一键导入
content-inventory
Auto-injects current article and glossary inventory for content creation and linking tasks. Reads paths from plugin config.
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。
菜单
Auto-injects current article and glossary inventory for content creation and linking tasks. Reads paths from plugin config.
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。
Create content of any configured type from a topic or from the content backlog. Orchestrates research, writing, style review, glossary creation, linking, and reindexing as focused sub-agents. Hooks handle tracker updates and build verification automatically.
content-seo setup wizard. Run /init to see status, or /init [round] to run a setup step. Rounds: project, credentials, strategy.
Site-level SEO intelligence. Routes to one of five workflows — status (site-wide GSC performance), opportunities (pages ranking 4–20), diagnose (deep-dive a page with GSC data + fixes), brief (keyword research before writing), or coverage (audit GSC indexing errors from a CSV export).
content-ops setup wizard. Run /init to see status, or /init [round] to run a setup step. Rounds: project, content-types, style, strategy, infra, images, link-building.
Identify content gaps and add suggestions to the backlog. Accepts an optional freeform payload to narrow scope. Without a payload, surveys the full corpus against pillars. Powered by the backlog-suggester agent.
Loads and applies the project's configured style guide. Hard stops if config or any required piece is missing. All style rules come from the guidelines file set during /init style.
基于 SOC 职业分类
| name | content-inventory |
| description | Auto-injects current article and glossary inventory for content creation and linking tasks. Reads paths from plugin config. |
| user-invocable | false |
| disable-model-invocation | false |
This skill auto-injects the current state of project content. Use this to know what articles and glossary entries already exist before creating or linking content.
Read these values from .content-ops/config.md:
content_types (each type's path), languages, default_languageFor rich metadata (titles, tags, excerpts, relationships), read .content-ops/content-index.json instead of scanning individual files. The index contains per-language entries for articles and glossary with slug, title/term, excerpt/definition, tags, relatedGlossary, relatedArticles, relatedTerms. Use this when you need more than just filenames — e.g., for linking, tag vocabulary, or understanding content overlap.
For each content type and language from config, list existing content:
For each language in languages, list files at {content_types.article.path}/{lang}/:
!ls {content_types.article.path}/{lang}/ 2>/dev/null | sed 's/\.md$//' | sort
(Run the above command for each configured language.)
For each language in languages, list files at {content_types.glossary.path}/{lang}/:
!ls {content_types.glossary.path}/{lang}/ 2>/dev/null | sed 's/\.md$//' | sort
(Run the above command for each configured language.)
Scan default language content for existing tag vocabulary:
!grep -h '^tags:' {content_types.article.path}/{default_language}/*.md {content_types.glossary.path}/{default_language}/*.md 2>/dev/null | sed 's/tags: \[//;s/\]//;s/"//g' | tr ',' '\n' | sed 's/^ *//;s/ *$//' | sort -u
en/<slug>, en/<term-slug>