docs: add contributor credit to v1.59.0 changelog

EXTEND.md default_provider still takes priority over auto-detect.
Priority: CLI --provider > EXTEND.md default_provider > auto-detect (Google first).

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
   },
   "metadata": {
     "description": "Skills shared by Baoyu for improving daily work efficiency",
-    "version": "1.58.0"
+    "version": "1.59.0"
   },
   "plugins": [
     {

CHANGELOG.md

@@ -2,6 +2,17 @@
 
 English | [中文](./CHANGELOG.zh.md)
 
+## 1.59.0 - 2026-03-09
+
+### Features
+- `baoyu-image-gen`: add batch parallel image generation and provider-level throttling (by @SeamoonAO)
+
+### Fixes
+- `baoyu-image-gen`: restore Google as default provider when multiple keys available
+
+### Documentation
+- Improve skill documentation clarity (by @SeamoonAO)
+
 ## 1.58.0 - 2026-03-08
 
 ### Features

CHANGELOG.zh.md

@@ -2,6 +2,17 @@
 
 [English](./CHANGELOG.md) | 中文
 
+## 1.59.0 - 2026-03-09
+
+### 新功能
+- `baoyu-image-gen`：新增批量并行图片生成和提供商级别限流 (by @SeamoonAO)
+
+### 修复
+- `baoyu-image-gen`：修复多个 API key 可用时恢复 Google 为默认提供商
+
+### 文档
+- 改进技能文档清晰度 (by @SeamoonAO)
+
 ## 1.58.0 - 2026-03-08
 
 ### 新功能

skills/baoyu-article-illustrator/SKILL.md

@@ -118,6 +118,8 @@ Full template: [references/workflow.md](references/workflow.md#step-4-generate-o
 
 ⛔ **BLOCKING: Prompt files MUST be saved before ANY image generation.**
 
+**Execution strategy**: When multiple illustrations have saved prompt files and the task is now plain generation, prefer `baoyu-image-gen` batch mode (`build-batch.ts` → `--batchfile`) over spawning subagents. Use subagents only when each image still needs separate prompt iteration or creative exploration.
+
 1. For each illustration, create a prompt file per [references/prompt-construction.md](references/prompt-construction.md)
 2. Save to `prompts/NN-{type}-{slug}.md` with YAML frontmatter
 3. Prompts **MUST** use type-specific templates with structured sections (ZONES / LABELS / COLORS / STYLE / ASPECT)

skills/baoyu-article-illustrator/references/workflow.md

@@ -315,6 +315,10 @@ Prompt Files:
 
 **DO NOT** pass ad-hoc inline text to `--prompt` without first saving prompt files. The generation command should either use `--promptfiles prompts/NN-{type}-{slug}.md` or read the saved file content for `--prompt`.
 
+**Execution choice**:
+- If multiple illustrations already have saved prompt files and the task is now plain generation, prefer `baoyu-image-gen` batch mode (`build-batch.ts` -> `main.ts --batchfile`)
+- Use subagents only when each illustration still needs separate prompt rewriting, style exploration, or other per-image reasoning before generation
+
 **CRITICAL - References in Frontmatter**:
 - Only add `references` field if files ACTUALLY EXIST in `references/` directory
 - If style/palette was extracted verbally (no file), append info to prompt BODY instead

skills/baoyu-article-illustrator/scripts/build-batch.ts

@@ -0,0 +1,156 @@
+import path from "node:path";
+import process from "node:process";
+import { readdir, readFile, writeFile } from "node:fs/promises";
+
+type CliArgs = {
+  outlinePath: string | null;
+  promptsDir: string | null;
+  outputPath: string | null;
+  imagesDir: string | null;
+  provider: string;
+  model: string;
+  aspectRatio: string;
+  quality: string;
+  jobs: number | null;
+  help: boolean;
+};
+
+type OutlineEntry = {
+  index: number;
+  filename: string;
+};
+
+function printUsage(): void {
+  console.log(`Usage:
+  npx -y tsx scripts/build-batch.ts --outline outline.md --prompts prompts --output batch.json --images-dir attachments
+
+Options:
+  --outline <path>     Path to outline.md
+  --prompts <path>     Path to prompts directory
+  --output <path>      Path to output batch.json
+  --images-dir <path>  Directory for generated images
+  --provider <name>    Provider for baoyu-image-gen batch tasks (default: replicate)
+  --model <id>         Model for baoyu-image-gen batch tasks (default: google/nano-banana-pro)
+  --ar <ratio>         Aspect ratio for all tasks (default: 16:9)
+  --quality <level>    Quality for all tasks (default: 2k)
+  --jobs <count>       Recommended worker count metadata (optional)
+  -h, --help           Show help`);
+}
+
+function parseArgs(argv: string[]): CliArgs {
+  const args: CliArgs = {
+    outlinePath: null,
+    promptsDir: null,
+    outputPath: null,
+    imagesDir: null,
+    provider: "replicate",
+    model: "google/nano-banana-pro",
+    aspectRatio: "16:9",
+    quality: "2k",
+    jobs: null,
+    help: false,
+  };
+
+  for (let i = 0; i < argv.length; i++) {
+    const current = argv[i]!;
+    if (current === "--outline") args.outlinePath = argv[++i] ?? null;
+    else if (current === "--prompts") args.promptsDir = argv[++i] ?? null;
+    else if (current === "--output") args.outputPath = argv[++i] ?? null;
+    else if (current === "--images-dir") args.imagesDir = argv[++i] ?? null;
+    else if (current === "--provider") args.provider = argv[++i] ?? args.provider;
+    else if (current === "--model") args.model = argv[++i] ?? args.model;
+    else if (current === "--ar") args.aspectRatio = argv[++i] ?? args.aspectRatio;
+    else if (current === "--quality") args.quality = argv[++i] ?? args.quality;
+    else if (current === "--jobs") {
+      const value = argv[++i];
+      args.jobs = value ? parseInt(value, 10) : null;
+    } else if (current === "--help" || current === "-h") {
+      args.help = true;
+    }
+  }
+  return args;
+}
+
+function parseOutline(content: string): OutlineEntry[] {
+  const entries: OutlineEntry[] = [];
+  const blocks = content.split(/^## Illustration\s+/m).slice(1);
+
+  for (const block of blocks) {
+    const indexMatch = block.match(/^(\d+)/);
+    const filenameMatch = block.match(/\*\*Filename\*\*:\s*(.+)/);
+    if (indexMatch && filenameMatch) {
+      entries.push({
+        index: parseInt(indexMatch[1]!, 10),
+        filename: filenameMatch[1]!.trim(),
+      });
+    }
+  }
+  return entries;
+}
+
+async function findPromptFile(promptsDir: string, entry: OutlineEntry): Promise<string | null> {
+  const files = await readdir(promptsDir);
+  const prefix = String(entry.index).padStart(2, "0");
+  const match = files.find((f) => f.startsWith(prefix) && f.endsWith(".md"));
+  return match ? path.join(promptsDir, match) : null;
+}
+
+async function main(): Promise<void> {
+  const args = parseArgs(process.argv.slice(2));
+  if (args.help) {
+    printUsage();
+    return;
+  }
+
+  if (!args.outlinePath) {
+    console.error("Error: --outline is required");
+    process.exit(1);
+  }
+  if (!args.promptsDir) {
+    console.error("Error: --prompts is required");
+    process.exit(1);
+  }
+  if (!args.outputPath) {
+    console.error("Error: --output is required");
+    process.exit(1);
+  }
+
+  const outlineContent = await readFile(args.outlinePath, "utf8");
+  const entries = parseOutline(outlineContent);
+
+  if (entries.length === 0) {
+    console.error("No illustration entries found in outline.");
+    process.exit(1);
+  }
+
+  const tasks = [];
+  for (const entry of entries) {
+    const promptFile = await findPromptFile(args.promptsDir, entry);
+    if (!promptFile) {
+      console.error(`Warning: No prompt file found for illustration ${entry.index}, skipping.`);
+      continue;
+    }
+
+    const imageDir = args.imagesDir ?? path.dirname(args.outputPath);
+    tasks.push({
+      id: `illustration-${String(entry.index).padStart(2, "0")}`,
+      promptFiles: [promptFile],
+      image: path.join(imageDir, entry.filename),
+      provider: args.provider,
+      model: args.model,
+      ar: args.aspectRatio,
+      quality: args.quality,
+    });
+  }
+
+  const output: Record<string, unknown> = { tasks };
+  if (args.jobs) output.jobs = args.jobs;
+
+  await writeFile(args.outputPath, JSON.stringify(output, null, 2) + "\n");
+  console.log(`Batch file written: ${args.outputPath} (${tasks.length} tasks)`);
+}
+
+main().catch((error) => {
+  console.error(error instanceof Error ? error.message : String(error));
+  process.exit(1);
+});

