ai-short-drama

AI Short-Drama Refined IP Creation v0.6.0

v0.6.0 changelog（2026-05-16）

SD-002 "City Dating Show" EP01 36 grid × 3 rounds (v2.5/v2.6/v2.7) run + full review reverse engineering. Fixed from "16/36 catastrophic-level consistency breakage" to "0 catastrophic / 60% ≥4 points" + distilled 2 industrial-grade SOPs.

Key Upgrades

⭐ references/storyboard-frame-industrial.md v0.3.0: Storyboard Image Craft SOP
- 8-segment prompt template (CHARACTER/BACKGROUND/ACTION/SCENE/CAMERA/LIGHT/TEXT/STYLE)
- NOT humans clause must be added: each protagonist separately Xxx body IS [arch] architecture NOT a human wearing X NOT a human with headpiece
- ref library craft bias iron rule: modern skyscrapers prone to anthropomorphism / ancient architecture always produces chibi human bodies
- Multi-character SOP: 1 protagonist ref + N text silhouette + bokeh blur
- Dramatic lighting lexicon (25+ keywords) + Hongguo-grade first-frame 10-point checklist
- 11-section complete document (including EP01 v2.7 measured verification grid13/21/22 all 5/5)

⭐ references/jimeng-failure-modes.md v0.1.0 (new): Jimeng 5.0 failure modes + full sensitive-word list
- 3 types of fail fully distinguished: InvalidNode (character count exceeded) / generation failed (moderation) / no image_url (network)
- prompt character hard upper limit: 1500 characters(measured distribution table)
- Villain word replacement table：sinister/menacingly/dark intent → moody/leaning/quiet
- Ambiguous word list：blush/cheeks/extreme close-up → rose tint/medium shot
- Concurrency vs serial rate limiting: long prompt + concurrency = fail, long prompt must run singly
- 4 grid practical diagnostic cases + craft verification checklist
⭐ scripts/generate_storyboard.py add --no-fingerprint flag
- Prevent 02_IP brief.md's ref style visual fingerprint (neutral / flat / NOT cinematic) from polluting storyboard images' dramatic lighting
- max_workers 8 → 4 (reduce concurrency to prevent rate limiting)
- timeout 300 → 420s + retry 2 times (prevent long prompt timeout)

Biggest Lesson

ref 工艺是分镜图工艺的上游。
ref 不纯（chibi 人体），分镜图加 NOT humans 也救不回来。
前期 IP 设计阶段就要避坑：选玻璃塔 / 简单几何，避复杂古建筑。

v0.3.0 changelog（2026-05-08）

SD-001 practical combat + industrial-grade methodology research distillation. Added Phase 1.5 storyboard image layer + 4-mode video generation.

Key Upgrades

⭐ Phase 1.5 Storyboard Image Layer(industrial-grade 5-step process core)
- scripts/生成分镜图.py: 1-4 candidate keyframes per grid (text2image)
- Storyboard image = video first frame (image2video / frames2video input)
- Modification cost 3 credits/image vs video 55 credits/segment = 18 times cheaper
- Video composition = static image (no longer random)
⭐ 4-Mode Video Generation(auto selects based on file existence)
- image2video: storyboard image first frame + action prompt (default main use 80%)
- frames2video: first frame + last frame locked (key climax 10%)
- multiframe2video: 2-20 keyframes one-shot continuous (complex action 5%)
- multimodal2video：9 image + 3 video + 3 audio fallback（5%）
⭐ ref 5-8 optimal(don't stuff 9 → attention scattered)
⭐ @ instruction explicit responsibility syntax(@Image1 as character reference / @Video1 reference camera movement)
⭐ Key grid first and last frames(climax/villain/inner voice/beat must lock)

Document Added

references/storyboard-frames-craft.md(storyboard image workflow + 4-model selection)

Script added / modified

scripts/生成分镜图.py(new, Step 3)
scripts/生成分集视频.py(modified, supports 4-model auto selection)
assets/templates/分镜.json(added video_mode / first_frame_path / last_frame_path / multiframe_paths fields)

v0.2.0 changelog（2026-05-08）

Practical distillation from SD-001 "Reborn Through Time as Xiaotian Quan". 13 failure modes → 13 fixes + industrial-grade standards.

