{"slug":"atian-create-lingzao-skill-8abed8","title":"\u7075\u9020\u81ea\u5a92\u4f53\u5185\u5bb9\u5de5\u4f5c\u6d41","description":"\u7075\u9020\u4e3b\u6280\u80fd\uff1a\u901a\u8fc7CLI\u67e5\u8be2\u5c0f\u7ea2\u4e66/\u6296\u97f3/\u516c\u4f17\u53f7\u516c\u5f00\u5185\u5bb9\uff08\u7b14\u8bb0\u641c\u7d22\u3001\u8d26\u53f7\u4e3b\u9875\u3001\u7b14\u8bb0\u8be6\u60c5\u3001\u8bc4\u8bba\u3001\u6587\u7ae0\u6570\u636e\u3001\u77ed\u89c6\u9891\u6587\u6848\uff09\uff0c\u5e76\u914d\u5408playbooks\u5b8c\u6210\u5b9a\u4f4d\u3001\u9009\u9898\u3001\u6807\u9898\u5c01\u9762\u3001\u53d1\u5e03\u524d\u68c0\u67e5\u4e0e\u53d1\u5e03\u540e\u590d\u76d8\u3002\u514d\u8d39\u5b89\u88c5\uff0c\u516c\u5f00\u5185\u5bb9\u67e5\u8be2\u4e0e\u56fe\u7247\u751f\u6210\u9700\u5728\u7075\u9020\u7f51\u9875\u7248\u5145\u503c\u5e76\u914d\u7f6eAPI Key\u3002","category":"\u7d20\u6750\u4e0e\u6548\u7387","tags":["atian-create","\u7d20\u6750\u4e0e\u6548\u7387"],"author":"atian-create","source_url":"https://github.com/atian-create/lingzao-skill/blob/1727b3a1acf83aa6754d08f0e3552be8550c5cb9/SKILL.md","license":"MIT","status":"published","verification":"source_reviewed","verification_notes":"\u5df2\u6838\u5bf9\u539f\u59cb\u4ed3\u5e93\u3001\u56fa\u5b9a\u63d0\u4ea4\u3001\u8bb8\u53ef\u3001\u6280\u80fd\u6b63\u6587\u4e0e\u5305\u7ed3\u6784\uff0c\u5e76\u8865\u5145\u4e2d\u6587\u6267\u884c\u9a8c\u6536\u8bf4\u660e\uff1b\u672a\u8fd0\u884c\u5305\u5185\u811a\u672c\u3002","revision":"de97a24cfa784cf6aa2d2d189575d566","created_at":"2026-11-02T14:47:08+00:00","updated_at":"2026-11-02T14:47:08+00:00","source_repo":"atian-create/lingzao-skill","source_path":"SKILL.md","source_commit":"1727b3a1acf83aa6754d08f0e3552be8550c5cb9","source_updated_at":"2026-11-02T14:46:04+00:00","stars":0,"proxy_score":null,"score":null,"grade":null,"dimensions":{},"evaluation":{},"installs":0,"platforms":[],"formats":[],"category_slug":"workflow","category_name":"\u7d20\u6750\u4e0e\u6548\u7387","quality":{"review_type":"text_and_package_review","readiness":"requires_setup","reviewed_at":"2026-11-02T14:46:04+00:00","review_summary":"\u4e3b\u6280\u80fd\u8def\u7531\u6e05\u6670\u3001\u547d\u4ee4\u4e0e\u53c2\u6570\u7ea6\u675f\u5177\u4f53\uff0c\u4ed8\u8d39\u4e0e\u77e5\u8bc6\u5e93\u540c\u6b65\u6709\u660e\u786e\u8fb9\u754c\uff1b\u4f46\u6838\u5fc3\u80fd\u529b\u4f9d\u8d56\u7075\u9020\u4ed8\u8d39\u670d\u52a1\u4e0eAPI Key\uff0c\u672a\u914d\u7f6e\u65f6\u4ec5\u5269\u672c\u5730playbook\uff0c\u9700\u7528\u6237\u81ea\u5907\u8d26\u53f7\u540e\u4f7f\u7528\u3002","cost_notes":"\u516c\u5f00\u5185\u5bb9\u67e5\u8be2\u3001\u6df1\u5ea6\u8d26\u53f7\u5206\u6790\u4e0e\u56fe\u7247\u751f\u6210\u6309\u79ef\u5206\u8ba1\u8d39\uff0cSKILL\u8981\u6c42\u4ed8\u8d39\u67e5\u8be2\u524d\u8bf4\u660e\u57fa\u7840/\u6df1\u5ea6\u8303\u56f4\u5e76\u907f\u514d\u9759\u9ed8\u6269\u5927\u7528\u91cf\uff1b\u5177\u4f53\u5355\u4ef7\u4e0e\u5145\u503c\u65b9\u5f0f\u4ee5\u7075\u9020\u7f51\u9875\u7248\u4e3a\u51c6\uff0c\u5305\u5185\u672a\u62a5\u4ef7\u3002","source_sha256":"5ed2e412c03c2c3baff3bafd566d0835d04eb6d45ff6f55b31309b164c517f46","prerequisites":["Python 3\uff08scripts/setup.sh\u3001lingzao_client.py\uff09","\u7075\u9020\u7f51\u9875\u7248\u8d26\u53f7\u3001\u79ef\u5206\u4e0eAPI Key\uff08LINGZAO_API_KEY\uff09","\u53ef\u8bbf\u95ee\u7075\u9020\u670d\u52a1\u57df\u540d\u7684\u7f51\u7edc\u73af\u5883","\u77e5\u8bc6\u5e93\u540c\u6b65\u9700\u7528\u6237\u5df2\u914d\u7f6eima/Obsidian/\u98de\u4e66\u5bf9\u5e94\u5de5\u5177\u4e0e\u6388\u6743"],"checks":["\u8c03\u7528search-notes\u524d\u5df2\u786e\u8ba4\u6392\u5e8f\u3001\u7b14\u8bb0\u7c7b\u578b\u3001\u65f6\u95f4\u8303\u56f4\uff0c\u6296\u97f3\u672a\u4f20\u4e0d\u652f\u6301\u7684\u6392\u5e8f\u6216\u76f4\u64ad\u7b14\u8bb0\u7c7b\u578b","\u4ece\u5217\u8868\u8fdb\u5165get-note-detail\u65f6\u590d\u7528\u8fd4\u56de\u7684xhs_note_type\uff0c\u7f3a\u5931\u65f6\u5148\u8be2\u95ee\u56fe\u6587/\u89c6\u9891","analyze-user-profile\u540e\u68c0\u67e5data.artifacts.subtitle_markdown.status\u4e0eurl\uff0cready\u65f6\u4e0b\u8f7dMarkdown\u518d\u5206\u6790","generate-image\u524d\u5b8c\u6210\u6700\u5c0fintake\uff08\u53c2\u8003\u56fe\u4e0e\u914d\u8272\uff09\uff0c\u8f93\u51fa\u6587\u4ef6\u6309--output\u6216\u7f16\u53f7\u4fdd\u5b58","\u77e5\u8bc6\u5e93\u540c\u6b65\u524d\u5148\u8be2\u95ee\u76ee\u6807\uff0c\u4e14\u540c\u6b65\u5185\u5bb9\u4e0d\u542bAPI Key\u3001\u7b7e\u540dURL\u6216\u5185\u90e8\u9519\u8bef\u7ec6\u8282"],"limitations":["\u6240\u6709\u67e5\u8be2\u4f9d\u8d56\u7075\u9020\u670d\u52a1\u7aef\u4e0e\u79ef\u5206\uff0c\u672a\u914d\u7f6eAPI Key\u65f6\u53ea\u80fd\u4f7f\u7528\u672c\u5730playbooks","\u6296\u97f3\u8bc4\u8bba\u4ec5\u652f\u6301latest\u6392\u5e8f\uff0c\u6296\u97f3\u4e3b\u9875\u4e0d\u63d0\u53d6\u5b57\u5e55\u9700\u9010\u6761extract-video-copy","\u516c\u4f17\u53f7\u6587\u7ae0\u547d\u4ee4\u4ec5\u652f\u6301\u5355URL\uff0c\u4e0d\u652f\u6301\u8d26\u53f7\u5386\u53f2\u6587\u7ae0\u5217\u8868","\u5305\u5185\u811a\u672c\u672a\u5728\u672c\u5ba1\u9605\u4e2d\u8fd0\u884c\uff0cCLI\u5b9e\u9645\u884c\u4e3a\u9700\u7528\u6237\u73af\u5883\u9a8c\u8bc1"],"issues":["SKILL.md\u4e2d\u5b89\u88c5\u4e0e\u66f4\u65b0\u5730\u5740\uff08assets-tian.midao.site\u3001lingzao.atian.vip\uff09\u4e3a\u5916\u90e8\u670d\u52a1\uff0c\u53ef\u7528\u6027\u672a\u6838\u5b9e","playbooks\u76ee\u5f55\u4e0b\u5927\u91cf\u6587\u4ef6\u672a\u9010\u4e00\u5ba1\u9605\uff0c\u5185\u5bb9\u8d28\u91cf\u4e0e\u4e00\u81f4\u6027\u5f85\u6838\u5b9e","SKILL.md\u7bc7\u5e45\u957f\u4e14\u542b\u8425\u9500\u8bdd\u672f\uff08\u5982\u65f6\u95f4\u8282\u7701\u63d0\u793a\uff09\uff0c\u9700\u6ce8\u610f\u4e0d\u5c06\u5176\u5f53\u4f5c\u6548\u679c\u627f\u8bfa"],"missing_files":[]},"quality_url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/SHILIU-QUALITY.md","usage_guide":{"task":"\u7528\u7075\u9020CLI\u505a\u516c\u5f00\u5185\u5bb9\u8c03\u7814\u4e0e\u81ea\u5a92\u4f53\u8fd0\u8425\u5de5\u4f5c\u6d41\uff1a\u627e\u5bf9\u6807\u8d26\u53f7\u3001\u62c6\u89e3\u7206\u6b3e\u7b14\u8bb0\u3001\u505a\u5173\u952e\u8bcd\u6d1e\u5bdf\u3001\u751f\u6210\u5185\u5bb9\u5305\u3001\u53d1\u5e03\u524d\u540e\u68c0\u67e5\u4e0e\u6570\u636e\u590d\u76d8\u3002","inputs":"\u5df2\u5b89\u88c5\u7684\u7075\u9020Skill\u4e0escripts/setup.sh\u914d\u7f6e\uff08base-url\u4e0eAPI Key\uff09\uff1b\u7528\u6237\u63d0\u4f9b\u7684\u5e73\u53f0\u94fe\u63a5\u6216\u5173\u952e\u8bcd\uff1b\u67e5\u8be2\u53c2\u6570\uff08\u6392\u5e8f\u3001\u7b14\u8bb0\u7c7b\u578b\u3001\u65f6\u95f4\u8303\u56f4\u3001\u8bc4\u8bba\u6392\u5e8f\uff09\uff1b\u9700\u8981\u56fe\u7247\u751f\u6210\u65f6\u7684\u53c2\u8003\u56fe\u4e0e\u914d\u8272\u7ea6\u675f\uff1b\u77e5\u8bc6\u5e93\u540c\u6b65\u76ee\u6807\uff08ima/Obsidian/\u98de\u4e66\uff09\u9700\u7528\u6237\u5df2\u914d\u7f6e\u5bf9\u5e94\u5de5\u5177\u3002","outputs":"CLI