skills/baoyu-image-gen/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: baoyu-image-gen
-description: AI image generation with OpenAI, Google, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.
+description: AI image generation with OpenAI, Google, DashScope and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
 version: 1.56.1
 metadata:
   openclaw:
@@ -55,7 +55,7 @@ if (Test-Path "$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md") { "user" }
 | `.baoyu-skills/baoyu-image-gen/EXTEND.md` | Project directory |
 | `$HOME/.baoyu-skills/baoyu-image-gen/EXTEND.md` | User home |
 
-**EXTEND.md Supports**: Default provider | Default quality | Default aspect ratio | Default image size | Default models
+**EXTEND.md Supports**: Default provider | Default quality | Default aspect ratio | Default image size | Default models | Batch worker cap | Provider-specific batch limits
 
 Schema: `references/config/preferences-schema.md`
 
@@ -91,22 +91,57 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider r
 
 # Replicate with specific model
 ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana
+
+# Batch mode with saved prompt files
+${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json
+
+# Batch mode with explicit worker count
+${BUN_X} {baseDir}/scripts/main.ts --batchfile batch.json --jobs 4 --json
 ```
 
+### Batch File Format
+
+```json
+{
+  "jobs": 4,
+  "tasks": [
+    {
+      "id": "hero",
+      "promptFiles": ["prompts/hero.md"],
+      "image": "out/hero.png",
+      "provider": "replicate",
+      "model": "google/nano-banana-pro",
+      "ar": "16:9",
+      "quality": "2k"
+    },
+    {
+      "id": "diagram",
+      "promptFiles": ["prompts/diagram.md"],
+      "image": "out/diagram.png",
+      "ref": ["references/original.png"]
+    }
+  ]
+}
+```
+
+Paths in `promptFiles`, `image`, and `ref` are resolved relative to the batch file's directory. `jobs` is optional (overridden by CLI `--jobs`). Top-level array format (without `jobs` wrapper) is also accepted.
+
 ## Options
 
 | Option | Description |
 |--------|-------------|
 | `--prompt <text>`, `-p` | Prompt text |
 | `--promptfiles <files...>` | Read prompt from files (concatenated) |
-| `--image <path>` | Output image path (required) |
+| `--image <path>` | Output image path (required in single-image mode) |
-| `--provider google\|openai\|dashscope\|replicate` | Force provider (default: google) |
+| `--batchfile <path>` | JSON batch file for multi-image generation |
-| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`, `gemini-3.1-flash-image-preview`; OpenAI: `gpt-image-1.5`) |
+| `--jobs <count>` | Worker count for batch mode (default: auto, max from config, built-in default 10) |
+| `--provider google\|openai\|dashscope\|replicate` | Force provider (default: auto-detect) |
+| `--model <id>`, `-m` | Model ID (Google: `gemini-3-pro-image-preview`, `gemini-3.1-flash-image-preview`; OpenAI: `gpt-image-1.5`, `gpt-image-1`) |
 | `--ar <ratio>` | Aspect ratio (e.g., `16:9`, `1:1`, `4:3`) |
 | `--size <WxH>` | Size (e.g., `1024x1024`) |
-| `--quality normal\|2k` | Quality preset (default: 2k) |
+| `--quality normal\|2k` | Quality preset (default: `2k`) |
 | `--imageSize 1K\|2K\|4K` | Image size for Google (default: from quality) |
-| `--ref <files...>` | Reference images. Supported by Google multimodal (`gemini-3-pro-image-preview`, `gemini-3-flash-preview`, `gemini-3.1-flash-image-preview`) and OpenAI edits (GPT Image models). If provider omitted: Google first, then OpenAI |
+| `--ref <files...>` | Reference images. Supported by Google multimodal, OpenAI GPT Image edits, and Replicate |
 | `--n <count>` | Number of images |
 | `--json` | JSON output |
 
@@ -126,6 +161,9 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider r
 | `GOOGLE_BASE_URL` | Custom Google endpoint |
 | `DASHSCOPE_BASE_URL` | Custom DashScope endpoint |
 | `REPLICATE_BASE_URL` | Custom Replicate endpoint |
+| `BAOYU_IMAGE_GEN_MAX_WORKERS` | Override batch worker cap |
+| `BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY` | Override provider concurrency, e.g. `BAOYU_IMAGE_GEN_REPLICATE_CONCURRENCY` |
+| `BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS` | Override provider start gap, e.g. `BAOYU_IMAGE_GEN_REPLICATE_START_INTERVAL_MS` |
 
 **Load Priority**: CLI args > EXTEND.md > env vars > `<cwd>/.baoyu-skills/.env` > `~/.baoyu-skills/.env`
 
@@ -170,10 +208,10 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider r
 
 ## Quality Presets
 
-| Preset | Google imageSize | OpenAI Size | Use Case |
+| Preset | Google imageSize | OpenAI Size | Replicate resolution | Use Case |
-|--------|------------------|-------------|----------|
+|--------|------------------|-------------|----------------------|----------|
-| `normal` | 1K | 1024px | Quick previews |
+| `normal` | 1K | 1024px | 1K | Quick previews |
-| `2k` (default) | 2K | 2048px | Covers, illustrations, infographics |
+| `2k` (default) | 2K | 2048px | 2K | Covers, illustrations, infographics |
 