Key fixes

⭐ scripts/generate_episode_video.py(replaces bash): subprocess args list directly calls dreamina, avoiding bash eval quoting errors with Chinese/special-character prompts (the old bug caused multimodal2video tasks to be silently dropped by the server, with list_task falsely showing alive for 30+ minutes)
⭐ scripts/ref_completeness_check.py: before generating video, forcibly scans all (@xxx_ref.png) references, and exits 1 if any are missing locally
⭐ scripts/derive_episode_files.py: one-click derivation from storyboard.json to Jimeng batch package.md / shot list.md
regex fix: containing full-width Chinese ） stop characters (r'@([^\s),）]+_ref\.png)'）
multimodal2video stuck auto-detection: after submission, check queue_status == 'Generating', otherwise fall back to list_task to recover submit_id

Rhythm upgrade

36 grid × 4-10s variation replaces rigid 60 grid × 3s (multimodal2video minimum is 4s, 3s is invalid)
Hongguo guaranteed-hit 7 moves (see details references/v21-97-percent-rules.md）
Duration distribution: 4s × 11 + 5s × 14 + 6s × 5 + 7s × 3 + 8-10s × 3 = 36 segments / ~190s

Asset standard upgrade

ref library target 80-150 images(vs v0.1.x 22 images)
single prompt 300-500 characters(vs v0.1.x 100-200 characters)
ref layering: ① master style ② character base multi-angle ③ character expression library ④ key actions ⑤ scene multi-angle ⑥ prop details

Docs

Added references/troubleshooting.md(13 failure modes + solutions)
Added references/v21-97-percent-rules.md(7 moves + 24-episode calibration template)
Changed references/storyboard-craft.md to 36 grid 4-10s variation
Changed references/jimeng-cli-guide.md to add v0.2.0 upgrade + web-side visibility

Core architecture: 2 Phase

┌─ Phase 1：创作（成本低，反复迭代）─────────────────┐
│  阶段 0：市场情报扫描                              │
│  阶段 1：IP 简报（5 子步）                         │
│  阶段 2：故事架构（4 子步）                        │
│  阶段 3：设定圣经（4 子步）                        │
│  阶段 3.5：ref 图自动生成（dreamina CLI）          │
│  阶段 5：批判 refine                              │
└──────────────────────────────────────────────────┘
                      ↓
┌─ Phase 1.5：分镜图（v0.3.0 工业级核心）⭐ 新增 ─────┐
│  ⚠️ 写 prompt 前必读：                            │
│   - storyboard-frame-industrial.md §5（8 段模板）  │
│   - jimeng-failure-modes.md §1+§2（字数+敏感词）   │
│  对每一集独立运行：                               │
│  3A：写该集分镜.json（v0.3.0 字段：video_mode +    │
│       first_frame_path + last_frame_path）         │
│  3B：python scripts/ref完备性检查.py              │
│  3C：python scripts/生成分镜图.py（每 grid 1-4    │
│       张候选关键帧 = 视频首帧）                    │
│  3D：人工选图（grid01_候选3.png → grid01.png）    │
│  3E：关键 grid（爆点/反派/心声）生首尾帧           │
│       （gridXX_首.png + gridXX_尾.png）           │
└──────────────────────────────────────────────────┘
                      ↓
┌─ Phase 2：出片（成本高，按集解锁）────────────────┐
│  4.A：python scripts/生成分集视频.py              │
│       auto 模式按文件存在自动选 4 模：             │
│       - frames2video（首尾帧锁定）                │
│       - image2video（分镜图首帧 + 动作）          │
│       - multiframe2video（2-20 帧一镜到底）       │
│       - multimodal2video（fallback 多 ref）       │
│  4.B：用户在剪映拼接 + 配音 + BGM + 字幕           │
└──────────────────────────────────────────────────┘

