openclaw 网盘下载
OpenClaw

技能详情(站内镜像,无评论)

首页 > 技能库 > Agentify

Analyze, rewrite, and generate design specs to make web pages and websites more easily usable by AI agents, web scrapers, and automation tools. Use when (1)...

开发与 DevOps

作者:ChartGen AI @ chartgen-ai

许可证:MIT-0

MIT-0 ·免费使用、修改和重新分发。无需归因。

版本:v1.0.1

统计:⭐ 1 · 55 · 1 current installs · 1 all-time installs

1

安装量(当前) 1

🛡 VirusTotal :良性 · OpenClaw :良性

Package:chartgen-ai/agentify

安全扫描(ClawHub)

  • VirusTotal :良性
  • OpenClaw :良性

OpenClaw 评估

The skill's requested actions and resources are coherent with its stated purpose (analyzing and rewriting web pages for agent-friendliness); it is instruction-only, requests no credentials, and has no install steps.

目的

Name/description match the runtime instructions: the skill analyzes HTML/code, rewrites templates to add semantic markup/ARIA/data-testid/JSON-LD, and generates design specs. No unrelated binaries, credentials, or installs are requested.

说明范围

SKILL.md explicitly instructs the agent to fetch URLs, read files by path/glob, scan a code directory (package.json, components), and read representative source files. Those actions are expected for this capability, but they do give the agent access to local files and external URLs when invoked — keep that in mind before granting access or invoking autonomously.

安装机制

No install spec or code files; this is instruction-only so nothing is written to disk by an installer. Lowest-risk install posture.

证书

The skill declares no environment variables, credentials, or config paths. The instructions reference reading project files and fetching HTTP(S) content, which are proportional to an analyzer/rewriter skill.

持久

always is false and autonomous invocation is the platform default. The skill does not request persistent system privileges or modify other skills; no elevated persistence observed.

综合结论

This skill appears coherent and low-risk: it only contains instructions and reference docs and asks for no credentials or installs. Before using: (1) only run it against URLs and local directories you control or have permission to scan, since it will fetch URLs and read files/globs; (2) avoid granting it access to directories containing secrets (keys, .env, system config); (3) review any suggested code changes before applying them (the SKILL.m…

安装(复制给龙虾 AI)

将下方整段复制到龙虾中文库对话中,由龙虾按 SKILL.md 完成安装。

请把本段交给龙虾中文库(龙虾 AI)执行:为本机安装 OpenClaw 技能「Agentify」。简介:Analyze, rewrite, and generate design specs to make web pages and websites more…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装:https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/chartgen-ai/agentify/SKILL.md
(来源:yingzhi8.cn 技能库)

SKILL.md

打开原始 SKILL.md(GitHub raw)

---
name: agentify
description: Analyze, rewrite, and generate design specs to make web pages and websites more easily usable by AI agents, web scrapers, and automation tools. Use when (1) evaluating how agent-friendly, accessible (a11y), or machine-readable a web page or HTML/JSX/Vue/Svelte code is, (2) rewriting web templates to add semantic markup, ARIA, structured data (schema.org / JSON-LD), and stable selectors (data-testid) for tools like Playwright, Puppeteer, Cypress, or Selenium, (3) generating agent-friendly design specification documents for development teams covering SEO, accessibility, and GEO (Generative Engine Optimization). Triggers on phrases like "agent-friendly", "make this page work with agents", "analyze for automation", "agentify", "improve SEO", "add structured data", "add data-testid", "web scraping friendly", "machine-readable", "a11y audit", "crawler-friendly".
---

# Agentify

Make web pages and websites more easily navigable, parseable, and operable by AI agents, web scrapers, and automation tools.

## Core Capabilities

### 1. Analyze

Evaluate web pages or code for agent-friendliness. Produce a scored report (0-100) with actionable improvements.