Markdown\u7ed3\u679c\uff08\u7b14\u8bb0\u5217\u8868\u3001\u8d26\u53f7\u4e3b\u9875\u3001\u7b14\u8bb0\u8be6\u60c5\u3001\u8bc4\u8bba\u3001\u6587\u7ae0\u6570\u636e\u3001\u77ed\u89c6\u9891\u6587\u6848\uff09\uff1b\u6309playbook\u4ea7\u51fa\u7684\u8bca\u65ad\u62a5\u544a\u3001\u5173\u952e\u8bcd\u62a5\u544a\u3001\u5185\u5bb9\u5305\uff08\u6807\u9898\u3001\u5c01\u9762\u6587\u6848\u30014-7\u9875\u56fe\u6587\u6b63\u6587\u300110\u4e2a\u53d1\u5e03\u5173\u952e\u8bcd\uff09\uff1b\u53ef\u9009\u56fe\u7247\u6587\u4ef6\uff1b\u7ecf\u7528\u6237\u540c\u610f\u540e\u7684\u77e5\u8bc6\u5e93Markdown\u3002","example_input":"\u5e2e\u6211\u627e5\u4e2a\u5c0f\u7ea2\u4e66AI\u5de5\u5177\u8d5b\u9053\u7684\u5bf9\u6807\u8d26\u53f7\uff0c\u7c89\u4e1d5-15\u4e07\u3001\u6700\u8fd130\u5929\u6709\u7206\u6b3e\uff0c\u7ed9\u51fa\u4e3b\u9875\u94fe\u63a5\u548c\u8fd1\u671f\u9ad8\u4e92\u52a8\u7b14\u8bb0\uff0c\u518d\u5bf9\u6bd4\u6211\u81ea\u5df1\u7684\u8d26\u53f7\u5dee\u5728\u54ea\u3002","example_output":"\u793a\u610f\uff1a\u5bf9\u6807\u8d26\u53f7\u8868\uff08\u4e3b\u9875\u94fe\u63a5\u3001\u7c89\u4e1d\u6570\u3001\u603b\u8d5e\u3001\u6700\u8fd1\u66f4\u65b0\u3001\u8fd130\u5929\u7206\u6b3e\u7b14\u8bb0\u53ca\u6307\u6807\u3001\u53ef\u5b66\u70b9\uff09\uff0c\u6309\u7c89\u4e1d\u6570\u4ece\u9ad8\u5230\u4f4e\u6392\u5e8f\uff1b\u968f\u540e\u662f\u81ea\u8d26\u53f7\u4e0e\u540c\u7ea7\u8d26\u53f7\u7684\u6a2a\u5411\u5bf9\u6bd4\u8868\u4e0e30\u5929\u8c03\u6574\u5efa\u8bae\u3002\u4ee5\u4e0a\u4e3a\u7ed3\u6784\u793a\u610f\uff0c\u975e\u5b9e\u9645\u67e5\u8be2\u7ed3\u679c\u3002"},"read_url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8","skill_url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/SKILL.md","download_url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/download","install_url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/install","files":[{"path":"LICENSE","bytes":901,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/LICENSE"},{"path":"README.md","bytes":9237,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/README.md"},{"path":"SHILIU-QUALITY.md","bytes":2529,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/SHILIU-QUALITY.md"},{"path":"SKILL.md","bytes":36622,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/SKILL.md"},{"path":"VERSION","bytes":7,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/VERSION"},{"path":"agents/openai.yaml","bytes":1567,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/agents/openai.yaml"},{"path":"agents/openclaw.yaml","bytes":276,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/agents/openclaw.yaml"},{"path":"playbooks/atian-creator-judgment-framework.md","bytes":10985,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/atian-creator-judgment-framework.md"},{"path":"playbooks/audience-persona-fit-check.md","bytes":5699,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/audience-persona-fit-check.md"},{"path":"playbooks/beginner-account-start-and-topic-radar.md","bytes":25119,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/beginner-account-start-and-topic-radar.md"},{"path":"playbooks/benchmark-account-discovery-quality-gate.md","bytes":17439,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/benchmark-account-discovery-quality-gate.md"},{"path":"playbooks/comparable-account-breakdown-report-template.md","bytes":14318,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/comparable-account-breakdown-report-template.md"},{"path":"playbooks/content-knowledge-base-workflow.md","bytes":27511,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/content-knowledge-base-workflow.md"},{"path":"playbooks/creator-case-general-analysis-framework.md","bytes":14263,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/creator-case-general-analysis-framework.md"},{"path":"playbooks/draft-rewrite-and-benchmark-workflow.md","bytes":8762,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/draft-rewrite-and-benchmark-workflow.md"},{"path":"playbooks/image-generation-agent-integration-guide.md","bytes":20290,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/image-generation-agent-integration-guide.md"},{"path":"playbooks/image-generation-execution-workflow.md","bytes":11500,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/image-generation-execution-workflow.md"},{"path":"playbooks/keyword-insight-report-template.md","bytes":11380,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/keyword-insight-report-template.md"},{"path":"playbooks/keyword-to-publishable-content-package.md","bytes":36186,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/keyword-to-publishable-content-package.md"},{"path":"playbooks/lingzao-progressive-interaction-map.md","bytes":42307,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/lingzao-progressive-interaction-map.md"},{"path":"playbooks/monetization-path-judgment-library.md","bytes":10874,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/monetization-path-judgment-library.md"},{"path":"playbooks/mother-content-cross-platform-distribution.md","bytes":7279,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/mother-content-cross-platform-distribution.md"},{"path":"playbooks/post-publish-data-review-workflow.md","bytes":12953,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/post-publish-data-review-workflow.md"},{"path":"playbooks/pre-publish-readiness-check.md","bytes":5702,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/pre-publish-readiness-check.md"},{"path":"playbooks/product-judgment-and-feedback-loop.md","bytes":8754,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/product-judgment-and-feedback-loop.md"},{"path":"playbooks/publishing-keyword-design-check.md","bytes":9503,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/publishing-keyword-design-check.md"},{"path":"playbooks/reference-image-graphic-note-workflow.md","bytes":4609,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/reference-image-graphic-note-workflow.md"},{"path":"playbooks/retention-and-follow-up-loop.md","bytes":12840,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/retention-and-follow-up-loop.md"},{"path":"playbooks/search-credit-notice.md","bytes":13737,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/search-credit-notice.md"},{"path":"playbooks/self-account-diagnosis-report-template.md","bytes":25031,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/self-account-diagnosis-report-template.md"},{"path":"playbooks/self-account-peer-horizontal-diagnosis.md","bytes":11865,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/self-account-peer-horizontal-diagnosis.md"},{"path":"playbooks/single-note-breakdown-workflow.md","bytes":20270,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/single-note-breakdown-workflow.md"},{"path":"playbooks/track-difficulty-judgment-library.md","bytes":12236,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/track-difficulty-judgment-library.md"},{"path":"playbooks/visual-generation-and-cover-workflow.md","bytes":10170,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/visual-generation-and-cover-workflow.md"},{"path":"playbooks/visual-reference-style-library.md