Why split it this way：

Unsatisfied with script / ref → iterate repeatedly in Phase 1, without burning video money
Storyboard image = video first frame → confirm the static image first in Phase 1.5 (3 credits/image), if unsatisfied modify prompt and regenerate → video composition is fixed (no longer random)
Modification cost: storyboard image 3 credits vs video segment 55 credits = 18 times cheaper, saving 50%+ on video trial and error
Video output cost is high → Phase 2 unlocked episode by episode, with the user accepting each episode
The real cost of AI short dramas is not creation, it is output. Use Phase 1 + 1.5 to polish the composition into place, and only then is Phase 2 worth spending money on

Trigger conditions

Any one of the following triggers:

User says "make/write/help me make ... a short drama"
Mentions Hongguo/Fanqie/Douyin/Kuaishou IP adaptation
Mentions Jimeng/Seedance/Kling/Vidu output, and talks about script
Mentions storyboard, storyboard, shot list, shot script
Mentions satisfying drama, angsty drama, chasing wife, revenge, rebirth, time travel, live-in son-in-law, grandma awakening, miracle doctor physiognomist, AI comic drama spectacle

Counterexamples that do not trigger:

User already has a complete script and only wants to change one line of dialogue → edit it directly
User asks "What's the outlook for the short-drama industry?" → ordinary Q&A
User asks "What is an AI short drama?" → ordinary Q&A

Default parameters (v0.6.0)

Item	Default value	Source
Per-episode duration	180-195s	Best measured on Hongguo (not strictly capped at 180)
Number of episodes	24 episodes(essential) / 72 episodes (regular)	24 episodes save cost + tight climaxes
Storyboard shots per episode	36 grid × 4-10s variation	multimodal2video minimum 4s, variation prevents a mechanical feel
Duration variation distribution	4s×11 + 5s×14 + 6s×5 + 7s×3 + 8-10s×3	v2.1 Hongguo guaranteed-hit iron rule
Video aspect ratio	9:16 vertical	Unified across Hongguo/Douyin/Kuaishou
Video mode	multimodal2video (omni-reference)	Seedance 2.0 Fast VIP, most stable with multiple ref inputs
Subtitles	On(wrapped in Chinese brackets + AIGC label)	Mandatory on Hongguo
ref library target	80-150 images(industrial grade)	Includes multi-angle action/expression/scene/prop details
Single prompt word count	300-500 words	Includes action physics + frame-by-frame expressions + lighting + subtitle specs
Platform	Hongguo (default) + Douyin (secondary)	300 million MAU + traffic funnel
Genre	Interactive choice	Hongguo pure-satisfaction / premium suspense / comic-drama spectacle / silly light comedy / period satisfaction drama
Payment model	Interactive choice	Free (ads) / Paid (unlock)
ref image generation	dreamina text2image 4-grid (multi-angle)	Phase 1 stage 3.5
Video output	dreamina multimodal2video (with automatic visual fingerprint append)	Phase 2 stage 4.C
Pre-check before running video	Must run `python scripts/ref完备性检查.py`	Prevents missing ref → AI free generation → consistency breakdown

On every startup, ask the user whether to adjust these.

About AI advantages(user prompt, don't push hard but do point it out):

The real moat of AI-generated video = hard for live actionspectacles (cultivation / apocalypse / Journey to the West / fantasy / superpowers). If the user's subject is something like grandma awakening / urban wife-chasing, which iseasy for live action, tell the user: "Although AI can do it too, AI's real advantage is the comic-drama spectacle genre. Would you consider switching genres?" — give 1 prompt, the user decides.