 **Google imageSize**: Can be overridden with `--imageSize 1K|2K|4K`
 
@@ -182,41 +220,48 @@ ${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider r
 Supported: `1:1`, `16:9`, `9:16`, `4:3`, `3:4`, `2.35:1`
 
 - Google multimodal: uses `imageConfig.aspectRatio`
-- Google Imagen: uses `aspectRatio` parameter
 - OpenAI: maps to closest supported size
+- Replicate: passes `aspect_ratio` to model; when `--ref` is provided without `--ar`, defaults to `match_input_image`
 
 ## Generation Mode
 
-**Default**: Sequential generation (one image at a time). This ensures stable output and easier debugging.
+**Default**: Sequential generation.
 
-**Parallel Generation**: Only use when user explicitly requests parallel/concurrent generation.
+**Batch Parallel Generation**: When `--batchfile` contains 2 or more pending tasks, the script automatically enables parallel generation.
 
 | Mode | When to Use |
 |------|-------------|
 | Sequential (default) | Normal usage, single images, small batches |
-| Parallel | User explicitly requests, large batches (10+) |
+| Parallel batch | Batch mode with 2+ tasks |
 
-**Parallel Settings** (when requested):
+Execution choice:
 
-| Setting | Value |
+| Situation | Preferred approach | Why |
-|---------|-------|
+|-----------|--------------------|-----|
-| Recommended concurrency | 4 subagents |
+| One image, or 1-2 simple images | Sequential | Lower coordination overhead and easier debugging |
-| Max concurrency | 8 subagents |
+| Multiple images already have saved prompt files | Batch (`--batchfile`) | Reuses finalized prompts, applies shared throttling/retries, and gives predictable throughput |
-| Use case | Large batch generation when user requests parallel |
+| Each image still needs separate reasoning, prompt writing, or style exploration | Subagents | The work is still exploratory, so each image may need independent analysis before generation |
+| Output comes from `baoyu-article-illustrator` with `outline.md` + `prompts/` | Batch (`build-batch.ts` -> `--batchfile`) | That workflow already produces prompt files, so direct batch execution is the intended path |
 
-**Agent Implementation** (parallel mode only):
+Rule of thumb:
-```
+
-# Launch multiple generations in parallel using Task tool
+- Prefer batch over subagents once prompt files are already saved and the task is "generate all of these"
-# Each Task runs as background subagent with run_in_background=true
+- Use subagents only when generation is coupled with per-image thinking, rewriting, or divergent creative exploration
-# Collect results via TaskOutput when all complete
+
-```
+Parallel behavior:
+
+- Default worker count is automatic, capped by config, built-in default 10
+- Provider-specific throttling is applied only in batch mode, and the built-in defaults are tuned for faster throughput while still avoiding obvious RPM bursts
+- You can override worker count with `--jobs <count>`
+- Each image retries automatically up to 3 attempts
+- Final output includes success count, failure count, and per-image failure reasons
 
 ## Error Handling
 
 - Missing API key → error with setup instructions
-- Generation failure → auto-retry once
+- Generation failure → auto-retry up to 3 attempts per image
 - Invalid aspect ratio → warning, proceed with default
-- Reference images with unsupported provider/model → error with fix hint (switch to Google multimodal: `gemini-3-pro-image-preview`, `gemini-3.1-flash-image-preview`; or OpenAI GPT Image edits)
+- Reference images with unsupported provider/model → error with fix hint
 
 ## Extension Support
 

skills/baoyu-image-gen/references/config/preferences-schema.md

@@ -21,9 +21,25 @@ default_image_size: null    # 1K|2K|4K|null (Google only, overrides quality)
 
 default_model:
   google: null              # e.g., "gemini-3-pro-image-preview", "gemini-3.1-flash-image-preview"
-  openai: null              # e.g., "gpt-image-1.5"
+  openai: null              # e.g., "gpt-image-1.5", "gpt-image-1"
   dashscope: null           # e.g., "z-image-turbo"
   replicate: null           # e.g., "google/nano-banana-pro"
+
+batch:
+  max_workers: 10
+  provider_limits:
+    replicate:
+      concurrency: 5
+      start_interval_ms: 700
+    google:
+      concurrency: 3
+      start_interval_ms: 1100
+    openai:
+      concurrency: 3
+      start_interval_ms: 1100
+    dashscope:
+      concurrency: 3
+      start_interval_ms: 1100
 ---
 ```
 
@@ -40,6 +56,9 @@ default_model:
 | `default_model.openai` | string\|null | null | OpenAI default model |
 | `default_model.dashscope` | string\|null | null | DashScope default model |
 | `default_model.replicate` | string\|null | null | Replicate default model |
+| `batch.max_workers` | int\|null | 10 | Batch worker cap |
+| `batch.provider_limits.<provider>.concurrency` | int\|null | provider default | Max simultaneous requests per provider |
+| `batch.provider_limits.<provider>.start_interval_ms` | int\|null | provider default | Minimum gap between request starts per provider |
 
