dasheng-media-workflow-skills

Use when Dasheng Publish needs to route Xiaohongshu publishing or content access through API-first CLI, MCP, or browser fallback bridges.

Use when Dasheng Publish needs to prepare, upload, or package Bilibili video submissions from completed transwrite video channel packs.

Use when running Stage 3 Draft from approved Brief topics and producing Reasoning Sheets, standard drafts, and draft quality gates.

Use when the workflow enters Postmortem after Publish and published content needs to be evaluated with performance data, Publish Guard status, accuracy checks, and knowledge-base writeback suggestions.

Use when Dasheng draft or transwrite needs HTML Anything templates, editable article HTML, social cards, posters, or visual HTML references.

Use when Dasheng transwrite needs no-human or human-material talking-head videos rendered through the local html-video project.

Use when running, resuming, auditing, or updating the Dasheng self-media workflow in this repo. This is the only formal orchestration entry and it governs the simplified canonical chain.

AI-driven topic generation for Dasheng workflow. Analyzes intake data to generate insightful, valuable, and actionable topic proposals with natural language titles and clear arguments.

Stage 3 Draft - 初稿生成（标准基线稿）

Use when entering the slim Dasheng publish execution stage to validate transwrite outputs, create publish packs, push drafts/manual packages, and recover published links.

Use when converting confirmed Dasheng drafts into channel-ready WeChat article, talking-head video, and podcast production packages.

Use when turning a Dasheng HTML article into a no-human vertical explainer video with voiceover, storyboard scenes, HTML animation, real charts, music, and final MP4.

Use when applying open-source warm cinematic portrait filters to Dasheng talking-head videos after rough cut.

Use when rough-cutting Chinese talking-head video with local FunASR transcription, silence trimming, repetition/filler detection, subtitles, and an audit page.

Use when producing or improving Dasheng真人出镜口播视频 from raw speaker footage, subtitles, rough cuts, B-roll, data charts, or HTML sticker overlays.

Use when Dasheng Publish needs a bridge to the external social-auto-upload project for video upload packages across Bilibili, Xiaohongshu, Douyin, Kuaishou, WeChat Channels, Baijiahao, TikTok, or YouTube.

Use when running the canonical Dasheng intake stage for the current day and producing real-title, real-link source radar outputs for Brief handoff.

Use when the workflow enters Stage 2 Brief and the current Agent must generate 8-10 candidate topic cards from canonical intake evidence under the Dasheng mainline.

Use when the workflow enters Stage 5 postmortem and published content needs to be evaluated with performance data, accuracy checks, and knowledge-base writeback suggestions.

Use when running, resuming, auditing, or updating the Dasheng self-media workflow in this repo. This is the only formal orchestration entry and it governs the simplified canonical chain.

Use when users provide standard articles, content templates, successful samples, or channel templates and want Codex to learn article paradigms/frameworks for different scenarios, channels, and styles.

Use when entering the formal publish stage of Dasheng workflow to run channel gating, video supplement, platform adaptation, platform execution, and publish verification.

面向自媒体作者的文风 DNA 提取与分析技能。从历史文章中建立可复用的风格画像，输出 14 维分析、段落配方、叙述方法体系、内容推进方式等，供改写阶段调用。

Use when creating or updating Feishu docs from markdown in this repo and you need the known-safe block conversion flow instead of writing docx blocks naively.

Stage 5 Rewrite v3 - 渠道改写（集成增强质量评分和锚点映射）

Use when an agent needs a standalone no-login hotspot/news radar for Dasheng workflows, especially public macro/policy/geopolitics/market trend capture without running the full intake stage.

Draft 阶段按需金融数据增强工具。用于把 A 股/指数行情、估值与时间序列数据转成可直接嵌入 Draft HTML 的 Chart.js `chart_specs`。

Legacy compatibility entry for dasheng-media-sop

Legacy compatibility entry for dasheng-media-sop

Use only when an old pipeline still explicitly calls the legacy brief step; the current standard merges editor brief generation into dasheng-daily-phase2

Use only when an old Dasheng pipeline still explicitly calls the legacy clustering wrapper; the current Stage 2 external entry is dasheng-daily-phase2 under dasheng-media-sop.

Use only when replaying a legacy Dasheng draft step; the standard Draft stage is now governed by dasheng-media-sop and the stage interface documents rather than this historical skill entry.

Use only when replaying or debugging the legacy Dasheng finalization step; the standard mainline now splits this logic across rewrite, material, publish, and postmortem under dasheng-media-sop.

Use only when replaying a historical outline-only workflow; the current mainline no longer exposes outline as a standalone stage and routes directly from brief to draft under dasheng-media-sop.

Use when running, resuming, or auditing the full Dasheng 8-stage media workflow with strict stage contracts and delivery outputs.

Use when entering the distribute stage to publish rewritten content and videos across WeChat, Xiaohongshu, Douyin, Weibo, and X platforms using existing OpenClaw platform skills.

Use when executing the upstream stages (intake, brief, draft) of Dasheng workflow and producing editor-ready topic sets and standard drafts.

Use when entering publish stage and needing the mandatory pre-publish video supplement, including interactive chart videos and motion narrative videos with style template selection.

Use when generating the 4-variant rewrite set per topic with hard word-count validation, final-structure inheritance, and optional personal style DNA injection.

Download videos from 1800+ websites and generate subtitles using Faster Whisper AI. Use when user wants to download videos from YouTube, Bilibili, Twitter, TikTok, Facebook, Vimeo, or any other supported video site, extract audio, or transcribe video content to text/subtitles.