Phase 1: Creation (5 stages + stage 3.5)

Stage 0: Market intelligence scan (4 substeps)

0.1 Search online for the current Top 5 drama titles

搜索 1：红果短剧 排行榜 <YYYY-MM>
搜索 2：番茄小说 改编 IP <近 30 天>
搜索 3：抖音短剧 <用户题材关键词> 热度
搜索 4：DataEye 短剧观察 / QuestMobile 月报
搜索 5：短剧 平台 审核 <当前年> 红线

0.2 Actually read industry breakdowns of 1-2 hit dramas (core)

WebFetch Plot commentary / industry breakdown articles for 1-2 hit dramas. Preferred sources: woshipm / 36Kr / Tencent News / 21 Economic Network.

If all 403 → fallback to built-in references/red-fruit-data.md。

0.3 Give the user a 3-option menu (do not output the report directly)

Let the user pick a differentiation angle.

0.4 Write to `01_市场情报.md`

See references/market-pulse.md。

Phase 1: IP positioning (5 substeps)

1.1 Genre selection (key)

5 options for the user to choose: A Hongguo pure-satisfaction style / B premium suspense style / C comic-drama spectacle style / D silly light-comedy style / E period satisfaction-drama style.

v0.1.2 new hint: add a note next to option C: "Hard to film with real people = AI advantage. If you plan to use AI to produce the film, C is the most cost-effective choice, because live-action crews for cultivation/doomsday/fantasy genres are extremely expensive, while AI can directly generate it." But do not push hard; let the user decide.

See references/genre-flavors.md。

1.2 Theme archetype (1 primary + 1 secondary)

See references/archetype-catalog.md。

1.3 Core hook (draft 3 versions for the user to choose)

1.4 Repeated satisfaction-point formula (draft 2 versions for the user to choose)

1.5 Write to `02_IP简报.md`

See references/ip-strategy.md。

Phase 2: Story architecture (4 substeps)

2.1 Three-act structure skeleton

2.2 Key reversal nodes (let the user choose)

2.3 72-episode outline (first give the key 25 episodes for the user to confirm)

2.4 Write `03_完整剧本.md` + `04_节奏地图.json`

See references/story-architecture.md。

Phase 3: Setting bible (4 substeps)

3.1 Character list (≤ 6 people)

3.2 5 close-up shots for personality anchoring

3.3 Visual motif + contrast points + costume list + Jimeng ref prompt

3.4 Write 3 bibles

05_角色圣经.md + 06_场景圣经.md + 07_道具圣经.md

See references/character-design.md。

Phase 3.5: Automatic ref image generation (new in v0.1.2, key)

This is the last step of Phase 1 and the prerequisite dependency for Phase 2。

3.5.1 Detect dreamina CLI

which dreamina && dreamina --version

If not installed → guide installation:

curl -fsSL https://jimeng.jianying.com/cli | bash

For detailed installation instructions, see references/jimeng-cli-guide.md。

3.5.2 Detect login status

dreamina user_credit

If not logged in → guide:dreamina login(browser authorization)

If balance is insufficient → prompt the user to top up (cannot continue)

3.5.3 Extract ref prompts

Read the "Jimeng character/scene/prop reference image generation package" section at the end of the 3 bibles, and extract all prompts:

N characters → N character refs (9:16 half-body portraits)
M scenes → M scene four-panel grids
K props → K prop three-view images

Estimated N+M+K images, each at 2k resolution about ¥0.5-1,total cost about ¥5-15。

3.5.4 Batch call dreamina text2image

Submit each image independently:

dreamina text2image \
  --prompt="<从 05_角色圣经.md 提取>" \
  --ratio=9:16 \
  --resolution_type=2k \
  --download_dir="<项目>/ref图/角色/" \
  --poll=60

Save to the project subdirectory:

SD-XXX_<拼音>/
├── ref图/
│   ├── 角色/
│   │   ├── 周翠英_ref.png
│   │   └── ...
│   ├── 场景/
│   │   └── scene_01_四宫格.png
│   └── 道具/
│       └── prop_01_三视图.png

Or use the project's built-in script:scripts/生成参考图.sh

3.5.5 Verify + user confirmation

After ref images are generatedthe user must take a look：

Are the character face shapes right?
Are the costume colors right?
Is the overall scene atmosphere right?