","bytes":21974,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/visual-reference-style-library.md"},{"path":"playbooks/xhs-operation-task-tree.md","bytes":11160,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/xhs-operation-task-tree.md"},{"path":"playbooks/xhs-profile-bio-design.md","bytes":7960,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/xhs-profile-bio-design.md"},{"path":"playbooks/xhs-title-design-check.md","bytes":7825,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/playbooks/xhs-title-design-check.md"},{"path":"scripts/check_version.py","bytes":275,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/scripts/check_version.py"},{"path":"scripts/configure.py","bytes":3015,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/scripts/configure.py"},{"path":"scripts/lingzao_client.py","bytes":66875,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/scripts/lingzao_client.py"},{"path":"scripts/setup.sh","bytes":1824,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/scripts/setup.sh"},{"path":"shiliu-quality.json","bytes":2200,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/shiliu-quality.json"},{"path":"shiliu-source.json","bytes":255,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/shiliu-source.json"},{"path":"usage.json","bytes":1346,"url":"https://shiliuai.cn/api/v2/skills/atian-create-lingzao-skill-8abed8/files/usage.json"}],"content":"---\nname: lingzao\ndescription: Use Lingzao creator-content tools for Xiaohongshu/XHS, Douyin, and WeChat official-account public content. Lingzao supports XHS SEO, Xiaohongshu account analysis, benchmark account discovery, viral note breakdown, keyword research, one-stop content packages from keyword/link/image/inspiration material, title and cover optimization, hand-drawn route-map cards, city food maps, travel itinerary maps, life checklist maps, workflow manual maps, creator content workflow, note search, creator search, profile lookup, recent posts, deep profile copy/subtitle analysis, note/article detail, post comments, article stats, related articles, short-video copy extraction, and prompt-based creator image generation.\n---\n\n# Lingzao\n\nLingzao helps agents research public creator content from Xiaohongshu / XHS,\nDouyin, and WeChat official-account articles.\n\nSearch phrases this Skill is designed to support: Lingzao Skill, lingzao xhs,\nLingzao Xiaohongshu, XHS SEO, Xiaohongshu SEO, Xiaohongshu account analysis,\nXHS account diagnosis, Xiaohongshu keyword research, XHS title optimization,\nXiaohongshu viral note breakdown, Xiaohongshu benchmark account finder, XHS\ncontent workflow, hand-drawn route map card, \u624b\u7ed8\u6536\u85cf\u5730\u56fe, \u7f8e\u98df\u5730\u56fe, \u65c5\u6e38\u8def\u7ebf\u56fe,\n\u751f\u6d3b\u6e05\u5355\u5730\u56fe, and \u5de5\u4f5c\u6d41\u8bf4\u660e\u4e66\u5730\u56fe.\n\nUse this skill when the user asks to:\n\n- Search Xiaohongshu notes by keyword.\n- Turn a keyword, link, screenshot, reference image, or inspiration material into\n  a Xiaohongshu content package with titles, cover copy, 4-7 page graphic-note\n  text, body copy, 10 keywords, pinned content, and a review loop.\n- Get Xiaohongshu search suggestions or popular recommendations.\n- Search public creators by keyword.\n- Look up a creator profile.\n- Read a creator's recent public posts.\n- Get recent post copy, subtitles, covers, metrics, and commercial signals from a creator profile.\n- Get details for a Xiaohongshu or Douyin post.\n- Get top-level public comments for one Xiaohongshu or Douyin post.\n- Get one WeChat official-account article's public detail and text.\n- Get public metrics for one WeChat official-account article.\n- Get related public WeChat official-account articles.\n- Extract spoken copy or transcript from a public short-video link.\n- Generate creator image assets from a prompt when the user explicitly asks to make an image.\n- Turn a city, food, travel, hiking, life checklist, or workflow topic into a\n  hand-drawn Xiaohongshu route-map card structure and generation brief.\n\nUse the lightweight sub-skills under `skills/` when a user only needs a single\ntask such as XHS title writing, Xiaohongshu account diagnosis, keyword design,\nnote breakdown, cover lab, hand-drawn route-map card, pre-publish check, or\npost-publish review. Use this main Lingzao Skill when the user needs live\npublic-content lookup, deeper\naccount analysis, Xiaohongshu public-link parsing, comment analysis, article\ndata, transcript extraction, image generation, report export, or\nknowledge-base sync.\n\n## Agent Playbooks\n\nFor higher-level creator strategy tasks, use the playbooks in\n`<skill_root>/playbooks/` before answering. They turn Lingzao's public-content\ntools into creator workflows instead of isolated lookups.\n\nUse these playbooks when relevant:\n\n- `lingzao-progressive-interaction-map.md`: route vague user inputs, homepage\n  links, note links, drafts, and reference-image requests with light questions.\n- `search-credit-notice.md`: explain basic vs deep search scope before paid\n  lookups and avoid silently expanding credit usage.\n- `atian-creator-judgment-framework.md`: apply A Tian's account-stage,\n  memory-anchor, content-mainline, and bottleneck judgment.\n- `creator-case-general-analysis-framework.md`: analyze any creator case across\n  tracks by identifying the account archetype, memory anchor, new narrative,\n  proof system, audience desire, content engine, format engine, comment demand,\n  commercial entry, hidden resources, learnable parts, non-copyable parts, and\n  user-fit tests.\n- `beginner-account-start-and-topic-radar.md`: handle zero-to-one creator\n  questions, topic discovery, keyword trees, and low-follower viral references.\n- `keyword-insight-report-template.md`: create scoped keyword insight reports\n  from a main keyword plus confirmed related/dropdown terms, with clear credit\n  estimates before expanding.\n- `keyword-to-publishable-content-package.md`: turn a keyword, vague topic,\n  note link, screenshot, reference image, saved note, or inspiration material\n  into publishable Xiaohongshu content packages with selected references,\n  topic angles, titles, cover copy, 4-7 page graphic-note text, spoken scripts,\n  Vlog storyboards, body copy, 10 publishing keywords, pinned content, and a\n  pre/post-publish review loop.\n- `mother-content-cross-platform-distribution.md`: turn one topic, draft,\n  note breakdown, product update, screenshot, transcript, or oral idea into a\n  one-stop cross-platform distribution package. When users say \"\u4e00\u6761\u9f99\",\n  \"\u5168\u5e73\u53f0\u540c\u6b65\", \"\u5206\u53d1\u5305\", or \"\u4e00\u4e2a\u6a21\u677f\u53d1\u591a\u4e2a\u5e73\u53f0\", start with the basic\n  Xiaohongshu + Moments + WeChat public-account package, then offer optional\n  expansion to podcast, X, Knowledge Planet, Bilibili, video account/Douyin,\n  Xiaohongshu image package, or knowledge-base/SOP.