grid-image-generator
- Repo stars 12,584
- Author updated Live
- Author repo huobao-drama
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @chatfire-AI · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: grid-image-generator
description: 本 SKILL 对应 gridpromptgenerator Agent，支持生成三类图片提示词： 详细模板见 reference/ 目录。 参考：reference/character-pr…
category: ai
runtime: no special runtime
---
# grid-image-generator output preview
## PART A: Task fit
- Use case: 本 SKILL 对应 gridpromptgenerator Agent，支持生成三类图片提示词： 详细模板见 reference/ 目录。 参考：reference/character-prompt.md [appearance], [personality/temperament], [role], [cinematic portrait], [high quality], [consistent art style], [no text, no watermark] runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “角色图片提示词 / 模板结构 / 生成规则” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “本 SKILL 对应 gridpromptgenerator Agent，支持生成三类图片提示词： 详细模板见 reference/ 目录。 参考：reference/character-prompt.md [appearance], [personality/temperament], [role], [cinematic portrait], [high quality], [consistent art style], [no text, no watermark] runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “角色图片提示词 / 模板结构 / 生成规则” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “角色图片提示词 / 模板结构 / 生成规则”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: grid-image-generator
description: 本 SKILL 对应 gridpromptgenerator Agent，支持生成三类图片提示词： 详细模板见 reference/ 目录。 参考：reference/character-pr…
category: ai
source: chatfire-AI/huobao-drama
---
# grid-image-generator
## When to use
- 本 SKILL 对应 gridpromptgenerator Agent，支持生成三类图片提示词： 详细模板见 reference/ 目录。 参考：reference/character-prompt.md [appearance]…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “角色图片提示词 / 模板结构 / 生成规则” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "grid-image-generator" {
input -> user goal + target files + boundaries + acceptance criteria
context -> 角色图片提示词 / 模板结构 / 生成规则
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}图片提示词生成指南
本 SKILL 对应 grid_prompt_generator Agent，支持生成三类图片提示词：
- 角色图片提示词 — 角色外貌与气质
- 场景图片提示词 — 场景氛围与光线
- 宫格图提示词 — 多镜头网格拼图
详细模板见 reference/ 目录。
角色图片提示词
参考：reference/character-prompt.md
模板结构
[appearance], [personality/temperament], [role], [cinematic portrait], [high quality], [consistent art style], [no text, no watermark]生成规则
- 以
appearance（外貌描述）为核心 personality决定气质基调（内敛/张扬/神秘等）role决定服装和道具风格- 必须包含
cinematic portrait+consistent art style - 避免出现文字、签名、水印
场景图片提示词
参考：reference/scene-prompt.md
模板结构
[location], [time period], [lighting atmosphere], [scene description], [cinematic scene], [high quality], [consistent art style], [no text, no watermark]生成规则
- 以
location（地点）为基础 time决定光线色调（白天/夜晚/黄昏）- 场景氛围词：atmospheric, moody, warm, cold 等
- 必须包含
cinematic scene+consistent art style - 避免出现文字、签名、水印
宫格图提示词
参考：reference/shot-prompt.md
三种模式
首帧模式 (first_frame)
每个格子 = 一个镜头的起始画面，但必须严格生成用户指定的 rows x cols 总格数。
[rows x cols grid layout], exactly [rows*cols] visible panels, consistent art style, [style description],
格1: [shot 1 opening scene],
格2: [shot 2 opening scene],
格3: [shot 3 opening scene],
...
格N: [opening scene],
high quality, cinematic lighting, no merged panels, no missing panels, no text, no watermark首尾帧模式 (first_last)
保持首尾帧节奏感，但仍然必须严格生成用户指定的 rows x cols 总格数，不允许偷偷改成 Nx2。
[rows x cols grid layout], exactly [rows*cols] visible panels, consistent art style, [style description],
格1: [opening beat],
格2: [closing beat],
格3: [opening beat],
格4: [closing beat],
...
high quality, cinematic, continuous motion implied, no merged panels, no missing panels, no text多参考模式 (multi_ref)
所有格子都是同一镜头的不同角度/构图参考，但仍然必须严格生成用户指定的 rows x cols 总格数。
[rows x cols grid layout], exactly [rows*cols] visible panels, same scene different angles, [style description],
[main scene description],
格1: wide shot establishing,
格2: medium shot character focus,
格3: close-up detail,
格4: dramatic angle,
...
consistent lighting and color palette, no merged panels, no missing panels, no text通用规则
- 提示词使用英文
- 必须明确写出用户指定的
rows x cols grid layout - 必须包含
consistent art style保持风格统一 - 必须明确要求
exactly N visible panels - 必须明确要求
no merged panels, no missing panels - 避免在格子间出现分割线的描述
- 尺寸建议：每格 960x540，总图 = 960×cols × 540×rows
- 当存在参考图映射时，统一使用
图片1/图片2/...指代参考图，不要把它和格1/格2/...混用
Decide Fit First
Design Intent
How To Use It
Boundaries And Review