If not → modify prompt → rerun (low cost, about ¥1 per single-image rerun)

OK → mark 项目元数据.json 's ref_done = true, and proceed to Phase 5 critique.

Phase 5: Critical refine (4 substeps)

5.1 6-dimension self-evaluation + anti-cliché detection + platform review scan

5.2 If hit → must fix → patch in the original file → 09_修订记录.md

5.3 Major revision → auto-archive `归档/v1.X_<日期>/`

Phase 1 completion criteria：

6-dimension total score ≥ 50/60
anti-cliché first-level blacklist: 0 hits
all platform reviews passed
all ref images OK
user confirms "ready to produce"

See references/critic-checklist.md。

Phase 2: Production (unlocked per episode)

Preconditions: Phase 1 complete + ref images complete + user explicitly says "start production".

Each episode runs 4.A → 4.D independently.

Stage 4.A: Choose the episode to produce

Phase 1 已完成 ✅。准备进 Phase 2 按集出片。

成本提醒：每集 60 段视频，约 ¥X-XX（按当前 dreamina 单价计算）。

要先出哪一集？建议顺序：

1. 第 1 集（开篇，最关键，先出测试 ref 图效果是否符合预期）
2. 第 8 集（一卡 / 一爆，付费短剧首付费点）
3. 第 27 集（二卡）
4. 第 50 集（三卡 / 终极反转）
5. 第 72 集（结局）
6. ...

挑 1 集开始。出完该集，确认效果再决定下一集。

Default recommendation: produce Episode 1 first as a test to see how the ref images look in the video. If not good → go back to Stage 3.5 to revise ref → re-produce Episode 1. Once Episode 1 is OK, then produce the rest in batch.

Stage 4.B: Write the storyboard + script + Jimeng batch package for that episode

If the episode's 分集/第XX集_<集名>/ does not yet exist → write according to references/scripting-craft.md(script) + references/storyboard-frame-industrial.md(storyboard images, 8-segment prompts + ref process bias) + references/jimeng-failure-modes.md(sensitive words / character limit / concurrency throttling):

剧本.md
分镜.json（60 grid）
镜头清单.md
即梦批量包.md(60-segment prompts)

Stage 4.C: dreamina image2video automatic production

Read the 60-segment prompts in 分集/第XX集_<集名>/即梦批量包.md ,call segment by segment dreamina image2video：

dreamina image2video \
  --image="ref图/角色/周翠英_ref.png" \
  --prompt="<段 N 的 prompt>" \
  --duration=3 \
  --ratio=9:16 \
  --download_dir="分集/第XX集/视频段/" \
  --poll=60

Each segment takes about 5-15 seconds to generate (dreamina server-side queue). 60 segments take about 30-90 minutes.

Or use the project's built-in script:scripts/生成分集视频.sh <集编号>

Video segments are output to:

分集/第01集_<集名>/
├── 剧本.md
├── 分镜.json
├── 镜头清单.md
├── 即梦批量包.md
└── 视频段/
    ├── 段01.mp4
    ├── 段02.mp4
    ├── ...
    └── 段60.mp4

Stage 4.D: Jianying assembly (manual)

The skill does not call Jianying, but provides complete guidance:

Create a new 9:16 / 1080×1920 / 30fps project in Jianying
Import in order from segment 1-60
Transitions between segments: "Dissolve 0.3s" (use "White flash 0.2s" for hype segments)
Voiceover: Jianying TTS or real person
BGM: search the Jianying music library using keywords from 02_IP简报.md
Subtitles: subtitle all dialogue, font size 60, white text with black outline
AIGC label (mandatory for Hongguo 2026): 5s each at opening and closing
Output MP4 H.264 / 1080P

Phase 2 single-episode completion criteria

All 60 video segments complete
User has watched the rough cut in Jianying
User says "OK this episode is fine"
Mark 项目元数据.json 's episodes_video_done.append(集号)

Then go to 4.A to select the next episode.