\n- `pre-publish-readiness-check.md`: before posting, ask whether the content is\n  already finished and then check content clarity, image/page readiness, cover\n  recognition, title clickability, first 3 lines or first 3 seconds, and natural\n  keyword embedding.\n- `audience-persona-fit-check.md`: before titles, keywords, account operation,\n  or content-package decisions, infer or ask who the content is for, who will\n  click, who will not click, and which audience/city/life-stage keywords should\n  shape the output.\n- `xhs-title-design-check.md`: design or diagnose Xiaohongshu titles after the\n  user sends a topic, draft, cover copy, reference note, or content package;\n  default to 3 strongest titles with keyword anchor and click reason instead\n  of a 10-title pool.\n- `xhs-profile-bio-design.md`: write or diagnose Xiaohongshu 100-character\n  profile bios and homepage introductions that clarify who the account is for,\n  what it shares, why to follow, and how it connects to nickname, pinned notes,\n  account stage, audience keywords, city keywords, and light commercial paths.\n- `benchmark-account-discovery-quality-gate.md`: find or judge benchmark\n  accounts with a default quality gate: still updating, recent high-performing\n  works, track/audience fit, stage fit, and clear learnable parts; stale\n  accounts should be marked as historical references, not main benchmarks.\n  User-facing results should show direct creator profile links and the specific\n  recent high-interaction works, not raw creator IDs. The first discovery round\n  should return up to 5 strong accounts, not 10-20 accounts; expand only after\n  the user confirms follower range, stage, city, audience, format, or asks for\n  more. Include follower count, total liked count, latest update, recent\n  30-day hit works with note metrics, content format, and why each account is\n  worth learning; sort visible recommendations by follower count from high to\n  low when available.\n- `self-account-peer-horizontal-diagnosis.md`: compare the user's own account\n  with same-track, same-stage, or same-follower-range peer accounts when the\n  user explicitly asks for peer comparison, such as \"\u6a2a\u5411\u5bf9\u6bd4\", \"\u540c\u7ea7\u8d26\u53f7\",\n  \"\u5bf9\u6807\u8d26\u53f7\", \"\u627e 5-15w \u7c89\u8d26\u53f7\u548c\u6211\u6bd4\", or \"\u548c\u540c\u8d5b\u9053\u8d26\u53f7\u6bd4\u6211\u5dee\u5728\u54ea\u91cc\". Generic\n  own-account concerns such as \"\u770b\u770b\u6211\u73b0\u5728\u7684\u95ee\u9898\" or \"\u6211\u662f\u4e0d\u662f\u8bf4\u8bdd\u592a\u5feb\" should\n  stay on `self-account-diagnosis-report-template.md` unless the user also asks\n  to compare against peers. It combines own-account diagnosis, active benchmark\n  selection, peer-account tables, title/cover/opening/speech/content-system\n  comparison, top gaps, 30-day adjustment plans, and a human next-step loop.\n- `single-note-breakdown-workflow.md`: break down one Xiaohongshu/Douyin note\n  link by title, cover, outline/script, shooting/editing layer when visible,\n  comment demand, viral mechanism, learnable parts, non-copyable parts, and\n  adaptation into the user's own graphic note, spoken script, Vlog storyboard,\n  or knowledge-base card. User phrases such as \"\u5b8c\u6574\u5206\u6790\u8fd9\u6761\u7b14\u8bb0\", \"\u6df1\u5ea6\u62c6\u89e3\",\n  \"\u62c6\u7ec6\u4e00\u70b9\", \"\u62cd\u6444\u624b\u6cd5\", \"\u5206\u955c\", or \"\u526a\u8f91\u8282\u594f\" should trigger the deeper\n  breakdown instead of a short summary.\n- `publishing-keyword-design-check.md`: design the final 10 Xiaohongshu\n  publishing keywords for a finished draft and check whether title, cover copy,\n  opening lines, and keyword field carry the keywords naturally.\n- `track-difficulty-judgment-library.md`: judge common tracks such as female\n  growth, career, good products, local life, health, fashion, and AI tools.\n- `monetization-path-judgment-library.md`: answer whether a track or account\n  can monetize through ads, courses, community, consulting, lead generation,\n  products, stores, or enterprise conversion.\n- `self-account-diagnosis-report-template.md`: structure own-account diagnosis\n  reports, follow-up actions, and a human closing with \"\u4eba\u60c5\u5473\" that turns\n  sharp diagnosis into one small next experiment instead of ending at a cold\n  action list. Own-account diagnosis should also include a share-worthy\n  conclusion card, action advice, and psychological reassurance.\n- `comparable-account-breakdown-report-template.md`: decide whether another\n  account is worth learning from, what can be learned, and what cannot be copied.\n- `draft-rewrite-and-benchmark-workflow.md`: rewrite drafts, adapt viral\n  formulas, and review multiple content ideas without only polishing sentences.\n- `reference-image-graphic-note-workflow.md`: turn reference images into\n  Xiaohongshu 4-page or 7-page graphic-note packages.\n- `visual-generation-and-cover-workflow.md`: route Xiaohongshu covers, graphic\n  notes, WeChat image packs, no-person knowledge cards, and product/ecommerce\n  visuals into image generation or ready-to-use prompt packages.\n- `image-generation-execution-workflow.md`: when image generation is available,\n  turn the visual route into actual images, run a visual-director quality gate,\n  and repair ugly/crowded/generic generations instead of leaving ordinary users\n  with raw prompts.\n- `image-generation-agent-integration-guide.md`: model-agnostic rules for\n  domestic Agent wrappers, including stable generation input/output fields,\n  good-vs-bad image standards, reference-image usage, known generation bugs,\n  friendly failure handling, and A Tian's example-collection homework.\n- `visual-reference-style-library.md`: classify A Tian's internal visual\n  reference folders into travel/food covers, WeChat article images, AI-person\n  infographics, Lingzao no-person knowledge cards, product conversion images,\n  face-led keyword video covers, interaction prompt covers, and text-dense\n  screenshot graphic notes, and room-as-identity lifestyle covers.\n- `post-publish-data-review-workflow.md`: review published Xiaohongshu notes\n  from note links, backend screenshots, scripts, covers, and 24h/48h/7d data.\n- `content-knowledge-base-workflow.md`: turn saved notes, public creator links,\n  keyword results, viral examples, and creator distillation requests into\n  user-owned topic, title, cover, structure, account-reference,\n  creator-research, and publishing-review libraries.