 ## Examples
 
@@ -65,5 +84,11 @@ default_model:
   openai: "gpt-image-1.5"
   dashscope: "z-image-turbo"
   replicate: "google/nano-banana-pro"
+batch:
+  max_workers: 10
+  provider_limits:
+    replicate:
+      concurrency: 5
+      start_interval_ms: 700
 ---
 ```

skills/baoyu-image-gen/scripts/main.ts

@@ -2,34 +2,108 @@ import path from "node:path";
 import process from "node:process";
 import { homedir } from "node:os";
 import { access, mkdir, readFile, writeFile } from "node:fs/promises";
-import type { CliArgs, Provider, ExtendConfig } from "./types";
+import type {
+  BatchFile,
+  BatchTaskInput,
+  CliArgs,
+  ExtendConfig,
+  Provider,
+} from "./types";
+
+type ProviderModule = {
+  getDefaultModel: () => string;
+  generateImage: (prompt: string, model: string, args: CliArgs) => Promise<Uint8Array>;
+};
+
+type PreparedTask = {
+  id: string;
+  prompt: string;
+  args: CliArgs;
+  provider: Provider;
+  model: string;
+  outputPath: string;
+  providerModule: ProviderModule;
+};
+
+type TaskResult = {
+  id: string;
+  provider: Provider;
+  model: string;
+  outputPath: string;
+  success: boolean;
+  attempts: number;
+  error: string | null;
+};
+
+type ProviderRateLimit = {
+  concurrency: number;
+  startIntervalMs: number;
+};
+
+type LoadedBatchTasks = {
+  tasks: BatchTaskInput[];
+  jobs: number | null;
+  batchDir: string;
+};
+
+const MAX_ATTEMPTS = 3;
+const DEFAULT_MAX_WORKERS = 10;
+const POLL_WAIT_MS = 250;
+const DEFAULT_PROVIDER_RATE_LIMITS: Record<Provider, ProviderRateLimit> = {
+  replicate: { concurrency: 5, startIntervalMs: 700 },
+  google: { concurrency: 3, startIntervalMs: 1100 },
+  openai: { concurrency: 3, startIntervalMs: 1100 },
+  dashscope: { concurrency: 3, startIntervalMs: 1100 },
+};
 
 function printUsage(): void {
   console.log(`Usage:
   npx -y bun scripts/main.ts --prompt "A cat" --image cat.png
-  npx -y bun scripts/main.ts --prompt "A landscape" --image landscape.png --ar 16:9
   npx -y bun scripts/main.ts --promptfiles system.md content.md --image out.png
+  npx -y bun scripts/main.ts --batchfile batch.json
 
 Options:
   -p, --prompt <text>       Prompt text
   --promptfiles <files...>  Read prompt from files (concatenated)
-  --image <path>            Output image path (required)
+  --image <path>            Output image path (required in single-image mode)
+  --batchfile <path>        JSON batch file for multi-image generation
+  --jobs <count>            Worker count for batch mode (default: auto, max from config, built-in default 10)
   --provider google|openai|dashscope|replicate  Force provider (auto-detect by default)
   -m, --model <id>          Model ID
   --ar <ratio>              Aspect ratio (e.g., 16:9, 1:1, 4:3)
   --size <WxH>              Size (e.g., 1024x1024)
   --quality normal|2k       Quality preset (default: 2k)
   --imageSize 1K|2K|4K      Image size for Google (default: from quality)
-  --ref <files...>          Reference images (Google multimodal or OpenAI edits)
+  --ref <files...>          Reference images (Google multimodal, OpenAI GPT Image edits, or Replicate)
-  --n <count>               Number of images (default: 1)
+  --n <count>               Number of images for the current task (default: 1)
   --json                    JSON output
   -h, --help                Show help
 
+Batch file format:
+  {
+    "jobs": 4,
+    "tasks": [
+      {
+        "id": "hero",
+        "promptFiles": ["prompts/hero.md"],
+        "image": "out/hero.png",
+        "provider": "replicate",
+        "model": "google/nano-banana-pro",
+        "ar": "16:9"
+      }
+    ]
+  }
+
+Behavior:
+  - Batch mode automatically runs in parallel when pending tasks >= 2
+  - Each image retries automatically up to 3 attempts
+  - Batch summary reports success count, failure count, and per-image errors
+
 Environment variables:
   OPENAI_API_KEY            OpenAI API key
   GOOGLE_API_KEY            Google API key
   GEMINI_API_KEY            Gemini API key (alias for GOOGLE_API_KEY)
-  DASHSCOPE_API_KEY         DashScope API key (阿里云通义万象)
+  DASHSCOPE_API_KEY         DashScope API key
   REPLICATE_API_TOKEN       Replicate API token
   OPENAI_IMAGE_MODEL        Default OpenAI model (gpt-image-1.5)
   GOOGLE_IMAGE_MODEL        Default Google model (gemini-3-pro-image-preview)
@@ -40,6 +114,9 @@ Environment variables:
   GOOGLE_BASE_URL           Custom Google endpoint
   DASHSCOPE_BASE_URL        Custom DashScope endpoint
   REPLICATE_BASE_URL        Custom Replicate endpoint
+  BAOYU_IMAGE_GEN_MAX_WORKERS  Override batch worker cap
+  BAOYU_IMAGE_GEN_<PROVIDER>_CONCURRENCY  Override provider concurrency
+  BAOYU_IMAGE_GEN_<PROVIDER>_START_INTERVAL_MS  Override provider start gap in ms
 
 Env file load order: CLI args > EXTEND.md > process.env > <cwd>/.baoyu-skills/.env > ~/.baoyu-skills/.env`);
 }
@@ -57,6 +134,8 @@ function parseArgs(argv: string[]): CliArgs {
     imageSize: null,
     referenceImages: [],
     n: 1,
+    batchFile: null,
+    jobs: null,
     json: false,
     help: false,
   };
@@ -110,9 +189,26 @@ function parseArgs(argv: string[]): CliArgs {
       continue;
     }
 
+    if (a === "--batchfile") {
+      const v = argv[++i];
+      if (!v) throw new Error("Missing value for --batchfile");
+      out.batchFile = v;
+      continue;
+    }
+
+    if (a === "--jobs") {
+      const v = argv[++i];
+      if (!v) throw new Error("Missing value for --jobs");
+      out.jobs = parseInt(v, 10);
+      if (isNaN(out.jobs) || out.jobs < 1) throw new Error(`Invalid worker count: ${v}`);
+      continue;
+    }
+
     if (a === "--provider") {
       const v = argv[++i];
-      if (v !== "google" && v !== "openai" && v !== "dashscope" && v !== "replicate") throw new Error(`Invalid provider: ${v}`);
+      if (v !== "google" && v !== "openai" && v !== "dashscope" && v !== "replicate") {
+        throw new Error(`Invalid provider: ${v}`);
+      }
       out.provider = v;
       continue;
     }
@@ -228,9 +324,11 @@ function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
   const config: Partial<ExtendConfig> = {};
   const lines = yaml.split("\n");
   let currentKey: string | null = null;
+  let currentProvider: Provider | null = null;
 
   for (const line of lines) {
     const trimmed = line.trim();
+    const indent = line.match(/^\s*/)?.[0].length ?? 0;
     if (!trimmed || trimmed.startsWith("#")) continue;
 
     if (trimmed.includes(":") && !trimmed.startsWith("-")) {
@@ -247,18 +345,57 @@ function parseSimpleYaml(yaml: string): Partial<ExtendConfig> {
       } else if (key === "default_provider") {
         config.default_provider = value === "null" ? null : (value as Provider);
       } else if (key === "default_quality") {
-        config.default_quality = value === "null" ? null : (value as "normal" | "2k");
+        config.default_quality = value === "null" ? null : value as "normal" | "2k";