⭐ v0.6.0 Visual Consistency SOP (required reading)

v0.6.0 update: the original v0.1.4 8-item SOP has been overturned by three rounds of SD-002 real-world testing / split into 3 industrial-grade documents. Beginners only need to read this section + the 3 references.

Storyboard image prompt process → references/storyboard-frame-industrial.md

8-segment template (CHARACTER/BACKGROUND/ACTION/SCENE/CAMERA/LIGHT/TEXT/STYLE)
1 protagonist ref + N silhouette multi-character SOP
Dramatic lighting vocabulary + Hongguo-grade first-frame 10-item checklist
ref library process bias (modern skyscrapers prone to objectification / ancient architecture must produce chibi human bodies)

ref image prompt process → references/ref-prompt-industrial.md

6-segment identity block (IDENTITY/BODY/FACE/ATTIRE/LAYOUT/STYLE)
Visual fingerprint placed at the beginning of the prompt, in the first 200 tokens
Objectified IP "IS the object NOT humanoid" must be added
4-view label watermark trap

Jimeng 5.0 troubleshooting + sensitive words → references/jimeng-failure-modes.md

Distinguish 3 types of fail: InvalidNode / generation failed / no image_url
prompt character hard limit: 1500 characters (under v0.6.0 measured conditions)
Villain words / ambiguous words / Chinese sensitive word replacement table
Long prompts must be run individually (do not run 4+ concurrently)

3 items of the old v0.1.4 SOP that have been overturned(must know):

❌ Old SOP "scripts automatically append visual fingerprint" → v0.6.0 uses --no-fingerprint to disable (ref style words will pollute the storyboard image's dramatic lighting)
❌ Old SOP "4 distinct angles" → only applies at the ref stage, do not write it into the storyboard image prompt
❌ Old SOP "after changing the prompt you must delete the old image and regenerate" → still holds, but the script will automatically skip ones that already exist; after changing the prompt you must manually delete the old file before running

See references/visual-consistency-sop.mdfor details (the old v0.1.4 document has been greatly slimmed down, keeping only the cost / workflow parts).

Project directory location rules (v0.1.2)

When the skill creates a short drama project,the project root directoryis determined in the following order:

User explicitly specifiesa path → use the specified path
The current cwd is a short drama workspace(contains aiForShortDrama / short-drama / 短剧 and other keywords, or already has a SD-XXX_*/ subdirectory) → create directly under cwd SD-XXX_<拼音>/
The current cwd is the user's home directory or a general workspace → default to recommending D:\hrdai\aiForShortDrama\SD-XXX_<拼音>/(the user's standard short drama workspace, already created on this machine)
None of the above → ask the user for the path, do not decide on your own

Default creation workspace：D:\hrdai\aiForShortDrama\

Every new short drama project goes under this directory, for easy centralized management + reuse of ref images / character assets.

Project file structure (v0.1.2)