\n- `retention-and-follow-up-loop.md`: end useful outputs with one concrete next\n  step such as published-note data review, reusable reference-search templates,\n  draft feedback, or a post-diagnosis small experiment with a return loop. It\n  also defines the SOP for not letting the user's words drop on the floor:\n  acknowledge resistance, lower the next action, and ask one concrete\n  next-step question. Dense outputs should offer Word, HTML/webpage preview, or\n  knowledge-base-ready packaging instead of leaving users with a wall of chat\n  text. When users say the diagnosis is accurate but they lack action, route to\n  a post-diagnosis activation package instead of adding more pressure.\n- `product-judgment-and-feedback-loop.md`: judge where users are really stuck,\n  explain Lingzao in human language, build content/sales narratives, turn user\n  feedback into product iteration, and decide which requests are worth building\n  versus noise.\n- `xhs-operation-task-tree.md`: route Lingzao users by concrete Xiaohongshu\n  operation tasks instead of course lists, covering homepage diagnosis,\n  benchmark discovery, viral-note adaptation, topic generation, content\n  production, cover/image work, pre-publish checks, post-publish review,\n  acquisition paths, and knowledge-base automation.\n\nKeep public wording focused on creator-content research and workflow support.\nDo not promise viral growth, guaranteed monetization, full monitoring, raw data\nexport, or copying another creator's content.\n\n## Install And Paid Capability Entry\n\nLingzao is installed as one free main Skill. Users do not need to install\nseparate title, keyword, account-diagnosis, benchmark, cover, or review skills.\nAfter installation, this main Skill routes the user's request to the right\nplaybook.\n\nThere are two user acquisition paths:\n\n1. Community/course users:\n   - They may already have A Tian's course, install link, payment steps, and\n     API Key setup instructions.\n   - Keep the in-chat explanation short: install the Skill, open the Lingzao web\n     dashboard, follow the tutorial, recharge credits, copy the API Key, then\n     run setup.\n\n2. Public-platform users from Xiaohongshu, Douyin, or other public content:\n   - Do not require them to open the web dashboard and pay before they\n     understand what Lingzao can do.\n   - Let them install the free main Skill first.\n   - Then explain the hidden paid entry in friendly language: the local\n     playbooks can help judge drafts, titles, covers, directions, and\n     publishing plans; when they need Lingzao to search public content, inspect\n     accounts, open note/article details, read comments, inspect article data,\n     extract video copy, or generate creator image assets, they need to open\n     the Lingzao web dashboard, follow the tutorial, recharge credits, and\n     configure an API Key.\n\nThe web dashboard is not only a payment page. Present it as the user's learning\nand setup hub:\n\n- learn how to install and configure Lingzao\n- learn how to ask Agent better questions instead of waiting in a group chat\n- learn how to use Skill workflows for self-media operation\n- learn account diagnosis, benchmark breakdown, title/keyword, pre-publish, and\n  post-publish review workflows\n- recharge credits and get the API Key when they need public-content lookup or\n  image generation\n\nUse this wording when a user has installed the Skill but has not configured an\nAPI Key yet:\n\n\u4f60\u5df2\u7ecf\u88c5\u597d\u7075\u9020 Skill \u4e86\u3002\u5b89\u88c5\u672c\u8eab\u662f\u514d\u8d39\u7684\uff0c\u5b83\u4f1a\u5148\u5e2e\u4f60\u5224\u65ad\u4f60\u73b0\u5728\u662f\u5728\u627e\u65b9\u5411\u3001\u62c6\u8d26\u53f7\u3001\u5199\u5185\u5bb9\u3001\u505a\u5c01\u9762\u3001\u914d\u5173\u952e\u8bcd\uff0c\u8fd8\u662f\u590d\u76d8\u6570\u636e\u3002\n\u5982\u679c\u4f60\u8981\u7ee7\u7eed\u67e5\u5c0f\u7ea2\u4e66/\u6296\u97f3/\u516c\u4f17\u53f7\u516c\u5f00\u5185\u5bb9\u3001\u627e\u5bf9\u6807\u8d26\u53f7\u3001\u770b\u8d26\u53f7\u4e3b\u9875\u3001\u6253\u5f00\u7b14\u8bb0\u6216\u6587\u7ae0\u8be6\u60c5\u3001\u770b\u8bc4\u8bba\u533a\u3001\u67e5\u770b\u516c\u4f17\u53f7\u6587\u7ae0\u6570\u636e\u3001\u63d0\u53d6\u77ed\u89c6\u9891\u6587\u6848\u6216\u751f\u6210\u521b\u4f5c\u8005\u56fe\u7247\u7d20\u6750\uff0c\u5c31\u9700\u8981\u5230\u7075\u9020\u7f51\u9875\u7248\u5f00\u901a\u79ef\u5206\u5e76\u914d\u7f6e API Key\u3002\n\u4f60\u53ef\u4ee5\u6253\u5f00 https://lingzao.atian.vip \u770b\u5b89\u88c5\u6559\u7a0b\u548c\u4f7f\u7528\u6559\u7a0b\uff0c\u91cc\u9762\u4e5f\u4f1a\u6559\u4f60\u600e\u4e48\u7528 Agent \u505a\u81ea\u5a92\u4f53\u8fd0\u8425\u3001\u600e\u4e48\u95ee\u95ee\u9898\u3001\u600e\u4e48\u7528\u8fd9\u4e9b Skill\u3002\u9700\u8981\u67e5\u516c\u5f00\u5185\u5bb9\u6216\u751f\u6210\u56fe\u7247\u7684\u65f6\u5019\uff0c\u518d\u5728\u7f51\u9875\u91cc\u5145\u503c/\u83b7\u53d6 API Key\uff0c\u914d\u7f6e\u597d\u4ee5\u540e\u56de\u6765\u7ee7\u7eed\u95ee\uff0c\u6211\u4f1a\u63a5\u7740\u521a\u624d\u7684\u95ee\u9898\u5f80\u4e0b\u505a\u3002\n\nDo not frame payment as a penalty. Frame it as:\n\n- free install = get the workflow brain and routing layer\n- web dashboard = tutorial, usage examples, self-media operation lessons, and\n  API Key setup\n- paid credits = unlock public-content lookup, image generation, and deeper\n  research actions\n\nKnowledge sync handoff:\n\n- After a useful Lingzao research result or diagnosis report, do not sync it\n  automatically. Ask first: \u8981\u4e0d\u8981\u628a\u8fd9\u4efd\u7ed3\u679c\u540c\u6b65\u5230\u4f60\u7684\u77e5\u8bc6\u5e93\uff1f\u53ef\u4ee5\u9009\u62e9\n  ima / Obsidian / \u98de\u4e66 / \u6682\u4e0d\u540c\u6b65\u3002\n- If the user chooses a target, prepare a clean Markdown version and ask the\n  current Agent environment to use the user's configured knowledge tool.\n- For ima, call the installed ima Skill or ima knowledge-base tool if the user\n  has configured one.\n- For Obsidian, use the user's Obsidian CLI, Obsidian Skill, or approved vault\n  workflow to write Markdown under a user-approved `Lingzao/` path.\n- For \u98de\u4e66, use the user's Lark/Feishu CLI or Skill with user authorization to\n  create or update a document.\n- Do not ask for or store ima, Obsidian, or Feishu credentials inside Lingzao.\n  Do not include internal implementation details, raw payloads, cache URLs,\n  signed URLs, API keys, or internal error details in synchronized content.\n\nProfile workflow:\n\n- If the user asks for a creator homepage or a basic homepage analysis, use `get-user-posted-notes` by default. It returns recent posts and enough author/post data for a basic read.\n- If the user sends a Xiaohongshu short link such as `xhslink.com/m/...`, or a\n  copied share sentence such as `@... \u67e5\u770bTa\u7684\u4e3b\u9875>> https://xhslink.com/m/...`,\n  extract the short link, normalize bare links to `https://...`, and read the\n  surrounding words before choosing a command. Do not classify the short link by\n  path alone. If the context says account, homepage, creator, profile,\n  benchmark, account diagnosis, homepage diagnosis, `Ta\u7684\u4e3b\u9875`, or recent posts,\n  treat it as a creator-homepage request and call\n  `get-user-posted-notes --url \"https://<short link>\"`.