菜单
Internal linking strategy and anchor text optimization patterns. Use when planning internal links or optimizing site structure.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | link-strategy |
| description | Internal linking strategy and anchor text optimization patterns. Use when planning internal links or optimizing site structure. |
PILLAR PAGE: "Content Marketing" (broad, high volume)
|
+-- Supporting Article: "Content Marketing Strategy"
| (links to and from pillar)
|
+-- Supporting Article: "Content Marketing Examples"
| (links to and from pillar)
|
+-- Supporting Article: "Content Marketing Tools"
(links to and from pillar)
Benefits:
| Type | Example | When to Use |
|---|---|---|
| Exact Match | "SEO tools" | Sparingly (1-2x per page) |
| Partial Match | "best SEO tools for startups" | Primary usage |
| Branded | "SEMrush" | Brand mentions |
| Generic | "click here" | Avoid if possible |
| Naked URL | "https://example.com" | Occasional |
Inventory existing links
Identify orphan pages
Find broken links
Optimize anchor text
Build topic clusters
## Internal Linking Plan
### Target Page: {url}
**Target Keyword**: {keyword}
### Linking Opportunities
1. **From**: {source_page}
- **Anchor**: {anchor_text}
- **Context**: {surrounding_sentence}
- **Priority**: HIGH/MEDIUM/LOW
2. **From**: {source_page}
- **Anchor**: {anchor_text}
- **Context**: {surrounding_sentence}
- **Priority**: HIGH/MEDIUM/LOW
### Topic Cluster Structure
PILLAR: {main_topic_page}
- Supporting: {page1}
- Supporting: {page2}
- Supporting: {page3}
CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.
Multi-agent code analysis orchestration using claudemem. Share claudemem output across parallel agents. Enables parallel investigation, consensus analysis, and role-based command mapping.
⚡ AUTO-INVOKE when user asks: 'audit', 'investigate', 'how does X work', 'find all', 'where is', 'trace', 'understand', 'map the codebase', 'comprehensive'. MUST run BEFORE Read/Glob when planning to read 3+ files. Prevents tool familiarity bias toward native tools.
Integration guide for using detective skills across plugins. Maps agent roles from frontend, bun, and other plugins to appropriate detective skills. Developer agents should use developer-detective, architect agents should use architect-detective, etc.
⚡ PRIMARY TOOL for: 'why is X broken', 'find bug source', 'root cause analysis', 'trace error', 'debug issue', 'find where X fails'. Uses claudemem v0.3.0 AST with context command for call chain analysis. GREP/FIND/GLOB ARE FORBIDDEN.
⛔ INTERCEPT TRIGGER: Automatically invoked BEFORE Read 3+ files OR Glob with broad patterns. Validates whether bulk file operations should be replaced with semantic search. Prevents token waste from sequential file reads.