菜单
List recent content drafts. Wraps `postall-agent list`. Activates when the user wish is read-only — "what drafts do I have", "show me unpublished posts", "any pending content".
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 | list-drafts |
| description | List recent content drafts. Wraps `postall-agent list`. Activates when the user wish is read-only — "what drafts do I have", "show me unpublished posts", "any pending content". |
Read-only inspection of the draft store.
status (optional) — filter by draft / published / partial. Default: all.postall-agent list [--status <STATUS>]
Parse the JSON. The response contains an array of drafts, each with id, topic, platforms, status, created_at.
Format a human-readable summary. Group by status if no filter was applied:
Found <N> drafts.
📝 Unpublished (3):
- abc123 | "Apple WWDC AI demo" | twitter, linkedin | created 2h ago
- def456 | "LangChain alternatives" | twitter | created 1d ago
✅ Published (12):
- ghi789 | "MacBook M5 review" | twitter, linkedin, wechat | published 3d ago
...
If the list is empty, say so plainly: "No drafts found."
If the JSON has success: false, surface the error verbatim.
Read-only. Doesn't produce a draft_id for downstream chaining (the user can issue a follow-up wish like "publish abc123" to chain manually).
Same as other postall skills — postall-agent must be installed.
Generate draft text for one or more social platforms from a topic or URL. Wraps `postall-agent generate`. Activates when the user wish includes a content topic plus a publishing intent ("write a tweet about X", "draft a LinkedIn post on Y", "summarize this URL into a wechat article").
Create a cover image for an existing draft. Wraps `postall-agent image`. Activates when the user wish references a draft and asks for "a cover image", "add a picture", or comes right after a generate-content step in a publishing pipeline.
Publish an existing draft to one or more platform accounts. Wraps `postall-agent publish`. Activates when the user wish says "publish", "send it out", "post to LinkedIn", or comes at the end of a publishing pipeline.
Echo the user's input back verbatim. Useful for greetings, smoke tests, or any wish that's purely conversational and doesn't need data fetching or analysis. Activates when the user says "echo X", "hi", "hello", or similar.
Fetch a URL and produce a concise one-paragraph summary. Activates when the user wish contains a URL or asks to "summarize", "read", "fetch", or "tell me what this page says about" a webpage.