\n- If a Xiaohongshu short link has no context, ask whether the user wants creator\n  homepage recent posts or one-post detail before spending credits. If the\n  context says this note, comments, copy, transcript, one-post breakdown, or is\n  a normal note share sentence with a title snippet plus `\u524d\u5f80\u3010\u5c0f\u7ea2\u4e66\u3011\u4e00\u63a2\u7a76\u7adf\u5427`,\n  treat it as a one-post candidate, not a homepage. One-post words such as\n  `\u8fd9\u6761` or `\u8fd9\u7bc7` take priority over generic diagnosis wording. Do not default\n  to `get-note-detail`; first confirm it is a single post and ask for the final\n  note URL or note_id plus whether it is \u56fe\u6587 or \u89c6\u9891 when needed.\n- Only add `get-user-info` when the user specifically needs full profile-level stats such as bio, follower count, following count, total likes, total collections, or total note count.\n- Use `analyze-user-profile` for Xiaohongshu deeper homepage copy/script/subtitle analysis, recent post text, covers, commercial signals, or product-note signals. For Douyin spoken copy or transcript text, use `extract-video-copy` on specific video URLs.\n- Do not call `get-user-info` and `get-user-posted-notes` as a fixed pair unless the user asks for both profile-level stats and recent-post analysis.\n- Do not force a full account diagnosis when the homepage has too few public\n  posts. Route by visible sample size:\n  - 0 posts: no account diagnosis; switch to beginner start/account setup\n    guidance.\n  - 1-2 posts: homepage first impression plus single-post feedback only.\n  - 3-5 posts: starter-account mini diagnosis.\n  - 6-9 posts: light account analysis.\n  - 10+ posts: standard account analysis can be offered.\n  - 20+ posts: standard deep diagnosis can use `analyze-user-profile --limit 20`\n    after credit confirmation.\n  - 40+ posts: deep diagnosis, creator distillation, or knowledge-base\n    distillation can use `--limit 40` after credit confirmation.\n\nPost drill-down workflow:\n\n- Xiaohongshu list-style commands (`search-notes`, `get-user-posted-notes`,\n  `analyze-user-profile`) return `xhs_note_type` on each note item when\n  Lingzao can identify whether it is \u56fe\u6587 or \u89c6\u9891.\n- When continuing from one of those note items to `get-note-detail`, pass the\n  returned `xhs_note_type` directly as `--xhs-note-type`; do not infer the type\n  from the URL.\n- If a Xiaohongshu note item has no `xhs_note_type`, ask the user whether it is\n  \u56fe\u6587 or \u89c6\u9891 before calling `get-note-detail`. `get-note-comments` can still\n  be called without this type.\n\n## Setup\n\nResolve this `SKILL.md` directory as `<skill_root>`, then run setup once:\n\n```bash\nbash \"<skill_root>/scripts/setup.sh\" --base-url \"https://your-lingzao-domain.com\"\n```\n\nEnvironment variables override saved config:\n\n```bash\nexport LINGZAO_API_KEY=\"lgz_xxx\"\nexport LINGZAO_BASE_URL=\"https://your-lingzao-domain.com\"\n```\n\nCheck the connection:\n\n```bash\n~/.lingzao/bin/lingzao doctor\n```\n\nBefore using Lingzao commands, check whether the skill has an update:\n\n```bash\n~/.lingzao/bin/lingzao check-version\n```\n\nIf an update is available, stop the current Lingzao operation and update the skill first. Do not continue using an outdated Lingzao Skill for search, profile, subtitle, or extraction work.\n\nTo update the skill, rerun the installer. For `npx skills`, try:\n\n```bash\nnpx skills add https://assets-tian.midao.site/skills/lingzao --skill lingzao -g --copy\n```\n\nUpdating keeps the saved API config in `~/.lingzao/config.json`; no API key setup is needed again.\n\nIf `~/.lingzao/bin/lingzao` is missing or points to the wrong directory, repair the command wrapper:\n\n```bash\nbash ~/.agents/skills/lingzao/scripts/setup.sh --skip-doctor\n```\n\nIf `~/.agents/skills/lingzao` does not exist, find the directory that contains `lingzao`'s `SKILL.md`, then run `scripts/setup.sh --skip-doctor` from that directory.\n\n## Before Calling\n\nBefore running a command with meaningful filters, ask the user for the relevant\nparameters if they did not already specify them.\n\n- For `search-notes`, ask for sorting, note type, and time range before calling:\n  sort can be `general`, `most_liked`, `popularity_descending`,\n  `comment_descending`, or `collect_descending`; note type can be `\u4e0d\u9650`,\n  `\u89c6\u9891\u7b14\u8bb0`, `\u56fe\u6587\u7b14\u8bb0`, or `\u76f4\u64ad\u7b14\u8bb0`; time range can be `\u4e0d\u9650`, `\u4e00\u5929\u5185`,\n  `\u4e00\u5468\u5185`, or `\u534a\u5e74\u5185`.\n- Douyin `search-notes` currently supports only `general`, `most_liked`, and\n  `popularity_descending`. Do not pass `comment_descending` or\n  `collect_descending` for Douyin searches.\n- Douyin `search-notes` note type currently supports only `\u4e0d\u9650`, `\u89c6\u9891\u7b14\u8bb0`,\n  and `\u56fe\u6587\u7b14\u8bb0`. Do not pass `\u76f4\u64ad\u7b14\u8bb0` for Douyin searches.\n- For `get-note-comments`, ask whether the user wants latest comments or\n  liked-count sorting before calling Xiaohongshu. Use `--sort latest` for latest\n  comments and `--sort most_liked` for Xiaohongshu liked-count sorting.\n- Douyin comments currently support only `latest`. Do not ask for or pass\n  `--sort most_liked` on Douyin comment requests.\n- Xiaohongshu list-style commands (`search-notes`, `get-user-posted-notes`,\n  `analyze-user-profile`) return `xhs_note_type` on each note item when\n  Lingzao can identify whether it is \u56fe\u6587 or \u89c6\u9891. When continuing from one of\n  those note items to `get-note-detail`, pass the returned value directly as\n  `--xhs-note-type`; do not infer the type from the URL. If a Xiaohongshu note\n  item has no `xhs_note_type`, ask the user whether it is \u56fe\u6587 or \u89c6\u9891 before\n  calling `get-note-detail`. `get-note-comments` can still be called without\n  this type.\n- If the user explicitly says to use defaults, proceed with the documented\n  defaults instead of asking again.\n\nAfter a successful research command, tell the user the estimated time saved\nshown in the CLI Markdown output. If you called multiple Lingzao research\ncommands for one user request, summarize the total once. Do not show time-saved\nlanguage for `doctor`, `check-version`, failed commands, or JSON-only internal\nprocessing.\n\n## Commands\n\n### Search Notes\n\n```bash\n~/.lingzao/bin/lingzao search-notes --platform xhs --keyword \"AI\u5199\u4f5c\"\n~/.lingzao/bin/lingzao search-notes --platform xhs --keyword \"AI\u5199\u4f5c\" --sort most_liked\n~/.lingzao/bin/lingzao search-notes --platform xhs --keyword \"AI\u751f\u56fe\" --sort collect_descending --note-type \"\u89c6\u9891\u7b14\u8bb0\" --time-filter \"\u4e00\u5468\u5185\"\n~/.lingzao/bin/lingzao search-notes --platform douyin --keyword \"AI\u751f\u56fe\" --sort most_liked --note-type \"\u89c6\u9891\u7b14\u8bb0\"\n```\n\nUse this when the user wants public notes around a topic.