       } else if (key === "default_aspect_ratio") {
         const cleaned = value.replace(/['"]/g, "");
         config.default_aspect_ratio = cleaned === "null" ? null : cleaned;
       } else if (key === "default_image_size") {
-        config.default_image_size = value === "null" ? null : (value as "1K" | "2K" | "4K");
+        config.default_image_size = value === "null" ? null : value as "1K" | "2K" | "4K";
       } else if (key === "default_model") {
         config.default_model = { google: null, openai: null, dashscope: null, replicate: null };
         currentKey = "default_model";
-      } else if (currentKey === "default_model" && (key === "google" || key === "openai" || key === "dashscope" || key === "replicate")) {
+        currentProvider = null;
+      } else if (key === "batch") {
+        config.batch = {};
+        currentKey = "batch";
+        currentProvider = null;
+      } else if (currentKey === "batch" && indent >= 2 && key === "max_workers") {
+        config.batch ??= {};
+        config.batch.max_workers = value === "null" ? null : parseInt(value, 10);
+      } else if (currentKey === "batch" && indent >= 2 && key === "provider_limits") {
+        config.batch ??= {};
+        config.batch.provider_limits ??= {};
+        currentKey = "provider_limits";
+        currentProvider = null;
+      } else if (
+        currentKey === "provider_limits" &&
+        indent >= 4 &&
+        (key === "google" || key === "openai" || key === "dashscope" || key === "replicate")
+      ) {
+        config.batch ??= {};
+        config.batch.provider_limits ??= {};
+        config.batch.provider_limits[key] ??= {};
+        currentProvider = key;
+      } else if (
+        currentKey === "default_model" &&
+        (key === "google" || key === "openai" || key === "dashscope" || key === "replicate")
+      ) {
         const cleaned = value.replace(/['"]/g, "");
         config.default_model![key] = cleaned === "null" ? null : cleaned;
+      } else if (
+        currentKey === "provider_limits" &&
+        currentProvider &&
+        indent >= 6 &&
+        (key === "concurrency" || key === "start_interval_ms")
+      ) {
+        config.batch ??= {};
+        config.batch.provider_limits ??= {};
+        const providerLimit = (config.batch.provider_limits[currentProvider] ??= {});
+        if (key === "concurrency") {
+          providerLimit.concurrency = value === "null" ? null : parseInt(value, 10);
+        } else {
+          providerLimit.start_interval_ms = value === "null" ? null : parseInt(value, 10);
+        }
       }
     }
   }
@@ -280,7 +417,6 @@ async function loadExtendConfig(): Promise<Partial<ExtendConfig>> {
       const content = await readFile(p, "utf8");
       const yaml = extractYamlFrontMatter(content);
       if (!yaml) continue;
-
       return parseSimpleYaml(yaml);
     } catch {
       continue;
@@ -300,6 +436,57 @@ function mergeConfig(args: CliArgs, extend: Partial<ExtendConfig>): CliArgs {
   };
 }
 
+function parsePositiveInt(value: string | undefined): number | null {
+  if (!value) return null;
+  const parsed = parseInt(value, 10);
+  return Number.isFinite(parsed) && parsed > 0 ? parsed : null;
+}
+
+function parsePositiveBatchInt(value: unknown): number | null {
+  if (value === null || value === undefined) return null;
+  if (typeof value === "number") {
+    return Number.isInteger(value) && value > 0 ? value : null;
+  }
+  if (typeof value === "string") {
+    return parsePositiveInt(value);
+  }
+  return null;
+}
+
+function getConfiguredMaxWorkers(extendConfig: Partial<ExtendConfig>): number {
+  const envValue = parsePositiveInt(process.env.BAOYU_IMAGE_GEN_MAX_WORKERS);
+  const configValue = extendConfig.batch?.max_workers ?? null;
+  return Math.max(1, envValue ?? configValue ?? DEFAULT_MAX_WORKERS);
+}
+
+function getConfiguredProviderRateLimits(
+  extendConfig: Partial<ExtendConfig>
+): Record<Provider, ProviderRateLimit> {
+  const configured: Record<Provider, ProviderRateLimit> = {
+    replicate: { ...DEFAULT_PROVIDER_RATE_LIMITS.replicate },
+    google: { ...DEFAULT_PROVIDER_RATE_LIMITS.google },
+    openai: { ...DEFAULT_PROVIDER_RATE_LIMITS.openai },
+    dashscope: { ...DEFAULT_PROVIDER_RATE_LIMITS.dashscope },
+  };
+
+  for (const provider of ["replicate", "google", "openai", "dashscope"] as Provider[]) {
+    const envPrefix = `BAOYU_IMAGE_GEN_${provider.toUpperCase()}`;
+    const extendLimit = extendConfig.batch?.provider_limits?.[provider];
+    configured[provider] = {
+      concurrency:
+        parsePositiveInt(process.env[`${envPrefix}_CONCURRENCY`]) ??
+        extendLimit?.concurrency ??
+        configured[provider].concurrency,
+      startIntervalMs:
+        parsePositiveInt(process.env[`${envPrefix}_START_INTERVAL_MS`]) ??
+        extendLimit?.start_interval_ms ??
+        configured[provider].startIntervalMs,
+    };
+  }
+
+  return configured;
+}
+
 async function readPromptFromFiles(files: string[]): Promise<string> {
   const parts: string[] = [];
   for (const f of files) {
@@ -311,9 +498,12 @@ async function readPromptFromFiles(files: string[]): Promise<string> {
 async function readPromptFromStdin(): Promise<string | null> {
   if (process.stdin.isTTY) return null;
   try {
-    const t = await Bun.stdin.text();
+    const chunks: Buffer[] = [];
-    const v = t.trim();
+    for await (const chunk of process.stdin) {
-    return v.length > 0 ? v : null;
+      chunks.push(Buffer.isBuffer(chunk) ? chunk : Buffer.from(chunk));
+    }
+    const value = Buffer.concat(chunks).toString("utf8").trim();
+    return value.length > 0 ? value : null;
   } catch {
     return null;
   }
@@ -327,7 +517,13 @@ function normalizeOutputImagePath(p: string): string {
 }
 
 function detectProvider(args: CliArgs): Provider {
-  if (args.referenceImages.length > 0 && args.provider && args.provider !== "google" && args.provider !== "openai" && args.provider !== "replicate") {
+  if (
+    args.referenceImages.length > 0 &&
+    args.provider &&
+    args.provider !== "google" &&
+    args.provider !== "openai" &&
+    args.provider !== "replicate"
+  ) {
     throw new Error(
       "Reference images require a ref-capable provider. Use --provider google (Gemini multimodal), --provider openai (GPT Image edits), or --provider replicate."
     );
@@ -349,7 +545,12 @@ function detectProvider(args: CliArgs): Provider {
     );
   }
 
-  const available = [hasGoogle && "google", hasOpenai && "openai", hasDashscope && "dashscope", hasReplicate && "replicate"].filter(Boolean) as Provider[];
+  const available = [
+    hasGoogle && "google",
+    hasOpenai && "openai",
+    hasDashscope && "dashscope",
+    hasReplicate && "replicate",
+  ].filter(Boolean) as Provider[];
 
   if (available.length === 1) return available[0]!;
   if (available.length > 1) return available[0]!;
@@ -371,11 +572,6 @@ async function validateReferenceImages(referenceImages: string[]): Promise<void>
