From 901c49f56b7b071782e26ebd6317897f567a98d2 Mon Sep 17 00:00:00 2001 From: wantsong Date: Tue, 2 Jun 2026 15:53:03 +0800 Subject: [PATCH] first commit --- README.md | 51 +++++++ VIDEO_WORKBENCH.md | 107 +++++++++++++ ccpe-consumption/runtime-links.md | 29 ++++ docs/ccpe-system-handoff.md | 116 ++++++++++++++ docs/context-handoff.md | 142 ++++++++++++++++++ indexes/active-episodes.md | 13 ++ indexes/active-series.md | 13 ++ indexes/completed-videos.md | 13 ++ indexes/source-article-map.md | 13 ++ series/abandoned/.gitkeep | 1 + series/active/.gitkeep | 1 + series/completed/.gitkeep | 1 + standalone/abandoned/.gitkeep | 1 + standalone/active/.gitkeep | 1 + standalone/completed/.gitkeep | 1 + templates/angle-proposal.md | 16 ++ templates/asset-log.md | 12 ++ .../episode-project/EPISODE_STRUCTURE.md | 55 +++++++ templates/episode.md | 22 +++ templates/publish-copy.md | 12 ++ templates/series-project/SERIES_STRUCTURE.md | 25 +++ templates/series.md | 21 +++ templates/shot.md | 19 +++ templates/source-map.md | 14 ++ templates/storyboard.md | 15 ++ templates/video-outline.md | 16 ++ 26 files changed, 730 insertions(+) create mode 100644 README.md create mode 100644 VIDEO_WORKBENCH.md create mode 100644 ccpe-consumption/runtime-links.md create mode 100644 docs/ccpe-system-handoff.md create mode 100644 docs/context-handoff.md create mode 100644 indexes/active-episodes.md create mode 100644 indexes/active-series.md create mode 100644 indexes/completed-videos.md create mode 100644 indexes/source-article-map.md create mode 100644 series/abandoned/.gitkeep create mode 100644 series/active/.gitkeep create mode 100644 series/completed/.gitkeep create mode 100644 standalone/abandoned/.gitkeep create mode 100644 standalone/active/.gitkeep create mode 100644 standalone/completed/.gitkeep create mode 100644 templates/angle-proposal.md create mode 100644 templates/asset-log.md create mode 100644 templates/episode-project/EPISODE_STRUCTURE.md create mode 100644 templates/episode.md create mode 100644 templates/publish-copy.md create mode 100644 templates/series-project/SERIES_STRUCTURE.md create mode 100644 templates/series.md create mode 100644 templates/shot.md create mode 100644 templates/source-map.md create mode 100644 templates/storyboard.md create mode 100644 templates/video-outline.md diff --git a/README.md b/README.md new file mode 100644 index 0000000..c6f1da7 --- /dev/null +++ b/README.md @@ -0,0 +1,51 @@ +# Video Workbench + +Video Workbench is the production workspace for dimensional output: turning deep essays, models, and ideas into short public-facing video packages. + +It is a sibling of Writing Workbench, not a subfolder of it. + +## Position + +```text +Knowledge Vault = source archive, formal essays, human model documents, historical discussions +Writing Workbench = deep article production workspace +Video Workbench = dimensional video output production workspace +CCPE System = AI cognitive asset engineering workspace +Delivery Systems = deployable external agentic products +``` + +## Mission + +This workspace manages the process of extracting one or two accessible points from deep essays or models and producing a video-ready package, usually under 10 minutes. + +It preserves: + +- series architecture +- episode scope +- angle proposals +- selected angle +- video outline +- global visual style +- storyboard logic +- shot-level deep production +- voiceover script +- image prompts +- generated image/audio assets +- editing notes +- publishing copy + +## Boundaries + +- Deep essays and human model documents remain in `knowledge-vault`. +- Deep article creation remains in `writing-workbench`. +- Actors, Skills, Model Cards, and Runtimes are maintained in `ccpe-system`. +- Manual editing and publishing remain human-controlled unless explicitly automated later. + +## Starting A New Session + +In a new Codex session opened on this project, use: + +```md +Please read README.md, VIDEO_WORKBENCH.md, docs/context-handoff.md, and docs/ccpe-system-handoff.md first, then continue work on Video Workbench according to those conventions. +``` + diff --git a/VIDEO_WORKBENCH.md b/VIDEO_WORKBENCH.md new file mode 100644 index 0000000..d58e0b6 --- /dev/null +++ b/VIDEO_WORKBENCH.md @@ -0,0 +1,107 @@ +# VIDEO_WORKBENCH.md + +## 1. Workspace Identity + +This project is the dimensional video output workspace. + +It turns deep source material into public-facing short video production packages. It is optimized for accessibility, rhythm, metaphor, visual planning, and asset preparation. + +## 2. Operating Principle + +One video should usually explain one or two points. + +The goal is not to compress a deep article into a shorter article. The goal is to extract a public-facing angle from a deep model or essay and rebuild it as a video-native experience. + +## 3. Source Inputs + +Typical sources: + +```text +knowledge-vault/sayings +knowledge-vault/rules +knowledge-vault/sources +knowledge-vault/discussions +``` + +Common inputs: + +- one long essay +- one human-facing model document +- selected source notes +- Deep Research reports +- a target audience/topic +- optional series plan + +## 4. Production Types + +Use `series/` when a long essay or model needs multiple episodes. + +Use `standalone/` when the output is a single independent video. + +Recommended project ids: + +```text +series/active/YYYY-MM-DD-sNNN-temp-series/ +standalone/active/YYYY-MM-DD-vNNN-temp-topic/ +``` + +Do not rely on final titles in folder names. Titles can evolve inside `series.md`, `episode.md`, or publishing files. + +## 5. Canonical Episode Stages + +The workflow maps to the user's prior dimensional output process: + +```text +00-architecture = series/episode architecture, source selection, word budget +01-proposals = three distinct angle proposals +02-tone-outline = selected angle, core anchor, metaphor, visual style, global prompt +03-storyboard = storyboard logic and time budget +04-deep-production = shot-level visual plan, image prompts, voiceover, design notes +05-assets = generated images, audio, optional video clips, asset log +06-editing = manual edit notes and timeline plan +07-publish = title options, description, platform copy, final script +08-review = review notes and postmortem +``` + +## 6. Word Budget + +Use the default standard: + +```text +1 minute = about 220 Chinese characters of voiceover +10 minutes = about 2200 Chinese characters +``` + +Adjust only when the user specifies a different narration speed. + +## 7. Asset Policy + +Image and audio generation can be automated when APIs and models are available. + +Video generation from images remains manual or semi-manual for now because output reliability varies. + +Editing and publishing are human-controlled in the initial version. + +## 8. CCPE Consumption + +Video Workbench consumes CCPE assets from: + +```text +C:\Users\wangq\Documents\Codex\ccpe-system +``` + +Likely assets: + +- Qiangge's Apprentice / dimensional output actor +- series architect +- angle proposal skill +- video outline skill +- storyboard skill +- shot deep-production skill +- image prompt generator +- voiceover script generator +- visual style model card +- short video production runtime + +Do not duplicate canonical CCPE definitions here. Use `ccpe-consumption/` for links and usage notes. + diff --git a/ccpe-consumption/runtime-links.md b/ccpe-consumption/runtime-links.md new file mode 100644 index 0000000..7f805e1 --- /dev/null +++ b/ccpe-consumption/runtime-links.md @@ -0,0 +1,29 @@ +# CCPE Runtime Links + +This file records how Video Workbench consumes CCPE System assets. + +Canonical CCPE workspace: + +```text +C:\Users\wangq\Documents\Codex\ccpe-system +``` + +## Planned Assets + +| Asset | Type | Status | Notes | +| --- | --- | --- | --- | +| Qiangge's Apprentice | Lite / Agent Spec | planned | Primary dimensional output actor | +| Short Video Production Runtime | Runtime | planned | Full video package workflow | +| Source-To-Episode Splitter | Skill | planned | Split deep source into episodes | +| Angle Proposal Generator | Skill | planned | Generate three entry angles | +| Tone And Outline Builder | Skill | planned | Build video outline and global visual style | +| Storyboard Logic Builder | Skill | planned | Build timed storyboard logic | +| Shot Deep Production | Skill | planned | Build shot visual plan, prompt, voiceover, notes | +| Image Prompt Generator | Skill | planned | Produce consistent image prompts | +| Voiceover Script Generator | Skill | planned | Fit narration to duration budget | +| Publish Copy Generator | Skill | planned | Prepare platform copy | + +## Policy + +Do not copy canonical CCPE artifacts here. Record links, usage notes, and task-specific adapters only. + diff --git a/docs/ccpe-system-handoff.md b/docs/ccpe-system-handoff.md new file mode 100644 index 0000000..841f240 --- /dev/null +++ b/docs/ccpe-system-handoff.md @@ -0,0 +1,116 @@ +# CCPE System Handoff For Video Workbench + +This document is the handoff for future work in: + +```text +C:\Users\wangq\Documents\Codex\ccpe-system +``` + +It records the CCPE assets needed to support Video Workbench. + +## Core Principle + +Use scenario-first layering. + +Do not force every old prompt into Skill, Agent, and Runtime layers. Preserve a working Lite kernel when it is the correct production form. Promote to Agent Spec, Skill, Model Card, or Runtime only when the video workflow needs that layer. + +## Existing Actor To Upgrade + +Previous single-agent actor: + +```text +强哥的徒弟 +``` + +Likely first target: + +```text +agents/lite/qiangge-apprentice.prompt.md +``` + +Purpose: + +```text +Transform deep essays and models into public-facing short video plans, scripts, visual prompts, and production packages. +``` + +## Recommended CCPE Build Sequence + +1. Upgrade `强哥的徒弟` into a verified CCPE-Lite artifact. +2. Preserve regression tests against the original workflow: + - angle proposals + - video outline + - storyboard logic + - shot deep production +3. Run Scenario Probe before promoting to Agent Spec or Skill. +4. Extract stable embedded models into Model Cards only when they are reusable beyond this actor. +5. Build small Skills only for repeatable actions: + - source-to-episode splitter + - angle proposal generator + - global visual style builder + - storyboard logic builder + - shot deep-production generator + - image prompt generator + - voiceover script generator + - publish copy generator +6. Build a `Short Video Production Runtime` only after the core stages are stable. +7. Validate the runtime with a trial Video Workbench project. + +## Candidate Asset Map + +| Asset | Candidate Type | Purpose | +| --- | --- | --- | +| Qiangge's Apprentice | CCPE-Lite / Agent Spec | Primary dimensional output actor | +| Dimensional Output Model | Model Card | Extract deep model into public-facing point | +| Series Architect | Agent / Skill | Split long essay/model into episodes | +| Angle Proposal Generator | Skill | Produce three distinct entry angles | +| Tone And Outline Builder | Skill | Produce video outline and global style | +| Storyboard Logic Builder | Skill | Produce shot logic with timing and word budget | +| Shot Deep Production | Skill | Produce visual plan, image prompt, voiceover, design notes | +| Image Prompt Generator | Skill | Generate consistent image prompts | +| Voiceover Script Generator | Skill | Fit narration to duration budget | +| Short Video Production Runtime | Runtime | Coordinate full video package production | + +## Runtime Boundary + +The first runtime should stop at a production package: + +- selected angle +- video outline +- storyboard logic +- shot deep-production files +- image prompts +- voiceover script +- optional image/audio assets +- editing notes +- publishing copy + +Do not automate manual editing or platform publishing in the first version. + +## Relationship To Writing Runtime + +Article production and video production should remain separate runtimes. + +They share sources and sometimes models, but they differ in: + +- target output +- audience +- timing constraints +- visual constraints +- asset generation +- evaluation criteria + +## Validation Target + +The first validation project should use one existing deep essay and one existing model document from Knowledge Vault. + +Expected success: + +- a clear episode or standalone scope +- three genuinely different angles +- a selected angle trace +- a coherent visual/narration protocol +- a complete storyboard +- shot-level prompts and voiceover +- a package ready for manual editing + diff --git a/docs/context-handoff.md b/docs/context-handoff.md new file mode 100644 index 0000000..fc564b2 --- /dev/null +++ b/docs/context-handoff.md @@ -0,0 +1,142 @@ +# Video Workbench Context Handoff + +This document preserves the working agreements for Video Workbench so future Codex sessions do not depend on copied chat history. + +## Confirmed Architecture + +```text +Knowledge Vault = source archive and model/essay library +Writing Workbench = deep article production workspace +Video Workbench = public-facing dimensional video output workspace +CCPE System = actor, skill, model, and runtime factory +``` + +Video Workbench is a sibling of Writing Workbench. It should not be folded into article production because the target output, rhythm, assets, and evaluation criteria are different. + +## User's Dimensional Output Workflow + +The user's deep essays are often 7,000 to 50,000 Chinese characters. Direct decompression into public form can multiply the text volume, which does not fit current public reading habits. + +The user's method: + +```text +Extract one or two points from a deep article or model. +Connect them to a public-facing concern. +Produce a video usually under 10 minutes. +Use about 220 Chinese characters per minute as the narration budget. +``` + +The previous single-agent actor was named `强哥的徒弟`. Video Workbench should preserve the workflow but move toward file-based, agentic production. + +## Workflow Stages + +### Stage 0: Series Architecture + +Decide whether the video belongs to a series or is standalone. + +Inputs usually include: + +- `knowledge-vault/rules` model documents +- `knowledge-vault/sayings` essay originals +- selected source material + +Outputs: + +- series plan, if any +- episode split +- target duration +- word budget +- selected source map + +### Stage 1: Angle Proposals + +Find three distinct entry angles. + +Output style: + +```text +EP.01 [temporary episode name] - angle proposal +``` + +The user selects the angle. + +### Stage 2: Tone And Outline + +Produce the video outline: + +- framing and positioning +- core thought anchor +- governing metaphor +- global visual style constraints +- Chinese style description +- English Global Prompt parameters +- narration/writing protocol + +### Stage 3: Storyboard Logic + +Produce storyboard logic with time and word budget. + +Example: + +```text +Shot 1 [Puzzle Introduction]: 30 seconds / about 110 Chinese characters. +Shot 2 [Deep Dive]: 90 seconds / about 330 Chinese characters. +``` + +### Stage 4: Shot Deep Production + +For each shot, produce: + +- page or screen visual plan +- image generation prompt +- voiceover script +- design subtext +- transition notes + +### Stage 5: Assets + +Generate or collect: + +- images +- voiceover audio +- optional video clips +- asset log + +Image and audio generation can be automated later. Image-to-video remains manual for now. + +### Stage 6: Editing + +Editing remains manual initially. + +Video Workbench should provide edit notes and timeline plan, not assume full editing automation. + +### Stage 7: Publishing + +Publishing remains manual initially. + +Video Workbench can prepare platform copy: + +- title options +- description +- cover copy +- hashtags / tags +- final script + +## Project Shape + +Use `series/` for multi-episode work and `standalone/` for one-off videos. + +Each episode should preserve both process and final outputs. The canonical expanded episode structure is in: + +```text +templates/episode-project/EPISODE_STRUCTURE.md +``` + +## New Session Instruction + +Use this in a new Video Workbench session: + +```md +Please read README.md, VIDEO_WORKBENCH.md, docs/context-handoff.md, and docs/ccpe-system-handoff.md first, then continue work on Video Workbench according to those conventions. +``` + diff --git a/indexes/active-episodes.md b/indexes/active-episodes.md new file mode 100644 index 0000000..e8e1b61 --- /dev/null +++ b/indexes/active-episodes.md @@ -0,0 +1,13 @@ +# Active Episodes + +No active standalone episodes yet. + +Record: + +- episode id +- temporary title +- source-map path +- current stage +- duration target +- next action + diff --git a/indexes/active-series.md b/indexes/active-series.md new file mode 100644 index 0000000..f82e98d --- /dev/null +++ b/indexes/active-series.md @@ -0,0 +1,13 @@ +# Active Series + +No active series projects yet. + +Record: + +- series id +- temporary title +- source model / essay +- episode count +- current episode +- next action + diff --git a/indexes/completed-videos.md b/indexes/completed-videos.md new file mode 100644 index 0000000..c0b7d1e --- /dev/null +++ b/indexes/completed-videos.md @@ -0,0 +1,13 @@ +# Completed Videos + +No completed videos yet. + +Record: + +- episode id +- final title +- source article/model +- final script path +- asset paths +- publish status + diff --git a/indexes/source-article-map.md b/indexes/source-article-map.md new file mode 100644 index 0000000..1f64e02 --- /dev/null +++ b/indexes/source-article-map.md @@ -0,0 +1,13 @@ +# Source Article Map + +This index maps video outputs back to Knowledge Vault sources. + +Record: + +- video or episode id +- source essay path +- source model path +- source notes or research +- extracted point +- resulting package path + diff --git a/series/abandoned/.gitkeep b/series/abandoned/.gitkeep new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/series/abandoned/.gitkeep @@ -0,0 +1 @@ + diff --git a/series/active/.gitkeep b/series/active/.gitkeep new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/series/active/.gitkeep @@ -0,0 +1 @@ + diff --git a/series/completed/.gitkeep b/series/completed/.gitkeep new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/series/completed/.gitkeep @@ -0,0 +1 @@ + diff --git a/standalone/abandoned/.gitkeep b/standalone/abandoned/.gitkeep new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/standalone/abandoned/.gitkeep @@ -0,0 +1 @@ + diff --git a/standalone/active/.gitkeep b/standalone/active/.gitkeep new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/standalone/active/.gitkeep @@ -0,0 +1 @@ + diff --git a/standalone/completed/.gitkeep b/standalone/completed/.gitkeep new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/standalone/completed/.gitkeep @@ -0,0 +1 @@ + diff --git a/templates/angle-proposal.md b/templates/angle-proposal.md new file mode 100644 index 0000000..5f81908 --- /dev/null +++ b/templates/angle-proposal.md @@ -0,0 +1,16 @@ +# Angle Proposal + +## Source + +## Audience + +## Duration Target + +## Proposal 1 + +## Proposal 2 + +## Proposal 3 + +## Recommended Selection + diff --git a/templates/asset-log.md b/templates/asset-log.md new file mode 100644 index 0000000..dc3a9ba --- /dev/null +++ b/templates/asset-log.md @@ -0,0 +1,12 @@ +# Asset Log + +## Images + +## Audio + +## Video Clips + +## Uploads + +## Notes + diff --git a/templates/episode-project/EPISODE_STRUCTURE.md b/templates/episode-project/EPISODE_STRUCTURE.md new file mode 100644 index 0000000..f804589 --- /dev/null +++ b/templates/episode-project/EPISODE_STRUCTURE.md @@ -0,0 +1,55 @@ +# Episode Project Structure + +Use this structure when expanding a standalone video or a series episode. + +```text +ep-01-temp-title/ + episode.md + source-map.md + + 00-architecture/ + series-context.md + episode-scope.md + word-budget.md + + 01-proposals/ + proposal-v1.md + selected-angle.md + + 02-tone-outline/ + video-outline.md + global-visual-style.md + global-prompt.md + narration-protocol.md + + 03-storyboard/ + storyboard-logic.md + + 04-deep-production/ + shots/ + shot-01.md + shot-02.md + voiceover-full.md + image-prompts.md + design-notes.md + + 05-assets/ + images/ + audio/ + video-clips/ + asset-log.md + + 06-editing/ + edit-notes.md + timeline-plan.md + + 07-publish/ + title-options.md + description.md + platform-copy.md + final-script.md + + 08-review/ + review-notes.md +``` + diff --git a/templates/episode.md b/templates/episode.md new file mode 100644 index 0000000..ff513b2 --- /dev/null +++ b/templates/episode.md @@ -0,0 +1,22 @@ +# Episode + +## Identity + +- Episode ID: +- Temporary title: +- Final title: +- Series: +- Status: +- Target duration: +- Word budget: + +## Source Point + +## Public-Facing Question + +## Selected Angle + +## Human Decision Gates + +## Notes + diff --git a/templates/publish-copy.md b/templates/publish-copy.md new file mode 100644 index 0000000..14e7190 --- /dev/null +++ b/templates/publish-copy.md @@ -0,0 +1,12 @@ +# Publish Copy + +## Title Options + +## Description + +## Cover Copy + +## Tags + +## Platform Variants + diff --git a/templates/series-project/SERIES_STRUCTURE.md b/templates/series-project/SERIES_STRUCTURE.md new file mode 100644 index 0000000..a68d776 --- /dev/null +++ b/templates/series-project/SERIES_STRUCTURE.md @@ -0,0 +1,25 @@ +# Series Project Structure + +Use this structure when expanding a new active series. + +```text +YYYY-MM-DD-sNNN-temp-series/ + series.md + source-map.md + episode-map.md + + episodes/ + ep-01-temp-title/ + episode.md + source-map.md + 00-architecture/ + 01-proposals/ + 02-tone-outline/ + 03-storyboard/ + 04-deep-production/ + 05-assets/ + 06-editing/ + 07-publish/ + 08-review/ +``` + diff --git a/templates/series.md b/templates/series.md new file mode 100644 index 0000000..520092d --- /dev/null +++ b/templates/series.md @@ -0,0 +1,21 @@ +# Series + +## Identity + +- Series ID: +- Temporary title: +- Final title: +- Status: +- Created: +- Last updated: + +## Source Model Or Essay + +## Series Thesis + +## Target Audience + +## Episode Plan + +## Notes + diff --git a/templates/shot.md b/templates/shot.md new file mode 100644 index 0000000..a2c2782 --- /dev/null +++ b/templates/shot.md @@ -0,0 +1,19 @@ +# Shot + +## Shot Identity + +- Shot number: +- Function: +- Time budget: +- Word budget: + +## Visual Plan + +## Image Prompt + +## Voiceover + +## Design Subtext + +## Transition Notes + diff --git a/templates/source-map.md b/templates/source-map.md new file mode 100644 index 0000000..c1529a5 --- /dev/null +++ b/templates/source-map.md @@ -0,0 +1,14 @@ +# Source Map + +## Knowledge Vault Sources + +## Source Essay + +## Source Model + +## Selected Excerpts + +## CCPE Sources + +## Notes + diff --git a/templates/storyboard.md b/templates/storyboard.md new file mode 100644 index 0000000..f22056d --- /dev/null +++ b/templates/storyboard.md @@ -0,0 +1,15 @@ +# Storyboard Logic + +## Duration Target + +## Word Budget + +## Shots + +### Shot 1 + +- Function: +- Time budget: +- Word budget: +- Logic: + diff --git a/templates/video-outline.md b/templates/video-outline.md new file mode 100644 index 0000000..5f20b5a --- /dev/null +++ b/templates/video-outline.md @@ -0,0 +1,16 @@ +# Video Outline + +## Framing And Positioning + +## Core Thought Anchor + +## Governing Metaphor + +## Global Visual Style + +## English Global Prompt Parameters + +## Narration Protocol + +## Outline +