Not in the top 1,000 by GitHub stars
A-cat-with-carrots/OnlyShot
OnlyShot · 神仙鱼 AI 短剧工业流水线 Claude Skill — 一句话 → 剧本/分镜/分镜图/视频/剪辑 五步 → 可发红果抖音的完整短剧。集成即梦/Seedance，17 失败模式沉淀。
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
75c57f2fff6e → 75c57f2fff6e
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 75c57f2fff6e
No earlier version was observed for comparison.
381GitHub stars
36stars in 7 days
1skill in this repository
0commits in 30 days
Heat
6.7- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
How it works
ai-short-drama
When your agent uses it
精细化 AI 短剧 IP 创作技能（v0.6.0）。三阶段架构：Phase 1 创作（剧本+ref图，反复迭代）→ Phase 1.5 分镜图（每 grid 1-4 张候选静态图 = 视频首帧，工业级核心层）→ Phase 2 出片（按集解锁，4 模自动选）。v0.6.0 关键升级：① ref 库工艺偏置铁律（现代摩天楼易拟物，古建筑必出 chibi 人体，前期 IP 设计阶段就要避坑）② 即梦 5.0 失败模式 + 敏感词清单（3 类 fail 区分 / prompt 1500 字硬上限 / 反派词替换表 / 暧昧词清单）③ 分镜图 8 段 prompt 模板（CHARACTER/BACKGROUND/ACTION/SCENE/CAMERA/LIGHT/TEXT/STYLE）+ NOT humans 子句必加。沿用 v0.3.0 升级：Phase 1.5 分镜图层、4 模视频、ref 5-8 最优。v0.2.0：bash → Python subprocess、36 grid × 4-10s 变奏、红果必爆 7 招、工业级 ref 库 80-150 张、单 prompt 300-500 字。务必触发：用户提到短剧、微短剧、竖屏剧、AI 短剧、AI 漫剧、剧本创作、分镜、即梦/Seedance 出片、红果/番茄/抖音 IP 改编、爽剧、重生、穿越、赘婿、追妻、神医相师、AI 漫剧奇观、或"帮我做一部短剧"类请求。
What it loads into context
Frontmatter
430 tokensAlways available to the agent
SKILL.md
8,674 tokensWhen the skill is activated
Reference documents
82,368 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- v0.6.0 changelog（2026-05-16）
- v0.3.0 changelog（2026-05-08）
- v0.2.0 changelog（2026-05-08）
- 核心架构：2 Phase
- 触发条件
- 默认参数（v0.6.0）
- 阶段 0：市场情报扫描（4 子步）
- 阶段 1：IP 定位（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（v0.1.2 新增，关键）
- 阶段 5：批判 refine（4 子步）
- 阶段 4.A：选要出片的集
- 阶段 4.B：写该集分镜 + 剧本 + 即梦批量包
- 阶段 4.C：dreamina image2video 自动出片
- 阶段 4.D：剪映拼接（手动）
- Phase 2 单集完成判定
- ⭐ v0.6.0 视觉一致性 SOP（必读）
- 项目目录位置规则（v0.1.2）
- 项目文件结构（v0.1.2）
- 与用户交互的规矩
- dreamina CLI 集成
- 启动指令
- 收尾交付
Scripts executed separately
scripts/extract_prompts.pyscripts/ref完备性检查.pyscripts/setup-jimeng.shscripts/派生分集文件.pyscripts/生成分镜图.pyscripts/生成分集视频.pyscripts/生成分集视频.shscripts/生成参考图.sh
Files
.gitignoreasset315 bytesLICENSEasset1,062 bytesREADME.mddoc24,204 bytesSKILL.mdcore26,870 bytesSKILL.mdcore26,870 bytesSKILL.mdcore26,870 bytesSKILL.mdcore26,870 bytesSKILL.mdcore26,870 bytesSKILL.mdcore26,870 bytesSKILL.mdcore26,870 bytesSKILL.mdcore26,870 bytesSKILL.mdcore26,870 bytesassets/templates/01_市场情报.mddoc1,562 bytesassets/templates/02_IP简报.mddoc2,751 bytesassets/templates/03_完整剧本.mddoc2,789 bytesassets/templates/05_角色圣经.mddoc3,257 bytesassets/templates/06_场景圣经.mddoc1,604 bytesassets/templates/07_道具圣经.mddoc1,450 bytesassets/templates/08_自我批判.mddoc4,137 bytesassets/templates/09_修订记录.mddoc797 bytesassets/templates/README.mddoc4,571 bytesassets/templates/分镜.jsonasset4,011 bytesassets/templates/剧本.mddoc2,299 bytesassets/templates/即梦批量包.mddoc2,334 bytesassets/templates/镜头清单.mddoc1,991 bytesassets/templates/项目元数据.jsonasset1,724 bytesevals/evals.jsonasset4,405 bytesreferences/archetype-catalog.mddoc8,874 bytesreferences/character-design.mddoc6,766 bytesreferences/cliche-detector.mddoc5,452 bytesreferences/critic-checklist.mddoc6,747 bytesreferences/genre-flavors.mddoc18,407 bytesreferences/ip-strategy.mddoc5,935 bytesreferences/jimeng-cli-guide.mddoc11,379 bytesreferences/jimeng-failure-modes.mddoc13,122 bytesreferences/jimeng-handoff.mddoc5,834 bytesreferences/market-pulse.mddoc5,296 bytesreferences/red-fruit-data.mddoc8,355 bytesreferences/ref-prompt-industrial.mddoc11,460 bytesreferences/schemas.mddoc6,330 