3199 个 · 按相关度排序
Extract text, tables, and attributes from rendered web pages into structured data. Check extracted content for personal information and malicious instructions, and save reusable extraction templates for pages on the same host.
中文简介正在准备中。当前显示英语简介。
Audit business addresses on contact pages and footers for completeness and clear HTML markup. Compare visible details with structured data, which describes the business to search engines, and Google Business Profile to identify inconsistencies.
中文简介正在准备中。当前显示英语简介。
Audit and add structured organization data on a business or brand homepage. Check machine-readable details such as the official name, logo, contact information, and social profiles to help Google understand the organization and its search information panel.
中文简介正在准备中。当前显示英语简介。
Audit informational pages so AI assistants can extract and understand their content. Review headings, HTML structure, content availability without JavaScript, and structured data, then suggest changes that make individual sections clearer when read on their own.
中文简介正在准备中。当前显示英语简介。
Audit a business website for inconsistent names, addresses, and phone numbers. Compare visible page content with structured data, then standardize spelling and formatting to support accurate business information in local search.
中文简介正在准备中。当前显示英语简介。
Review and fix breadcrumb HTML so readers, including people using screen readers, can understand site hierarchy and their current location. Check navigation labels, ordered lists, current-page attributes, and consistency with structured data.
中文简介正在准备中。当前显示英语简介。
Review author information in structured data, a machine-readable description of page content. Check names, profile links, and connections to articles or pages, then identify corrections using the rendered HTML and HTTP response.
中文简介正在准备中。当前显示英语简介。
Build editable Three.js worlds from text or structured briefs, with terrain, distinct regions, landmarks, vegetation, and camera paths. Review the environment from multiple viewpoints and refine selected areas while preserving the overall layout and reproducible settings.
中文简介正在准备中。当前显示英语简介。
Build prompts for FLUX image generation and editing, with guidance on model selection, lighting, composition, text, and precise colors. It also covers structured scene descriptions using JSON and editing with multiple reference images.
中文简介正在准备中。当前显示英语简介。
Plan and edit a presentation explaining the progression from unstructured Claude Code use to configured engineering workflows. It provides a teaching sequence, proficiency levels, and a TodoApp example connecting project instructions, skills, agents, and automation.
中文简介正在准备中。当前显示英语简介。
Set up and inspect an Ethereum node through a command-line interface. Install execution and consensus clients, configure validator metadata, expose RPC access for external requests, and retrieve structured health reports for agent workflows.
中文简介正在准备中。当前显示英语简介。
Develop and prioritize early research ideas through independent brainstorming, structured discussion, evidence checks, and critical review. Keep assumptions, uncertainty, dissent, and scoring reasons visible, then record the human decision and appropriate next steps.
中文简介正在准备中。当前显示英语简介。
Delegate a clearly scoped repository analysis or implementation task to Pi without an interactive session. The skill limits the working directory and available tools, then checks structured output for errors before using the result.
中文简介正在准备中。当前显示英语简介。
Delegate a bounded task to the local OpenClaw main agent without opening an interactive interface. Run it in an authorized directory, read its structured response, and check for reported errors or timeouts.
中文简介正在准备中。当前显示英语简介。
Read a supplied paper in depth and produce a structured Markdown explanation of its research logic, essential design choices, and evidence limits. Work through key equations with concrete numerical examples and identify missing controls or unreported information.
中文简介正在准备中。当前显示英语简介。
Turn one scientific paper into a structured, 16-section reading card. Break down its methods, connect claims to experimental evidence, identify limitations, and develop research hypotheses, with source references and clear labels for anything the supplied material cannot support.
中文简介正在准备中。当前显示英语简介。
Convert existing scripts, CLI tools, or Crawlee projects into reusable Apify Actors, programs packaged as Docker images. Define JSON inputs and outputs, integrate the SDK, test locally, and deploy to Apify.
中文简介正在准备中。当前显示英语简介。
Design or review command-line tools that AI agents can call. Use 98 proposed rules to define structured output, input validation, error handling, safety controls, and help information, with three levels for gradual adoption.
中文简介正在准备中。当前显示英语简介。
Plan structured adversarial tests for AI applications to assess safety bypasses, data leaks, and unauthorized tool use. Organize test prompts, record findings, and prioritize fixes using reporting guidance and an adaptable testing template.
中文简介正在准备中。当前显示英语简介。
Convert human-written CLAUDE.md instructions into a structured label format for AI agents. Use it to review lengthy rules, reduce instruction overhead, and prepare prompts for migration between AI tools while preserving the intended rules.
中文简介正在准备中。当前显示英语简介。
Retrieve structured JSON from public X/Twitter post links through the third-party ADHX API. Use available text, author details, engagement counts, and long-form article content to summarize posts, extract key points, or examine audience responses.
中文简介正在准备中。当前显示英语简介。
Explore a web application as a user to find reproducible bugs and usability problems. Produce a structured report with reproduction steps, screenshots, and videos for interactive issues, giving responsible teams concrete evidence to investigate.
中文简介正在准备中。当前显示英语简介。
Implement Python error handling with early input checks, appropriate exception types, and clear messages. Handle individual failures in batch jobs, preserve error context for debugging, and use Pydantic models to validate structured input.
中文简介正在准备中。当前显示英语简介。
Prepare GRPO reinforcement learning configurations for tasks with programmatically checkable answers, such as math, code, and structured output. Design and inspect reward functions, then select training variants when runs show instability or exploit flaws in scoring.
中文简介正在准备中。当前显示英语简介。