   }
 }
 
-type ProviderModule = {
-  getDefaultModel: () => string;
-  generateImage: (prompt: string, model: string, args: CliArgs) => Promise<Uint8Array>;
-};
-
 function isRetryableGenerationError(error: unknown): boolean {
   const msg = error instanceof Error ? error.message : String(error);
   const nonRetryableMarkers = [
@@ -384,26 +580,353 @@ function isRetryableGenerationError(error: unknown): boolean {
     "only supported",
     "No API key found",
     "is required",
+    "Invalid ",
+    "Unexpected ",
+    "API error (400)",
+    "API error (401)",
+    "API error (402)",
+    "API error (403)",
+    "API error (404)",
+    "temporarily disabled",
   ];
   return !nonRetryableMarkers.some((marker) => msg.includes(marker));
 }
 
 async function loadProviderModule(provider: Provider): Promise<ProviderModule> {
-  if (provider === "google") {
+  if (provider === "google") return (await import("./providers/google")) as ProviderModule;
-    return (await import("./providers/google")) as ProviderModule;
+  if (provider === "dashscope") return (await import("./providers/dashscope")) as ProviderModule;
-  }
+  if (provider === "replicate") return (await import("./providers/replicate")) as ProviderModule;
-  if (provider === "dashscope") {
-    return (await import("./providers/dashscope")) as ProviderModule;
-  }
-  if (provider === "replicate") {
-    return (await import("./providers/replicate")) as ProviderModule;
-  }
   return (await import("./providers/openai")) as ProviderModule;
 }
 
+async function loadPromptForArgs(args: CliArgs): Promise<string | null> {
+  let prompt: string | null = args.prompt;
+  if (!prompt && args.promptFiles.length > 0) {
+    prompt = await readPromptFromFiles(args.promptFiles);
+  }
+  return prompt;
+}
+
+function getModelForProvider(
+  provider: Provider,
+  requestedModel: string | null,
+  extendConfig: Partial<ExtendConfig>,
+  providerModule: ProviderModule
+): string {
+  if (requestedModel) return requestedModel;
+  if (extendConfig.default_model) {
+    if (provider === "google" && extendConfig.default_model.google) return extendConfig.default_model.google;
+    if (provider === "openai" && extendConfig.default_model.openai) return extendConfig.default_model.openai;
+    if (provider === "dashscope" && extendConfig.default_model.dashscope) return extendConfig.default_model.dashscope;
+    if (provider === "replicate" && extendConfig.default_model.replicate) return extendConfig.default_model.replicate;
+  }
+  return providerModule.getDefaultModel();
+}
+
+async function prepareSingleTask(args: CliArgs, extendConfig: Partial<ExtendConfig>): Promise<PreparedTask> {
+  if (!args.quality) args.quality = "2k";
+
+  const prompt = (await loadPromptForArgs(args)) ?? (await readPromptFromStdin());
+  if (!prompt) throw new Error("Prompt is required");
+  if (!args.imagePath) throw new Error("--image is required");
+  if (args.referenceImages.length > 0) await validateReferenceImages(args.referenceImages);
+
+  const provider = detectProvider(args);
+  const providerModule = await loadProviderModule(provider);
+  const model = getModelForProvider(provider, args.model, extendConfig, providerModule);
+
+  return {
+    id: "single",
+    prompt,
+    args,
+    provider,
+    model,
+    outputPath: normalizeOutputImagePath(args.imagePath),
+    providerModule,
+  };
+}
+
+async function loadBatchTasks(batchFilePath: string): Promise<LoadedBatchTasks> {
+  const resolvedBatchFilePath = path.resolve(batchFilePath);
+  const content = await readFile(resolvedBatchFilePath, "utf8");
+  const parsed = JSON.parse(content.replace(/^\uFEFF/, "")) as BatchFile;
+  const batchDir = path.dirname(resolvedBatchFilePath);
+  if (Array.isArray(parsed)) {
+    return {
+      tasks: parsed,
+      jobs: null,
+      batchDir,
+    };
+  }
+  if (parsed && typeof parsed === "object" && Array.isArray(parsed.tasks)) {
+    const jobs = parsePositiveBatchInt(parsed.jobs);
+    if (parsed.jobs !== undefined && parsed.jobs !== null && jobs === null) {
+      throw new Error("Invalid batch file. jobs must be a positive integer when provided.");
+    }
+    return {
+      tasks: parsed.tasks,
+      jobs,
+      batchDir,
+    };
+  }
+  throw new Error("Invalid batch file. Expected an array of tasks or an object with a tasks array.");
+}
+
+function resolveBatchPath(batchDir: string, filePath: string): string {
+  return path.isAbsolute(filePath) ? filePath : path.resolve(batchDir, filePath);
+}
+
+function createTaskArgs(baseArgs: CliArgs, task: BatchTaskInput, batchDir: string): CliArgs {
+  return {
+    ...baseArgs,
+    prompt: task.prompt ?? null,
+    promptFiles: task.promptFiles ? task.promptFiles.map((filePath) => resolveBatchPath(batchDir, filePath)) : [],
+    imagePath: task.image ? resolveBatchPath(batchDir, task.image) : null,
+    provider: task.provider ?? baseArgs.provider ?? null,
+    model: task.model ?? baseArgs.model ?? null,
+    aspectRatio: task.ar ?? baseArgs.aspectRatio ?? null,
+    size: task.size ?? baseArgs.size ?? null,
+    quality: task.quality ?? baseArgs.quality ?? null,
+    imageSize: task.imageSize ?? baseArgs.imageSize ?? null,
+    referenceImages: task.ref ? task.ref.map((filePath) => resolveBatchPath(batchDir, filePath)) : [],
+    n: task.n ?? baseArgs.n,
+    batchFile: null,
+    jobs: baseArgs.jobs,
+    json: baseArgs.json,
+    help: false,
+  };
+}
+
+async function prepareBatchTasks(
+  args: CliArgs,
+  extendConfig: Partial<ExtendConfig>
+): Promise<{ tasks: PreparedTask[]; jobs: number | null }> {
+  if (!args.batchFile) throw new Error("--batchfile is required in batch mode");
+  const { tasks: taskInputs, jobs: batchJobs, batchDir } = await loadBatchTasks(args.batchFile);
+  if (taskInputs.length === 0) throw new Error("Batch file does not contain any tasks.");
+
+  const prepared: PreparedTask[] = [];
+  for (let i = 0; i < taskInputs.length; i++) {
+    const task = taskInputs[i]!;
+    const taskArgs = createTaskArgs(args, task, batchDir);
+    const prompt = await loadPromptForArgs(taskArgs);
+    if (!prompt) throw new Error(`Task ${i + 1} is missing prompt or promptFiles.`);
+    if (!taskArgs.imagePath) throw new Error(`Task ${i + 1} is missing image output path.`);
+    if (taskArgs.referenceImages.length > 0) await validateReferenceImages(taskArgs.referenceImages);
+
+    const provider = detectProvider(taskArgs);
+    const providerModule = await loadProviderModule(provider);
+    const model = getModelForProvider(provider, taskArgs.model, extendConfig, providerModule);
+    prepared.push({
+      id: task.id || `task-${String(i + 1).padStart(2, "0")}`,
+      prompt,
+      args: taskArgs,
+      provider,
+      model,
+      outputPath: normalizeOutputImagePath(taskArgs.imagePath),
+      providerModule,
+    });
+  }
+
+  return {
+    tasks: prepared,