bytesreferences/scripting-craft.mddoc4,237 bytesreferences/story-architecture.mddoc6,537 bytesreferences/storyboard-craft.mddoc9,380 bytesreferences/storyboard-frame-industrial.mddoc24,924 bytesreferences/storyboard-frames-craft.mddoc9,286 bytesreferences/troubleshooting.mddoc7,724 bytesreferences/v21-97-percent-rules.mddoc8,496 bytesreferences/visual-consistency-sop.mddoc8,259 bytesscripts/extract_prompts.pyruns3,340 bytesscripts/ref完备性检查.pyruns4,761 bytesscripts/setup-jimeng.shruns2,560 bytesscripts/派生分集文件.pyruns3,539 bytesscripts/生成分镜图.pyruns10,891 bytesscripts/生成分集视频.pyruns14,296 bytesscripts/生成分集视频.shruns8,640 bytesscripts/生成参考图.shruns6,838 bytes
Read SKILL.md
# AI 短剧精细化 IP 创作 v0.6.0
## v0.6.0 changelog（2026-05-16）
> SD-002《城市恋综》EP01 36 grid × 3 轮（v2.5/v2.6/v2.7）跑 + 全审反推。从「16/36 灾难级一致性破损」修到「0 灾难 / 60% ≥4 分」+ 沉淀 2 个工业级 SOP。
### 关键升级
- ⭐ **`references/storyboard-frame-industrial.md`** v0.3.0：分镜图工艺 SOP
- 8 段 prompt 模板（CHARACTER/BACKGROUND/ACTION/SCENE/CAMERA/LIGHT/TEXT/STYLE）
- **NOT humans 子句必加**：每个主角单独 `Xxx body IS [arch] architecture NOT a human wearing X NOT a human with headpiece`
- **ref 库工艺偏置铁律**：现代摩天楼易拟物 / 古建筑必出 chibi 人体
- 多角色 SOP：1 主角 ref + N 文字 silhouette + bokeh blur
- 戏剧光词库（25+ 关键词）+ 红果级首帧 10 条 checklistSkills included
- ai-short-drama
Repository facts
- License
- MIT
- Created
- May 5, 2026
- Last pushed
- Jul 7, 2026
- Forks
- 38
- Open issues
- 2
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 8 notes
SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedSKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 8 dangerous shell commandsin 5 files: SKILL.md:291 references/jimeng-cli-guide.md:51 scripts/setup-jimeng.sh:27 and 2 more
- 28 network referencesin 6 files: README.md:6 references/jimeng-cli-guide.md:91 scripts/setup-jimeng.sh:14 and 3 more
- No hidden or obfuscated text
- No instruction overrides
- 8 executable scriptsin 8 files: scripts/extract_prompts.py:1 scripts/ref完备性检查.py:1 scripts/setup-jimeng.sh:1 and 5 more
- 2 references to secretsin 1 file: .gitignore:27
- No requests to vote in Hot
Show all 46 signals by file
.gitignore
README.md
- Network accessline 6
[](https://docs.anthropic.com/en/docs/claude-code) - Network accessline 7
[](LICENSE) - Network accessline 8
[]() - Network accessline 9
[]() - Network accessline 73
# Windows git clone https://github.com/A-cat-with-carrots/OnlyShot-ai-short-drama-skill "$env:USERPROFILE\.claude\skills\ai-short-drama" - Network accessline 74
git clone https://github.com/A-cat-with-carrots/OnlyShot-ai-short-drama-skill "$env:USERPROFILE\.claude\skills\ai-short-drama" - Network accessline 76
# macOS / Linux git clone https://github.com/A-cat-with-carrots/OnlyShot-ai-short-drama-skill ~/.claude/skills/ai-short-drama - Network accessline 77
git clone https://github.com/A-cat-with-carrots/OnlyShot-ai-short-drama-skill ~/.claude/skills/ai-short-drama - Network accessline 83
cd <your-project> mkdir -p .claude/skills git clone https://github.com/A-cat-with-carrots/OnlyShot-ai-short-drama-skill .claude/skills/ai-short-drama - Network accessline 85
git clone https://github.com/A-cat-with-carrots/OnlyShot-ai-short-drama-skill .claude/skills/ai-short-drama - Dangerous shell operationline 93
curl -fsSL https://jimeng.jianying.com/cli | bash - Network accessline 93
curl -fsSL https://jimeng.jianying.com/cli | bash - Network accessline 454
- 原始灵感：[zhaihao118/Micro-Drama-Skills](https://github.com/zhaihao118/Micro-Drama-Skills)
SKILL.md
- Dangerous shell operationline 291
