smart-blog-skills

研究協調者（Orchestrator）。管理 research cache，派遣 3 個平行研究 sub-agent （stats-researcher、image-researcher、competitor-researcher），合併研究結果。 自己不做搜尋，只做：topic 預審 → cache 判斷 → 派遣 → 品質評估 → 儲存。

Quality assessment specialist for blog posts. Runs the full 5-category, 100-point scoring system, identifies issues by severity, checks for AI content detection signals, validates source tier quality, and flags known AI-detectable phrases. Invoked for quality review tasks during blog workflows.

SEO optimization specialist for blog posts. Validates on-page SEO elements post-writing: title tag, meta description, heading hierarchy, internal/external links, canonical URL, OG meta tags, Twitter Card, URL structure. Produces a pass/fail checklist with specific fixes.

Specialized translation and localization agent for blog content. Produces native-quality translations of an entire blog post, optimized for both human readers and search engines, with format preservation (markdown, MDX, HTML, frontmatter, schema JSON-LD, SVG charts) and locale-correct number, date, currency, and quote formatting. Invoke from `translate` and `multilingual` orchestrators when a single source-to-target language translation is needed. One agent invocation handles one target language.

寫作專家。根據研究結果和模板寫出優質文章，遵循 content-rules.md 寫作規則， 寫完後自我檢查。包含 Answer-First 格式、反 AI 偵測、資料驗證標註。

Smart Blog 品質分析。5 大類 100 分評分，包含 Humanizer 29 模式 AI 偵測、 SEO 驗證、E-E-A-T 評估、PageSpeed 整合。支援 PDF 報告輸出。 Use when user says "analyze blog", "分析文章", "blog audit", "品質評分", "smart-blog analyze", "blog analyze".

Generate audio narration of blog posts using Google Gemini TTS. Supports summary narration, full article read-aloud, and two-speaker podcast/dialogue mode with 30 voice options. Outputs MP3 with HTML5 audio embed code. Works standalone via /smart-blog-skills:audio or internally from write. Falls back gracefully when API key is not configured. Use when user says "blog audio", "narrate blog", "audio version", "text to speech", "tts", "podcast mode", "read aloud", "audio narration", "voice", "narration", "generate audio".

Full-site blog health assessment scanning all blog files for quality scores, orphan pages, topic cannibalization, stale content, and AI citation readiness. Spawns parallel subagents for comprehensive analysis. Produces per-post scores and a prioritized action queue. Use when user says "audit blog", "blog audit", "site audit", "blog health", "audit all posts", "check all blogs".

Blog backlink profile analysis. Analyzes referring domains, anchor text distribution, toxic link detection, and competitor link gap. Uses free search operators and web-accessible tools. Use when user says "backlinks", "link profile", "referring domains", "anchor text", "toxic links", "link gap", "link building", "disavow", "backlink audit", or "who links to my blog".

Smart Blog 防幻覺部落格引擎。34 個子技能：寫、分析、改寫、大綱、摘要簡報、 編輯行事曆、關鍵字重疊偵測、圖表、事實查核、FLOW 框架、AI 引用優化、圖片生成、 多語言稽核、文化本地化、人設語氣、跨平台二創、Schema 標記、SEO 驗證、 分類標籤、翻譯、音訊旁白、NotebookLM、策略規劃、主題群組、多語言一鍵發布、 全站稽核、效能檢測、品質監控、llms.txt 生成、品牌提及掃描、SEO 漂移監控、 AI 爬蟲分析、受眾研究、反向連結分析。雙重優化 Google 排名（E-E-A-T）和 AI 引用平台 （ChatGPT、Perplexity、AI Overview）。繁體中文優先。 Use when user says "blog", "write blog", "smart-blog", "smart blog", "寫文章", "部落格", "blog post", "分析文章", "改寫", "大綱", "內容簡報", "blog outline", "analyze blog", "rewrite blog", "blog strategy", "blog brief".

1 hook across 1 event