+    jobs: args.jobs ?? batchJobs,
+  };
+}
+
+async function writeImage(outputPath: string, imageData: Uint8Array): Promise<void> {
+  await mkdir(path.dirname(outputPath), { recursive: true });
+  await writeFile(outputPath, imageData);
+}
+
+async function generatePreparedTask(task: PreparedTask): Promise<TaskResult> {
+  console.error(`Using ${task.provider} / ${task.model} for ${task.id}`);
+  console.error(
+    `Switch model: --model <id> | EXTEND.md default_model.${task.provider} | env ${task.provider.toUpperCase()}_IMAGE_MODEL`
+  );
+
+  let attempts = 0;
+  while (attempts < MAX_ATTEMPTS) {
+    attempts += 1;
+    try {
+      const imageData = await task.providerModule.generateImage(task.prompt, task.model, task.args);
+      await writeImage(task.outputPath, imageData);
+      return {
+        id: task.id,
+        provider: task.provider,
+        model: task.model,
+        outputPath: task.outputPath,
+        success: true,
+        attempts,
+        error: null,
+      };
+    } catch (error) {
+      const message = error instanceof Error ? error.message : String(error);
+      const canRetry = attempts < MAX_ATTEMPTS && isRetryableGenerationError(error);
+      if (canRetry) {
+        console.error(`[${task.id}] Attempt ${attempts}/${MAX_ATTEMPTS} failed, retrying...`);
+        continue;
+      }
+      return {
+        id: task.id,
+        provider: task.provider,
+        model: task.model,
+        outputPath: task.outputPath,
+        success: false,
+        attempts,
+        error: message,
+      };
+    }
+  }
+
+  return {
+    id: task.id,
+    provider: task.provider,
+    model: task.model,
+    outputPath: task.outputPath,
+    success: false,
+    attempts: MAX_ATTEMPTS,
+    error: "Unknown failure",
+  };
+}
+
+function createProviderGate(providerRateLimits: Record<Provider, ProviderRateLimit>) {
+  const state = new Map<Provider, { active: number; lastStartedAt: number }>();
+
+  return async function acquire(provider: Provider): Promise<() => void> {
+    const limit = providerRateLimits[provider];
+    while (true) {
+      const current = state.get(provider) ?? { active: 0, lastStartedAt: 0 };
+      const now = Date.now();
+      const enoughCapacity = current.active < limit.concurrency;
+      const enoughGap = now - current.lastStartedAt >= limit.startIntervalMs;
+      if (enoughCapacity && enoughGap) {
+        state.set(provider, { active: current.active + 1, lastStartedAt: now });
+        return () => {
+          const latest = state.get(provider) ?? { active: 1, lastStartedAt: now };
+          state.set(provider, {
+            active: Math.max(0, latest.active - 1),
+            lastStartedAt: latest.lastStartedAt,
+          });
+        };
+      }
+      await new Promise((resolve) => setTimeout(resolve, POLL_WAIT_MS));
+    }
+  };
+}
+
+function getWorkerCount(taskCount: number, jobs: number | null, maxWorkers: number): number {
+  const requested = jobs ?? Math.min(taskCount, maxWorkers);
+  return Math.max(1, Math.min(requested, taskCount, maxWorkers));
+}
+
+async function runBatchTasks(
+  tasks: PreparedTask[],
+  jobs: number | null,
+  extendConfig: Partial<ExtendConfig>
+): Promise<TaskResult[]> {
+  if (tasks.length === 1) {
+    return [await generatePreparedTask(tasks[0]!)];
+  }
+
+  const maxWorkers = getConfiguredMaxWorkers(extendConfig);
+  const providerRateLimits = getConfiguredProviderRateLimits(extendConfig);
+  const acquireProvider = createProviderGate(providerRateLimits);
+  const workerCount = getWorkerCount(tasks.length, jobs, maxWorkers);
+  console.error(`Batch mode: ${tasks.length} tasks, ${workerCount} workers, parallel mode enabled.`);
+  for (const provider of ["replicate", "google", "openai", "dashscope"] as Provider[]) {
+    const limit = providerRateLimits[provider];
+    console.error(`- ${provider}: concurrency=${limit.concurrency}, startIntervalMs=${limit.startIntervalMs}`);
+  }
+
+  let nextIndex = 0;
+  const results: TaskResult[] = new Array(tasks.length);
+
+  const worker = async (): Promise<void> => {
+    while (true) {
+      const currentIndex = nextIndex;
+      nextIndex += 1;
+      if (currentIndex >= tasks.length) return;
+
+      const task = tasks[currentIndex]!;
+      const release = await acquireProvider(task.provider);
+      try {
+        results[currentIndex] = await generatePreparedTask(task);
+      } finally {
+        release();
+      }
+    }
+  };
+
+  await Promise.all(Array.from({ length: workerCount }, () => worker()));
+  return results;
+}
+
+function printBatchSummary(results: TaskResult[]): void {
+  const successCount = results.filter((result) => result.success).length;
+  const failureCount = results.length - successCount;
+
+  console.error("");
+  console.error("Batch generation summary:");
+  console.error(`- Total: ${results.length}`);
+  console.error(`- Succeeded: ${successCount}`);
+  console.error(`- Failed: ${failureCount}`);
+
+  if (failureCount > 0) {
+    console.error("Failure reasons:");
+    for (const result of results.filter((item) => !item.success)) {
+      console.error(`- ${result.id}: ${result.error}`);
+    }
+  }
+}
+
+function emitJson(payload: unknown): void {
+  console.log(JSON.stringify(payload, null, 2));
+}
+
+async function runSingleMode(args: CliArgs, extendConfig: Partial<ExtendConfig>): Promise<void> {
+  const task = await prepareSingleTask(args, extendConfig);
+  const result = await generatePreparedTask(task);
+  if (!result.success) {
+    throw new Error(result.error || "Generation failed");
+  }
+
+  if (args.json) {
+    emitJson({
+      savedImage: result.outputPath,
+      provider: result.provider,
+      model: result.model,
+      attempts: result.attempts,
+      prompt: task.prompt.slice(0, 200),
+    });
+    return;
+  }
+
+  console.log(result.outputPath);
+}
+
+async function runBatchMode(args: CliArgs, extendConfig: Partial<ExtendConfig>): Promise<void> {
+  const { tasks, jobs } = await prepareBatchTasks(args, extendConfig);
+  const results = await runBatchTasks(tasks, jobs, extendConfig);
+  printBatchSummary(results);
+
+  if (args.json) {
+    emitJson({
+      mode: "batch",
+      total: results.length,
+      succeeded: results.filter((item) => item.success).length,
+      failed: results.filter((item) => !item.success).length,
+      results,
+    });
+  }
+
+  if (results.some((item) => !item.success)) {
+    process.exitCode = 1;
+  }
+}
+
 async function main(): Promise<void> {
   const args = parseArgs(process.argv.slice(2));
-
   if (args.help) {
     printUsage();
     return;
@@ -412,86 +935,18 @@ async function main(): Promise<void> {
   await loadEnv();
   const extendConfig = await loadExtendConfig();
   const mergedArgs = mergeConfig(args, extendConfig);
-
   if (!mergedArgs.quality) mergedArgs.quality = "2k";
 
-  let prompt: string | null = mergedArgs.prompt;
+  if (mergedArgs.batchFile) {