curl -fsSL https://jimeng.jianying.com/cli | bash - Network accessline 291
curl -fsSL https://jimeng.jianying.com/cli | bash - Dangerous shell operationline 608
- 安装：`curl -fsSL https://jimeng.jianying.com/cli | bash`（Mac/Linux/Windows Git Bash） - Network accessline 608
- 安装：`curl -fsSL https://jimeng.jianying.com/cli | bash`（Mac/Linux/Windows Git Bash）
assets/templates/README.md
- Network accessline 3
> AI 短剧 IP — 由 [`ai-short-drama` skill v0.1.2](https://github.com/A-cat-with-carrots/ai-short-drama-skill) 创作
references/jimeng-cli-guide.md
- Dangerous shell operationline 51
bash `eval "dreamina multimodal2video --prompt='$full_prompt'"` 在 prompt 含中文 `「」`、`(@xxx_ref.png)`、`@`、半全角混合 字符时 **quoting 解析错误** → dreamina CLI 收到 malformed prompt → server 创建 task entry 但**不实际处理**： - Dangerous shell operationline 91
curl -fsSL https://jimeng.jianying.com/cli | bash - Network accessline 91
curl -fsSL https://jimeng.jianying.com/cli | bash - Network accessline 103
1. 装 Git for Windows：https://git-scm.com/download/win - Network accessline 336
| 提示余额不足 | 充值，或换免费配额账号 | | 角色脸跳 | 改 `image2video` 的 `--image` 用更高质量 ref，prompt 加「保持参考图一致」3 次 | | Windows curl 报错 | 用 Git Bash，不要用 PowerShell | - Network accessline 337
| 角色脸跳 | 改 `image2video` 的 `--image` 用更高质量 ref，prompt 加「保持参考图一致」3 次 | | Windows curl 报错 | 用 Git Bash，不要用 PowerShell | | Mac M 系列芯片报错 | 装最新版（v1.3.4 起 arm64 原生支持）| - Network accessline 338
| Windows curl 报错 | 用 Git Bash，不要用 PowerShell |
references/troubleshooting.md
- Dangerous shell operationline 16
bash `eval "dreamina multimodal2video --prompt='$full_prompt'"` 在 prompt 含中文 `「」`、`(@xxx_ref.png)`、`@`、半全角混合 字符时 quoting 解析错误。dreamina CLI 收到 malformed prompt，server 创建 task entry 但不实际处理。
scripts/extract_prompts.py
- Executable scriptline 1
#!/usr/bin/env python3
scripts/ref完备性检查.py
- Executable scriptline 1
Executable file
scripts/setup-jimeng.sh
- Executable scriptline 1
#!/usr/bin/env bash - Network accessline 14
if ! command -v curl &> /dev/null; then - Network accessline 15
echo "❌ curl 未安装。Mac/Linux 请装 curl，Windows 请确保使用 Git Bash。" - Network accessline 25
echo "⏳ dreamina CLI 未安装，开始安装..." echo "" curl -fsSL https://jimeng.jianying.com/cli | bash - Network accessline 26
echo "" curl -fsSL https://jimeng.jianying.com/cli | bash echo "" - Dangerous shell operationline 27
curl -fsSL https://jimeng.jianying.com/cli | bash - Network accessline 27
curl -fsSL https://jimeng.jianying.com/cli | bash - Dangerous shell operationline 50
rm -f /tmp/dreamina_credit_check.json
scripts/派生分集文件.py
- Executable scriptline 1
Executable file
scripts/生成分镜图.py
- Executable scriptline 1
Executable file - Network accessline 123
target.parent.mkdir(parents=True, exist_ok=True) try: urllib.request.urlretrieve(url, target) - Network accessline 124
try: urllib.request.urlretrieve(url, target) return target.stat().st_size - Network accessline 125
urllib.request.urlretrieve(url, target)
scripts/生成分集视频.py
- Executable scriptline 1
Executable file
scripts/生成分集视频.sh
- Executable scriptline 1
#!/usr/bin/env bash
scripts/生成参考图.sh
- Executable scriptline 1
#!/usr/bin/env bash
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Combined signals: 2 facts
- Passes content downloaded from jimeng.jianying.com to an interpreterSKILL.md:291High confidence
- Passes content downloaded from jimeng.jianying.com to an interpreterscripts/setup-jimeng.sh:27High confidence
Signal confidence: 44 facts
- Network access in prose of documentationREADME.md:6Low confidence
- Network access in prose of documentationREADME.md:7Low confidence
