements of the day from Eastmoney.com, supporting filtering by stock code and keywords. Suitable for monitoring key information for investment decisions such as major events, performance express reports, shareholder changes, restructuring announcements, etc. Data source: Eastmoney.com (stable and reliable).
React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). Organizes 70+ rules across 8 priority categories — waterfalls, bundle size, server-side, client fetching, re-render, rendering, JS micro-perf, advanced. Use when writing, reviewing, or refactoring React/Next.js code for performance.
Control a Chrome browser session through the chrome-devtools-axi CLI - navigate, snapshot, click, fill forms, run JavaScript, inspect console and network, take screenshots, audit performance. Use whenever a task needs a real browser: opening or testing a web page, clicking through a flow, extracting page content, or debugging a website.
AFL++ is a fork of AFL with better fuzzing performance and advanced features. Use for multi-core fuzzing of C/C++ projects.
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.
Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.
Implement efficient pagination strategies for large datasets using offset/limit, cursor-based, and keyset pagination. Use when returning collections, managing large result sets, or optimizing query performance.
Rust systems programming patterns and style guide for building reliable systems software. This skill should be used when writing Rust code, especially for systems programming, CLI tools, or performance-critical applications. Covers project organization with Cargo workspaces, module structure, naming conventions (RFC 430), type/trait patterns (Option, builders, associated types), and error handling with thiserror/anyhow.