浏览和安装 Killer-Skills 目录中的数千个 AI Agent 技能。支持 Claude Code、Windsurf、Cursor 等。
Format high-quality Git commit messages from staged or unstaged changes with stable conventions. Use when Codex is asked to create, polish, or validate commit messages, especially for Conventional Commits, commitlint-compatible repositories, squash/fixup flows, or teams that require consistent subject/body/footer structure.
gws-chat 是一个独立的、开源的 Google Chat CLI 工具
One-time git account setup (user.name, user.email) and commit workflow. Use when the user asks to set up git, configure git identity, or when git user.name/user.email appear unset. After setup, use Git MCP tools or the commit script for commits with messages.
This skill should be used when the user wants to commit their work to git and push to GitHub. It guides through reviewing changes, crafting meaningful commit messages following project conventions (including Conventional Commits when detected), creating commits with security checks, and pushing to remote repositories.
This skill provides comprehensive guidance for inter-agent communication using the Synapse A2A framework. Use this skill when sending messages to other agents via synapse send/reply commands, understanding priority levels, handling A2A protocol operations, managing task history, configuring settings, or using File Safety features for multi-agent coordination. Automatically triggered when agent communication, A2A protocol tasks, history operations, or file safety operations are detected.
Triage and process WhatsApp action files from the AI Employee vault. This skill should be used when WHATSAPP_*.md files appear in /Needs_Action folder, or when user asks to handle WhatsApp messages, draft replies, or generate invoices from chat requests. Reads message content, detects intent, creates Plan.md with steps, and always routes replies to /Pending_Approval — never sends directly to WhatsApp without human approval.
This skill should be used when the user asks to create an esphome config, set up an esp32 device, configure esphome yaml, add a sensor to esphome, fix esphome compile error, or mentions gpio pin assignment, wifi setup, ota update, or error messages like Unknown platform, GPIO already in use, Could not compile, or WiFi connection failed. Provides rapid ESPHome configuration generation, troubleshooting, and validation.
Write, critique, and iterate prompts for OpenAI GPT-5 series models. Use for tasks like: (1) turning vague requirements into high-signal instructions, (2) selecting between quick vs deep reasoning behaviors, (3) creating robust structured-output prompts (JSON schemas, tool calls), (4) designing evaluation prompts and rubrics, and (5) debugging prompt failures (hallucinations, format drift, tool misuse). Trigger when the user mentions GPT-5, prompt engineering, system/developer messages, structured outputs, agent prompts, or wants best-practice templates.
Follow project structure standards, environment variable management, Content Collections setup, version control practices, and build/deployment conventions. Use this skill when setting up project structure, managing configuration files, organizing dependencies, or establishing development workflows. When working on project directory structure and organization, environment variable files (.env, .env.local, .env.production), Content Collections configuration (src/content/config.ts), package.json and dependency management, git commit messages and branching strategy, configuration files (astro.config.mjs, tsconfig.json), build and deployment setups, or documentation files (README.md, ADRs).
Implement comprehensive input validation on server-side with complementary client-side validation for user experience, using allowlists, type checking, and sanitization to prevent injection attacks. Use this skill when validating user inputs, form data, API requests, file uploads, query parameters, or any external data entering the application. Apply this skill when implementing server-side validation as the primary security layer, adding client-side validation for immediate user feedback, validating data types and formats, checking ranges and required fields, sanitizing inputs to prevent SQL injection and XSS attacks, using allowlists over blocklists, providing field-specific error messages, or enforcing business rules at appropriate application layers. This skill ensures validation happens at all entry points consistently, security is never dependent on client-side checks alone, users receive helpful immediate feedback, and data integrity is maintained through multiple layers of validation.