**When to use:** The user wants to audit a page, URL, or codebase for agent accessibility.

**Workflow:**

1. Acquire the content:
   - URL → fetch and retrieve HTML
   - File path → read the file
   - Glob pattern → find matching files, analyze each
   - IDE selection → analyze selected code
2. Read the scoring reference: [references/scoring.md](references/scoring.md)
3. Read the full checklist: [references/checklist.md](references/checklist.md)
4. Evaluate across 9 categories (100 points total):

| # | Category | Pts | Focus |
|---|----------|-----|-------|
| 1 | Semantic HTML | 15 | Heading hierarchy, landmarks, semantic tags vs div soup |
| 2 | ARIA & Accessibility | 15 | Roles, labels, live regions, keyboard attributes |
| 3 | Structured Data | 15 | JSON-LD / schema.org presence, completeness |
| 4 | Form Readability | 10 | Label association, autocomplete, fieldset grouping |
| 5 | Navigation Clarity | 10 | Consistent nav, breadcrumbs, skip links, sitemap |
| 6 | Automation Attributes | 10 | data-testid coverage, data-* for key elements |
| 7 | CSS Selector Stability | 5 | Meaningful class names vs generated hashes |
| 8 | API Discoverability | 10 | Canonical URLs, link relations, OpenAPI |
| 9 | Meta & Machine Signals | 10 | robots meta, description, OG tags, sitemap |

5. Output report in this format:
   - Score: X/100 (Grade A-F)
   - Per-category score breakdown table
   - Top 5 priority improvements with before/after code
   - Detailed findings per category
   - Quick wins section (changes under 5 minutes, 5+ point gain)

### 2. Rewrite

Transform web templates to be agent-friendly while preserving all existing functionality.

**When to use:** The user wants to improve existing code for agent consumption.

**Workflow:**

1. Detect framework from file extension (.html, .jsx, .tsx, .vue, .svelte)
2. Read the patterns reference: [references/patterns.md](references/patterns.md)
3. Read framework-specific guidance: [references/frameworks.md](references/frameworks.md)
4. Read and understand the entire file before modifying
5. Apply transformations in order:
   - Replace non-semantic elements with semantic equivalents (only when intent is unambiguous)
   - Add ARIA attributes to interactive elements
   - Add `data-testid` to buttons, links, inputs, content containers (kebab-case naming)
   - Improve form labels, autocomplete, fieldset grouping
   - Insert JSON-LD structured data where content type is identifiable
   - Add meta tags for full HTML pages
   - Add skip links and nav labels
   - Fix heading hierarchy

**Safety rules (non-negotiable):**
- Never remove existing code, event handlers, or component logic
- Never change class names, IDs, or visual appearance
- Never break framework-specific syntax
- Only add attributes, never replace unless strictly better
- Match existing formatting style

6. After modification, summarize: number of changes per category, changes considered but skipped, and follow-up suggestions needing human judgment

### 3. Design Spec

Generate a comprehensive agent-friendly design specification document for development teams.

**When to use:** The user wants to establish standards for agent-friendly web development.

**Workflow:**

1. Parse arguments for project name and focus area (e-commerce, dashboard, docs, SaaS, marketing)
2. Scan the project if in a code directory:
   - Detect framework (package.json, config files)
   - Detect test framework
   - Grep for existing data-testid, aria-*, schema.org patterns
   - Read 2-3 representative components to understand code style
3. Read the spec template: [references/spec-template.md](references/spec-template.md)
4. Read the example spec: [references/spec-example.md](references/spec-example.md)
5. Generate a markdown spec to `agent-friendly-spec.md` covering:
   - Executive summary
   - Semantic HTML guidelines
   - ARIA & accessibility patterns
   - Naming conventions (data-testid, CSS classes, components)
   - Structured data (JSON-LD) per page type
   - Form design patterns
   - Navigation patterns
   - API & discoverability
   - Meta tags & machine signals
   - Component-level checklists
   - Testing for agent-friendliness
   - Migration guide (quick wins → medium → large effort)

Each section must include: priority level (P0/P1/P2), code examples for the detected framework, anti-patterns, and verification methods.

## Shared Knowledge Base

For the canonical reference on all agent-friendly web patterns (semantic HTML, ARIA, structured data, data attributes, forms, navigation, APIs, meta tags, CSS stability, interaction patterns), read: [references/knowledge-base.md](references/knowledge-base.md)