Agent Skills
› opensquilla/opensquilla
› meta-content-publish-pipeline
meta-content-publish-pipeline
GitHub用于将想法、研究或文档转化为博客、社交媒体、小红书等多平台可发布内容的元技能。通过多技能编排,实现从单一素材到多渠道出版草稿的自动化生成。
Trigger Scenarios
用户希望将笔记或想法发布为博客或社交媒体内容
用户需要将文档转化为视频脚本或Newsletter
涉及多平台内容分发和格式转换的请求
Install
npx skills add opensquilla/opensquilla --skill meta-content-publish-pipeline -g -y
SKILL.md
Frontmatter
{
"kind": "meta",
"name": "meta-content-publish-pipeline",
"always": false,
"metadata": {
"opensquilla": {
"risk": "medium",
"capabilities": [
"network",
"filesystem-write"
]
}
},
"triggers": [
"content pipeline",
"发布成内容",
"小红书文案",
"知乎文章",
"博客改写",
"短视频脚本",
"一稿多发"
],
"provenance": {
"origin": "opensquilla-original",
"license": "Apache-2.0"
},
"composition": {
"steps": [
{
"id": "intake",
"kind": "llm_chat",
"with": {
"task": "Parse the publishing contract.\n\nRequest:\n{{ inputs.user_message | xml_escape | truncate(5000) }}\n\nReturn exactly:\nSOURCE_TYPE: <idea|notes|research|transcript|document|mixed>\nCHANNELS:\n - <blog|newsletter|xiaohongshu|zhihu|slides|short_video|other>\nAUDIENCE: <audience or unknown>\nTONE: <practical|personal|expert|sales|story>\nNEEDS_RESEARCH: <yes|no>\nNEEDS_CLARIFICATION: <yes|no>\nMISSING_FIELDS:\n - <source_material|channels|none>\n",
"system": "You parse content publishing requests and identify channels and source material."
}
},
{
"id": "clarify",
"kind": "user_input",
"when": "'NEEDS_CLARIFICATION: yes' in outputs.intake",
"clarify": {
"mode": "form",
"intro": "内容流水线需要素材和发布渠道。",
"fields": [
{
"name": "source_material",
"type": "string",
"prompt": "素材 \/ Source material",
"required": true,
"max_chars": 3000
},
{
"name": "channels",
"type": "string",
"prompt": "发布渠道 \/ Channels",
"required": true,
"max_chars": 200
}
],
"nl_extract": true,
"timeout_hours": 24,
"cancel_keywords": [
"取消",
"算了",
"cancel",
"stop"
]
},
"depends_on": [
"intake"
]
},
{
"id": "research",
"kind": "skill_exec",
"when": "'NEEDS_RESEARCH: yes' in outputs.intake",
"with": {
"query": "{{ outputs.intake | truncate(260) }}",
"engines": [
"duckduckgo",
"brave"
],
"max_results": 12
},
"skill": "multi-search-engine",
"depends_on": [
"intake",
"clarify"
]
},
{
"id": "source_digest",
"kind": "skill_exec",
"with": {
"text": "Request:\n{{ inputs.user_message | xml_escape | truncate(7000) }}\n\nResearch:\n{{ outputs.research | truncate(5000) }}",
"style": "content_source_digest",
"max_words": 1800
},
"skill": "summarize",
"depends_on": [
"intake",
"clarify",
"research"
]
},
{
"id": "channel_strategy",
"kind": "llm_chat",
"with": {
"task": "Build channel strategy:\n- core thesis\n- proof\/examples\n- per-channel angle\n- title hooks\n- visual suggestions\n- compliance\/risk notes\n\nIntake:\n{{ outputs.intake | truncate(1200) }}\nDigest:\n{{ outputs.source_digest | truncate(5000) }}",
"system": "You adapt one source idea into channel-specific content plans without clickbait."
},
"depends_on": [
"source_digest"
]
},
{
"id": "publish_pack",
"kind": "llm_chat",
"with": {
"task": "Return:\n- master brief\n- channel-specific drafts\n- short-video script if relevant\n- image\/slide prompts if relevant\n- source\/citation notes\n- posting checklist\n- what needs human approval\n\nStrategy:\n{{ outputs.channel_strategy | truncate(7000) }}",
"system": "You write publication-ready content packs."
},
"depends_on": [
"channel_strategy"
]
}
]
},
"description": "Use this meta-skill instead of answering directly when the user wants to turn an idea, research, notes, talk, or document into publishable blog, social, Xiaohongshu, Zhihu, slide, newsletter, or short-video content through multi-skill orchestration.",
"meta_priority": 57,
"final_text_mode": "step:publish_pack"
}
Content Publish Pipeline
Transforms one idea or source packet into multi-channel publishing drafts.
Version History
- 7f72a32 Current 2026-07-05 18:40