\nBefore calling, ask the user for `--sort`, `--note-type`, and `--time-filter`\nwhen they have not specified those preferences.\n\n### Search Suggestions\n\n```bash\n~/.lingzao/bin/lingzao search-suggestions --platform xhs --keyword \"AI\u751f\u56fe\"\n~/.lingzao/bin/lingzao search-suggestions --platform xhs\n```\n\nUse this when the user wants Xiaohongshu keyword expansions, autocomplete\nphrases, or popular search recommendations. If `--keyword` is omitted, Lingzao\nreturns popular recommendations.\n\n### Search Creators\n\n```bash\n~/.lingzao/bin/lingzao search-users --platform xhs --keyword \"\u6bcd\u5a74\u535a\u4e3b\"\n~/.lingzao/bin/lingzao search-users --platform douyin --keyword \"AI\u751f\u56fe\"\n```\n\nUse this when the user wants creators in a topic or niche.\n\n### Get Creator Profile\n\n```bash\n~/.lingzao/bin/lingzao get-user-info --url \"https://www.xiaohongshu.com/user/profile/...\"\n~/.lingzao/bin/lingzao get-user-info --platform xhs --user-id \"63c21e0f000000002801a1bb\"\n~/.lingzao/bin/lingzao get-user-info --platform douyin --user-id \"MS4wLjABAAAA...\"\n```\n\nUse this when the user provides a creator profile URL or platform user ID and needs full profile-level stats. For Douyin bare user IDs, use the profile `sec_user_id`. For basic homepage analysis, prefer `get-user-posted-notes` and avoid calling both commands by default.\n\n### Get Creator Recent Posts\n\n```bash\n~/.lingzao/bin/lingzao get-user-posted-notes --url \"https://www.xiaohongshu.com/user/profile/...\"\n~/.lingzao/bin/lingzao get-user-posted-notes --platform xhs --user-id \"63c21e0f000000002801a1bb\"\n~/.lingzao/bin/lingzao get-user-posted-notes --platform douyin --user-id \"MS4wLjABAAAA...\" --limit 20\n```\n\nUse this when the user wants to understand what a creator has posted recently. Use this by default for basic creator homepage analysis. Douyin recent posts are a single-page call and currently support `--limit 20` at most. If the user asks for full profile-level stats, add `get-user-info`; if the user asks for Xiaohongshu post copy, scripts, captions, or transcript text across recent posts, use `analyze-user-profile` instead. For Douyin transcript text, use `extract-video-copy` on selected video URLs.\n\n### Analyze Creator Profile\n\n```bash\n~/.lingzao/bin/lingzao analyze-user-profile --url \"https://www.xiaohongshu.com/user/profile/...\" --limit 20\n~/.lingzao/bin/lingzao analyze-user-profile --platform xhs --user-id \"63c21e0f000000002801a1bb\" --limit 40\n~/.lingzao/bin/lingzao analyze-user-profile --platform douyin --user-id \"MS4wLjABAAAA...\" --limit 20\n```\n\nUse this when the user wants deeper creator profile data, including post text, covers, commercial signals, and profile-level content signals. For Xiaohongshu, it also includes subtitle/script previews. For Douyin, it does not extract homepage subtitles or transcript text; use `extract-video-copy` on selected video URLs when the user needs spoken copy.\nUse `--limit 20` by default. The default Markdown output shows readable subtitle previews when the platform provides them.\n\nImportant for Xiaohongshu: the complete profile subtitle/copy Markdown artifact is a top-level response field, not a per-note subtitle URL. Always check:\n\n`data.artifacts.subtitle_markdown.status`\n`data.artifacts.subtitle_markdown.url`\n\nDo not search only inside `items[]`. If `data.artifacts.subtitle_markdown.status == \"ready\"` and `url` exists, download it before deep script or subtitle analysis:\n\n```bash\ncurl -L \"$subtitle_markdown_url\" -o /tmp/lingzao-profile-subtitles.md\n```\n\nUse the downloaded Markdown file for complete subtitle/copy analysis. Use `--format json` when the user needs the structured fields. JSON includes `data.artifacts.subtitle_markdown.url` for the complete Markdown file when available, and inline `items[].text.subtitle.content/plain_text` are preview-sized to keep the response readable. If the artifact is unavailable, use the inline subtitle fields. For Douyin, expect `data.artifacts.subtitle_markdown.status == \"unsupported\"` and use the returned profile insights plus selected-video extraction instead.\n\n### Get Post Detail\n\n```bash\n~/.lingzao/bin/lingzao get-note-detail --url \"https://www.xiaohongshu.com/explore/...\" --xhs-note-type image\n~/.lingzao/bin/lingzao get-note-detail --platform xhs --note-id \"69690331000000001a02266a\" --xhs-note-type video\n~/.lingzao/bin/lingzao get-note-detail --platform douyin --note-id \"7372484715782352169\"\n```\n\nUse this when the user asks to analyze one public post.\nFor Xiaohongshu details, pass `--xhs-note-type image` for \u56fe\u6587 and\n`--xhs-note-type video` for \u89c6\u9891. If the note came from `search-notes`,\n`get-user-posted-notes`, or `analyze-user-profile`, reuse that item's\n`xhs_note_type` value.\n\n### Get Post Comments\n\n```bash\n~/.lingzao/bin/lingzao get-note-comments --url \"https://www.xiaohongshu.com/explore/...\"\n~/.lingzao/bin/lingzao get-note-comments --url \"https://www.xiaohongshu.com/explore/...\" --sort most_liked\n~/.lingzao/bin/lingzao get-note-comments --platform xhs --note-id \"69690331000000001a02266a\"\n~/.lingzao/bin/lingzao get-note-comments --platform douyin --note-id \"7372484715782352169\"\n~/.lingzao/bin/lingzao get-note-comments --url \"https://www.douyin.com/jingxuan?modal_id=...\" --cursor \"next_cursor_from_previous_response\"\n```\n\nUse this when the user asks for public comments on one post. The first version returns top-level comments only. Use `--sort most_liked` for Xiaohongshu liked-count sorting; Douyin currently supports the default `latest` sort only. If the response has `data.page.next_cursor`, pass that value with `--cursor` to fetch the next page.\nBefore calling Xiaohongshu comments, ask whether the user wants latest comments\nor liked-count sorting. For Douyin comments, use only `--sort latest`; do not\npass `--sort most_liked`.\n\n### Get WeChat Official-Account Articles\n\n```bash\n~/.lingzao/bin/lingzao get-article-detail --url \"https://mp.weixin.qq.com/s/...\"\n~/.lingzao/bin/lingzao get-article-stats --url \"https://mp.weixin.qq.com/s/...\"\n~/.lingzao/bin/lingzao get-related-articles --url \"https://mp.weixin.qq.com/s/...\"\n```\n\nUse these when the user provides a public WeChat official-account article URL\nand asks to analyze the article, inspect public engagement metrics, or expand\nfrom that article to related public articles. The first version is URL-only and\ncosts 20 credits per call. An empty related-articles list is a valid response.\nDo not use these commands for account article history, account listing, or\nmulti-page fanout unless Lingzao adds a separate capability.