全部 Agent Skills
41,263 个结果
- Tooling Nmapn1majne3Canonical Nmap CLI syntax, two-pass scanning workflow, and sandbox-safe bounded scan patterns.
- Tooling Nuclein1majne3Exact Nuclei command structure, template selection, and bounded high-throughput execution controls.
- Tooling Sqlmapn1majne3sqlmap target syntax, non-interactive execution, and common validation/enumeration workflows.
- Tooling Subfindern1majne3Subfinder passive subdomain enumeration syntax, source controls, and pipeline-ready output patterns.
- Trading Strategiesagentmc15Framework for developing, testing, and deploying trading strategies for prediction markets. Use when creating new strategies, implementing signals, or building backtesting logic.
- Tsecbench Fetchn1majne3通过 TSecBench 平台 API 拉取跑分数据、上传 Hosted 镜像、发车与收尾:agent 详情、积分时间线、LLM 会话明细、榜单、COS 直传、创建/结束跑分、实时监控。凡用户给出 tsecbench.zc.tencent.com 链接、提到"跑分记录/会话记录/拉数据/复盘/对比跑分/上传镜像/发车/开始跑分/结束评测"、或要分析某次跑分的 token 消耗、调用节奏、瓶颈时,使用本 skill。
- Tsecbench Hosted Challenge Loopn1majne3Completes a TSecBench Hosted Evaluation Run through the process-isolated Hosted Challenge Client.
- UndocshairyfMinimal Documentation Theme and CLI for shared usage across UnJS projects. Use when creating documentation sites with Nuxt, Nuxt Content, and Nuxt UI.
- UnjshairyfUnJS ecosystem - agnostic JavaScript libraries, tools, and utilities. Use when working with UnJS packages like h3, nitro, ofetch, unstorage, or building universal JavaScript applications.
- UX DesigneragenticsorgExpert UI/UX design guidance for building unique, accessible, and user-centered interfaces. Use when designing interfaces, making visual design decisions, choosing colors/typography, implementing responsive layouts, or when user mentions design, UI, UX, styling, or visual appearance. Always ask before making design decisions.
- ValtiohairyfValtio proxy state management for React and vanilla JavaScript. Use when creating reactive state, managing application state, or working with proxy-based state management.
- Valtio DefinehairyfComprehensive skills for working with valtio-define
- Verify Accepted Steeringn1majne3Checks that Accepted Steering is not replayed after a daemon crash. Use when changing Steering dispatch, the send-start fence, durable Steering transitions, startup recovery, or per-owner dispatch serialization.
- Verify Cyberpendan1majne3Launches an isolated CyberPenda Web UI and real daemon, drives user journeys, and retains verification evidence. Use when proving a UI change, checking persistence, or capturing screenshots of CyberPenda.
- Web ReaderanswerzhaoImplement web page content extraction capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to scrape web pages, extract article content, retrieve page metadata, or build applications that process web content. Supports automatic content extraction with title, HTML, and publication time retrieval.
- WorkflowjohnlindquistManage GitHub Actions workflows using gh CLI. Use to check CI status, view run logs, analyze failures, and rerun workflows.
- Writing Humanizer Zhhairyf去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
- 1NickPappas/move-code-quality-skillNick Pappas技能合集Claude Code skill for analyzing Move packages against the official Move Book Code Quality Checklist
- Agent Context LoaderBbgnsurfTechProactive auto-loading: automatically detects and loads agents.md files Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
- Agent Email Patternsagentmail-toArchitecture patterns for AI agents that communicate over email -- why agents need dedicated inboxes rather than human email accounts, infrastructure/provider tradeoffs, one-inbox-per-agent, two-way conversation loops, human-in-the-loop drafts, WebSocket vs webhook event design, multi-agent topologies, OTP flows, and the threat model (prompt injection, webhook spoofing, credential exposure, data…
- Agentmailagentmail-toBuild with the AgentMail TypeScript or Python SDK for inbox, message, thread, draft, attachment, domain, allow/block list, pod, webhook, and WebSocket workflows, including programmatic agent sign-up, domain/DNS administration, and deliverability triage (bounces, spam, blocked mail).
- Agentmail Cliagentmail-toOperate AgentMail from a shell with the official CLI. Use when the user wants commands for listing or creating inboxes, reading or searching mail, sending or replying, managing drafts, or scripting JSON/YAML output; do not use for SDK code, MCP setup, or framework adapters.
- Agentmail MCPagentmail-toConfigure or troubleshoot the hosted AgentMail MCP server for Codex, Claude Code, Cursor, Claude.ai, ChatGPT, or another Streamable HTTP MCP client. Use for installation, OAuth, API-key headers, connection failures, or MCP tool discovery. Do not use when the connection already works and the user just wants to send, check, or manage mail — use the sibling action skills for that.
- Agentmail Sdkagentmail-toDeprecated alias of the agentmail skill, kept so existing installs and pinned URLs keep resolving. Prefer installing agentmail; this is an identical generated copy covering AgentMail SDK usage in TypeScript and Python.