D:\hrdai\aiForShortDrama\                       ← 用户标准短剧工作区
├── 即梦 CLI 体验指南.pdf                       ← 用户参考文档
├── README.md                                    ← 工作区 README
│
├── SD-001_<拼音>/                              ← 第 1 部短剧
│   ├── README.md                                ← 项目首页
│   ├── 项目元数据.json
│   │
│   ├── 01_市场情报.md
│   ├── 02_IP简报.md
│   ├── 03_完整剧本.md
│   ├── 04_节奏地图.json
│   ├── 05_角色圣经.md
│   ├── 06_场景圣经.md
│   ├── 07_道具圣经.md
│   │
│   ├── ref图/                                   ← 阶段 3.5
│   │   ├── 角色/
│   │   │   ├── <角色>_ref.png
│   │   │   └── ...
│   │   ├── 场景/scene_01_四宫格.png
│   │   └── 道具/prop_01_三视图.png
│   │
│   ├── 分集/                                    ← Phase 2 按集解锁
│   │   ├── 第01集_<集名>/
│   │   │   ├── 剧本.md
│   │   │   ├── 分镜.json
│   │   │   ├── 镜头清单.md
│   │   │   ├── 即梦批量包.md
│   │   │   └── 视频段/                          ← 阶段 4.C 产出
│   │   │       ├── 段01.mp4
│   │   │       └── ...
│   │   └── 第08集_<集名>/...
│   │
│   ├── 08_自我批判.md
│   ├── 09_修订记录.md
│   │
│   └── 归档/                                    ← 大改前 snapshot
│       └── v1.0_<日期>/
│
├── SD-002_<拼音>/                              ← 第 2 部短剧
│   └── ...
│
└── SD-003_<拼音>/                              ← 第 N 部

`项目元数据.json` key fields

{
  "project_id": "SD-001",
  "project_name": "<>",
  "skill_version": "v0.1.2",
  "version": "v1.0",
  "phase": "Phase1_创作 | Phase1_完成 | Phase2_出片 | 完成",
  "stage_progress": {
    "0_市场": "completed",
    "1_IP": "completed",
    "2_故事": "completed",
    "3_设定": "completed",
    "3.5_ref图": "completed",
    "5_批判": "completed",
    "Phase2": "in_progress"
  },
  "ref_done": true,
  "episodes_video_done": [1, 8],
  "next_action": "出第 27 集（二卡）"
}

Rules for interacting with the user

Split each stage into 3-5 substeps, and for each substep provide anoptions menufor the user to choose from (A/B/C), rather than giving a complete document for the user to read through
At the start of each session, proactively do a market intelligence scan + WebFetch to actually read hit shows
If the user's subject matter falls in a declining period / red ocean, honestly tell the user and offer alternative directions
If the user has not specified genre / episode count / paid, ask
AI production suggestion: if the user's subject matter falls within the range that is easy to shoot with real people (grandma / mother-in-law and daughter-in-law / chasing wife), give a one-time hint that "animated drama spectacle style is an AI advantage", but do not push it hard
Phase 1 → Phase 2 must have an explicit switch confirmation: only when the user says "start production" can you enter Phase 2
Phase 2 must be unlocked episode by episode, you cannot produce multiple episodes at once
Automatically archive before every major change

dreamina CLI integration

See references/jimeng-cli-guide.md. Key points:

Installation:curl -fsSL https://jimeng.jianying.com/cli | bash（Mac/Linux/Windows Git Bash）
Login:dreamina login(browser authorization)
Check balance:dreamina user_credit
Text-to-image:dreamina text2image --prompt=... --ratio=9:16 --resolution_type=2k --poll=60
Image-to-video:dreamina image2video --image=... --prompt=... --duration=3 --poll=60
Async query:dreamina query_result --submit_id=<ID>

The skill directly calls the dreamina command through the Bash tool, no API key management needed.