\n\n### Extract Short-Video Copy\n\n```bash\n~/.lingzao/bin/lingzao extract-video-copy --url \"https://www.xiaohongshu.com/explore/...\"\n~/.lingzao/bin/lingzao extract-video-copy --url \"https://v.douyin.com/...\"\n```\n\nUse this when the user asks for short-video spoken copy, transcript, subtitles, or\u53e3\u64ad\u6587\u6848.\n\n### Generate Image\n\n```bash\n~/.lingzao/bin/lingzao generate-image --prompt \"\u4e00\u5f20\u5c0f\u7ea2\u4e66\u5c01\u9762\u56fe\uff0c\u4e3b\u9898\u662f AI \u751f\u56fe\u65b0\u624b\u907f\u5751\uff0c\u5e72\u51c0\u660e\u4eae\uff0c\u4e2d\u6587\u5927\u6807\u9898\u7559\u767d\" --output /tmp/lingzao-image.png\n~/.lingzao/bin/lingzao generate-image --prompt \"\u6781\u7b80\u4ea7\u54c1\u6d77\u62a5\uff0c\u767d\u5e95\uff0c\u67d4\u548c\u9634\u5f71\" --size 1024x1536 --output /tmp/poster.png\n~/.lingzao/bin/lingzao generate-image --prompt \"\u53c2\u8003\u4e24\u5f20\u56fe\uff0c\u4fdd\u7559\u4eba\u7269\u98ce\u683c\uff0c\u628a\u4ea7\u54c1\u754c\u9762\u6362\u6210\u7075\u9020\u9996\u9875\u622a\u56fe\" --size 1536x2048 --image /tmp/style.png --image /tmp/product.png --output /tmp/poster.png\n~/.lingzao/bin/lingzao generate-image --prompt \"\u6279\u91cf\u751f\u6210 3 \u5f20\u5c01\u9762\u8349\u7a3f\" --count 3 --size 1024x1536 --output /tmp/poster.png\n```\n\nUse this only when the user asks to generate a creator image asset. For normal\nresearch, do not call image generation automatically.\n\nBefore calling `generate-image`, run the minimal intake gate. If the user only\nsays something like \"\u7ed9\u6211\u505a\u4e00\u5f20\u67d0\u67d0\u6d77\u62a5\u56fe\" or provides only a broad topic, do\nnot spend credits immediately. Ask for the two visual anchors first:\n\n1. \u4f60\u6709\u6ca1\u6709\u53c2\u8003\u56fe\uff1f\u53ef\u4ee5\u53d1 1-3 \u5f20\u4f60\u559c\u6b22\u7684\u5c01\u9762/\u6d77\u62a5/\u56fe\u6587\u622a\u56fe\u3002\n2. \u4f60\u6709\u6ca1\u6709\u60f3\u8981\u7684\u914d\u8272\uff1f\u6bd4\u5982\u660e\u4eae\u767d\u5e95\u3001\u7eff\u8272\u6e05\u723d\u3001\u9ed1\u91d1\u9ad8\u7ea7\u3001\u84dd\u8272\u79d1\u6280\u611f\u3002\n\nIf those are still unclear, ask at most one extra route-changing question, such\nas the publishing platform/size, exact on-image text, or whether the user wants\npeople/no people. Only proceed directly without asking when the user already\nprovided enough constraints: topic + platform/format + visual style/reference\nor color + on-image text/material.\nUse `--image` for local reference images; repeat it for multiple images. The\nSkill uploads those files directly to Lingzao for the current request, so the\nuser does not need to upload them elsewhere first. Supported reference image\nformats are png, jpeg, and webp.\n\n#### Reference Image Handling\n\nFor Codex, WorkBuddy, and other agent runtimes:\n\n- `--image` accepts local filesystem paths only. If the user provides a\n  reference image through a chat attachment, pasted image, screenshot, or input\n  box, first materialize that image as a local file before calling the CLI.\n  Preserve the original supported image format when saving the file.\n- Use a per-run temporary directory for runtime-provided images, for example\n  `/tmp/lingzao-image-inputs/<run-id>/ref-1.png` and\n  `/tmp/lingzao-image-inputs/<run-id>/ref-2.png`. Use absolute paths in the CLI\n  call.\n- If the user already provided a stable local path, such as a file under\n  `/Users/...`, you may pass that path directly. If the runtime-provided image\n  lives in a transient attachment/cache path, copy it into the per-run temp\n  directory first.\n- Do not proactively convert image formats. If the input image is already png,\n  jpeg, or webp and its file size is reasonable, pass it as-is. Do not convert\n  png to webp or jpeg just because an example path uses a different extension.\n- Only when a reference image is larger than 2 MB, create a smaller copy in the\n  temp directory and pass that copy with `--image`. Keep the file extension and\n  actual image bytes consistent. If resizing or compression fails, use the\n  original supported image file instead of trying another format.\n- Do not overwrite the user's original image file. Do not store reference\n  images in the repo. If the runtime cannot save an uploaded or pasted image to\n  a local path, ask the user to save the image locally and provide the path.\n- In the prompt, state what should be borrowed from the reference images, such\n  as layout, color palette, product shape, character style, or composition. Do\n  not say only \"reference this image\" when a more specific instruction is\n  possible.\n\nExample with a runtime-provided reference image:\n\n```bash\nmkdir -p /tmp/lingzao-image-inputs/run-001 /tmp/lingzao-image-outputs/run-001\n~/.lingzao/bin/lingzao generate-image \\\n  --prompt \"\u53c2\u8003\u8fd9\u5f20\u56fe\u7684\u6392\u7248\u548c\u660e\u4eae\u8272\u5f69\uff0c\u751f\u6210\u4e00\u5f20\u5c0f\u7ea2\u4e66\u5c01\u9762\u56fe\uff0c\u4e3b\u9898\u662f AI \u751f\u56fe\u65b0\u624b\u907f\u5751\uff0c\u4e2d\u6587\u5927\u6807\u9898\u7559\u767d\" \\\n  --size 1024x1024 \\\n  --image /tmp/lingzao-image-inputs/run-001/ref-1.png \\\n  --output /tmp/lingzao-image-outputs/run-001/result.png\n```\n\nThe command creates a Lingzao async batch and automatically polls the returned\nstatus URL until the background job finishes or the command timeout is reached.\nImage generation can take several minutes; `--timeout` can extend waiting for\nlarge or slow batches, but does not shorten the built-in per-image polling\nwindow. For one image, `--output` writes the result to the exact path you\nprovide. For `--count` greater than 1, `--output /tmp/poster.png` writes every\nsuccessful image as numbered files such as `/tmp/poster-1.png`,\n`/tmp/poster-2.png`, and so on. Default Markdown output requires `--output` so\npaid generated images are saved locally. Use `--format json` only when you need\nstructured item statuses or raw image payloads.\n\n## Usage Notes\n\n- For profile and post URLs, pass the URL directly when possible.\n- For raw IDs, include `--platform`.\n- Omit `--limit` unless the user asks for a specific count.\n- Search notes default to comprehensive sorting, all note types, and all time; use `--sort`, `--note-type`, and `--time-filter` when the user asks for ranked or filtered note search.\n- Use `--format json` only when another tool needs structured output.\n- Default output is Markdown for agents to read and summarize.\n- If the API key or account needs attention, ask the user to open the Lingzao dashboard.\n","usage":"\u8bfb\u53d6 SKILL.md\uff0c\u5e76\u6309\u9700\u8bfb\u53d6\u914d\u5957\u6587\u4ef6\uff1b\u4e0b\u8f7d ZIP \u83b7\u53d6\u5b8c\u6574\u5305\u3002\u6280\u80fd\u662f\u4efb\u52a1\u65b9\u6cd5\uff0c\u4e0d\u6388\u4e88\u65b0\u589e\u8d26\u6237\u3001\u4ed8\u8d39\u6216\u7cfb\u7edf\u6743\u9650\u3002"}