- Network access in prose of documentationREADME.md:8Low confidence
- Network access in prose of documentationREADME.md:9Low confidence
- Network access in code of documentationREADME.md:73Low confidence
- Network access in code of documentationREADME.md:74Low confidence
- Network access in code of documentationREADME.md:76Low confidence
- Network access in code of documentationREADME.md:77Low confidence
- Network access in code of documentationREADME.md:83Low confidence
- Network access in code of documentationREADME.md:85Low confidence
- Dangerous shell operation in code of documentationREADME.md:93Low confidence
- Network access in code of documentationREADME.md:93Low confidence
- Network access in prose of documentationREADME.md:454Low confidence
- Dangerous shell operation in code of the SKILL.mdSKILL.md:291High confidence
- Network access in code of the SKILL.mdSKILL.md:291High confidence
- Dangerous shell operation in prose of the SKILL.mdSKILL.md:608Low confidence
- Network access in prose of the SKILL.mdSKILL.md:608Low confidence
- Network access in prose of documentationassets/templates/README.md:3Low confidence
- Dangerous shell operation in prose of documentationreferences/jimeng-cli-guide.md:51Low confidence
- Dangerous shell operation in code of documentationreferences/jimeng-cli-guide.md:91Low confidence
- Network access in code of documentationreferences/jimeng-cli-guide.md:91Low confidence
- Network access in prose of documentationreferences/jimeng-cli-guide.md:103Low confidence
- Network access in prose of documentationreferences/jimeng-cli-guide.md:336Low confidence
- Network access in prose of documentationreferences/jimeng-cli-guide.md:337Low confidence
- Network access in prose of documentationreferences/jimeng-cli-guide.md:338Low confidence
- Dangerous shell operation in prose of documentationreferences/troubleshooting.md:16Low confidence
- Executable script in code of a file that runsscripts/extract_prompts.py:1High confidence
- Executable script in prose of a file that runsscripts/ref完备性检查.py:1Low confidence
- Executable script in code of a file that runsscripts/setup-jimeng.sh:1High confidence
- Network access in code of a file that runsscripts/setup-jimeng.sh:14High confidence
- Network access in code of a file that runsscripts/setup-jimeng.sh:15High confidence
- Network access in code of a file that runsscripts/setup-jimeng.sh:25High confidence
- Network access in code of a file that runsscripts/setup-jimeng.sh:26High confidence
- Dangerous shell operation in code of a file that runsscripts/setup-jimeng.sh:27High confidence
- Network access in code of a file that runsscripts/setup-jimeng.sh:27High confidence
- Dangerous shell operation in code of a file that runsscripts/setup-jimeng.sh:50High confidence
- Executable script in prose of a file that runsscripts/派生分集文件.py:1Low confidence
- Executable script in prose of a file that runsscripts/生成分镜图.py:1Low confidence
- Network access in code of a file that runsscripts/生成分镜图.py:123High confidence
- Network access in code of a file that runsscripts/生成分镜图.py:124High confidence
- Network access in code of a file that runsscripts/生成分镜图.py:125High confidence
- Executable script in prose of a file that runsscripts/生成分集视频.py:1Low confidence
- Executable script in code of a file that runsscripts/生成分集视频.sh:1High confidence
- Executable script in code of a file that runsscripts/生成参考图.sh:1High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