Startup command

The user may trigger it like this:

"Make a ... short drama"
"Help me write a ... themed hit drama"
"I have an idea: ..."
"Adapt ... this novel into a short drama"

Response template for the first sentence after startup:

收到。本技能 2 阶段架构：

Phase 1 创作（成本低，反复迭代）
  - 市场情报 + IP 简报 + 故事架构 + 设定圣经 + ref 图自动生成 + 批判
  - dreamina text2image 生 ref 图，成本约 ¥5-15

Phase 2 出片（成本高，按集解锁）
  - dreamina image2video 单集 60 段，按集生成

先 Phase 1，跟你 5 阶段互动确认。3 个最关键问题：

1. 流派：A 红果纯爽 / B 精品悬疑 / C 漫剧奇观（AI 优势）/ D 沙雕轻喜 / E 年代爽剧
2. 集数：默认 70，要改吗？
3. 付费：免费（广告）/ 付费（解锁，第 8 集首付费）

回答后启动阶段 0。

Final delivery

When Phase 1 is completed, provide a "creation completion checklist":

✅ 《XXX》Phase 1 创作完成

📋 IP 信息
- 流派、集数、平台、对标、钩子、爽点公式

📊 创作产出
- 9 个编号文件（市场情报 → 自我批判）
- N 张 ref 图（角色 / 场景 / 道具）
- 72 集大纲 + 节奏地图

🎬 下一步
准备进 Phase 2？告诉我先出哪一集（建议第 1 集试水）。

At the completion of each episode in Phase 2, provide an "episode production completion checklist".

About this skill

v0.6.0 changelog（2026-05-16）

Key Upgrades

Biggest Lesson

v0.3.0 changelog（2026-05-08）

Key Upgrades

Document Added

Script added / modified

v0.2.0 changelog（2026-05-08）

Key fixes

Rhythm upgrade

Asset standard upgrade

Docs

Core architecture: 2 Phase

Trigger conditions

Default parameters (v0.6.0)

Stage 0: Market intelligence scan (4 substeps)

0.1 Search online for the current Top 5 drama titles

0.2 Actually read industry breakdowns of 1-2 hit dramas (core)

0.3 Give the user a 3-option menu (do not output the report directly)

0.4 Write to 01_市场情报.md

Phase 1: IP positioning (5 substeps)

1.1 Genre selection (key)

1.2 Theme archetype (1 primary + 1 secondary)

1.3 Core hook (draft 3 versions for the user to choose)

1.4 Repeated satisfaction-point formula (draft 2 versions for the user to choose)

1.5 Write to 02_IP简报.md

Phase 2: Story architecture (4 substeps)

2.1 Three-act structure skeleton

2.2 Key reversal nodes (let the user choose)

2.3 72-episode outline (first give the key 25 episodes for the user to confirm)

2.4 Write 03_完整剧本.md + 04_节奏地图.json

Phase 3: Setting bible (4 substeps)

3.1 Character list (≤ 6 people)

3.2 5 close-up shots for personality anchoring

3.3 Visual motif + contrast points + costume list + Jimeng ref prompt

3.4 Write 3 bibles

Phase 3.5: Automatic ref image generation (new in v0.1.2, key)

3.5.1 Detect dreamina CLI

3.5.2 Detect login status

3.5.3 Extract ref prompts

3.5.4 Batch call dreamina text2image

3.5.5 Verify + user confirmation

Phase 5: Critical refine (4 substeps)

5.1 6-dimension self-evaluation + anti-cliché detection + platform review scan

5.2 If hit → must fix → patch in the original file → 09_修订记录.md

5.3 Major revision → auto-archive 归档/v1.X_<日期>/

Stage 4.A: Choose the episode to produce

Stage 4.B: Write the storyboard + script + Jimeng batch package for that episode

Stage 4.C: dreamina image2video automatic production

Stage 4.D: Jianying assembly (manual)

Phase 2 single-episode completion criteria

⭐ v0.6.0 Visual Consistency SOP (required reading)

Project directory location rules (v0.1.2)

Project file structure (v0.1.2)

项目元数据.json key fields

Rules for interacting with the user

dreamina CLI integration

Startup command

Final delivery

0.4 Write to `01_市场情报.md`

1.5 Write to `02_IP简报.md`

2.4 Write `03_完整剧本.md` + `04_节奏地图.json`

5.3 Major revision → auto-archive `归档/v1.X_<日期>/`

`项目元数据.json` key fields