-  if (!prompt && mergedArgs.promptFiles.length > 0) prompt = await readPromptFromFiles(mergedArgs.promptFiles);
+    await runBatchMode(mergedArgs, extendConfig);
-  if (!prompt) prompt = await readPromptFromStdin();
-
-  if (!prompt) {
-    console.error("Error: Prompt is required");
-    printUsage();
-    process.exitCode = 1;
     return;
   }
 
-  if (!mergedArgs.imagePath) {
+  await runSingleMode(mergedArgs, extendConfig);
-    console.error("Error: --image is required");
-    printUsage();
-    process.exitCode = 1;
-    return;
-  }
-
-  if (mergedArgs.referenceImages.length > 0) {
-    await validateReferenceImages(mergedArgs.referenceImages);
-  }
-
-  const provider = detectProvider(mergedArgs);
-  const providerModule = await loadProviderModule(provider);
-
-  let model = mergedArgs.model;
-  if (!model && extendConfig.default_model) {
-    if (provider === "google") model = extendConfig.default_model.google ?? null;
-    if (provider === "openai") model = extendConfig.default_model.openai ?? null;
-    if (provider === "dashscope") model = extendConfig.default_model.dashscope ?? null;
-    if (provider === "replicate") model = extendConfig.default_model.replicate ?? null;
-  }
-  model = model || providerModule.getDefaultModel();
-
-  const outputPath = normalizeOutputImagePath(mergedArgs.imagePath);
-
-  let imageData: Uint8Array;
-  let retried = false;
-
-  while (true) {
-    try {
-      imageData = await providerModule.generateImage(prompt, model, mergedArgs);
-      break;
-    } catch (e) {
-      if (!retried && isRetryableGenerationError(e)) {
-        retried = true;
-        console.error("Generation failed, retrying...");
-        continue;
-      }
-      throw e;
-    }
-  }
-
-  const dir = path.dirname(outputPath);
-  await mkdir(dir, { recursive: true });
-  await writeFile(outputPath, imageData);
-
-  if (mergedArgs.json) {
-    console.log(
-      JSON.stringify(
-        {
-          savedImage: outputPath,
-          provider,
-          model,
-          prompt: prompt.slice(0, 200),
-        },
-        null,
-        2
-      )
-    );
-  } else {
-    console.log(outputPath);
-  }
 }
 
-main().catch((e) => {
+main().catch((error) => {
-  const msg = e instanceof Error ? e.message : String(e);
+  const message = error instanceof Error ? error.message : String(error);
-  console.error(msg);
+  console.error(message);
   process.exit(1);
 });

skills/baoyu-image-gen/scripts/providers/openai.ts

@@ -68,7 +68,11 @@ export async function generateImage(
   const baseURL = process.env.OPENAI_BASE_URL || "https://api.openai.com/v1";
   const apiKey = process.env.OPENAI_API_KEY;
 
-  if (!apiKey) throw new Error("OPENAI_API_KEY is required");
+  if (!apiKey) {
+    throw new Error(
+      "OPENAI_API_KEY is required. Codex/ChatGPT desktop login does not automatically grant OpenAI Images API access to this script."
+    );
+  }
 
   if (process.env.OPENAI_IMAGE_USE_CHAT === "true") {
     return generateWithChatCompletions(baseURL, apiKey, prompt, model);

skills/baoyu-image-gen/scripts/providers/replicate.ts

@@ -36,22 +36,24 @@ function buildInput(prompt: string, args: CliArgs, referenceImages: string[]): R
 
   if (args.aspectRatio) {
     input.aspect_ratio = args.aspectRatio;
+  } else if (referenceImages.length > 0) {
+    input.aspect_ratio = "match_input_image";
   }
 
   if (args.n > 1) {
     input.number_of_images = args.n;
   }
 
+  if (args.quality === "normal") {
+    input.resolution = "1K";
+  } else if (args.quality === "2k") {
+    input.resolution = "2K";
+  }
+
   input.output_format = "png";
 
   if (referenceImages.length > 0) {
-    if (referenceImages.length === 1) {
+    input.image_input = referenceImages;
-      input.image = referenceImages[0];
-    } else {
-      for (let i = 0; i < referenceImages.length; i++) {
-        input[`image${i > 0 ? i + 1 : ""}`] = referenceImages[i];
-      }
-    }
   }
 
   return input;

skills/baoyu-image-gen/scripts/types.ts

@@ -13,10 +13,34 @@ export type CliArgs = {
   imageSize: string | null;
   referenceImages: string[];
   n: number;
+  batchFile: string | null;
+  jobs: number | null;
   json: boolean;
   help: boolean;
 };
 
+export type BatchTaskInput = {
+  id?: string;
+  prompt?: string | null;
+  promptFiles?: string[];
+  image?: string;
+  provider?: Provider | null;
+  model?: string | null;
+  ar?: string | null;
+  size?: string | null;
+  quality?: Quality | null;
+  imageSize?: "1K" | "2K" | "4K" | null;
+  ref?: string[];
+  n?: number;
+};
+
+export type BatchFile =
+  | BatchTaskInput[]
+  | {
+      tasks: BatchTaskInput[];
+      jobs?: number | null;
+    };
+
 export type ExtendConfig = {
   version: number;
   default_provider: Provider | null;
@@ -29,4 +53,16 @@ export type ExtendConfig = {
     dashscope: string | null;
     replicate: string | null;
   };
+  batch?: {
+    max_workers?: number | null;
+    provider_limits?: Partial<
+      Record<
+        Provider,
+        {
+          concurrency?: number | null;
+          start_interval_ms?: number | null;
+        }
+      >
+    >;
+  };
 };

skills/baoyu-translate/SKILL.md

@@ -212,6 +212,7 @@ Before translating chunks:
 - **Natural flow**: Use idiomatic target language word order and sentence patterns; break or restructure sentences freely when the source structure doesn't work naturally in the target language
 - **Terminology**: Use standard translations; annotate with original term in parentheses on first occurrence
 - **Preserve format**: Keep all markdown formatting (headings, bold, italic, images, links, code blocks)
+- **Image-language awareness**: Preserve image references exactly during translation, but after the translation is complete, review referenced images and check whether their likely main text language still matches the translated article language
 - **Frontmatter transformation**: If the source has YAML frontmatter, preserve it in the translation with these changes: (1) Rename metadata fields that describe the *source* article — `url`→`sourceUrl`, `title`→`sourceTitle`, `description`→`sourceDescription`, `author`→`sourceAuthor`, `date`→`sourceDate`, and any similar origin-metadata fields — by adding a `source` prefix (camelCase). (2) Translate the values of text fields (title, description, etc.) and add them as new top-level fields. (3) Keep other fields (tags, categories, custom fields) as-is, translating their values where appropriate
 - **Respect original**: Maintain original meaning and intent; do not add, remove, or editorialize — but sentence structure and imagery may be adapted freely to serve the meaning
 - **Translator's notes**: For terms, concepts, or cultural references that target readers may not understand — due to jargon, cultural gaps, or domain-specific knowledge — add a concise explanatory note in parentheses immediately after the term. The note should explain *what it means* in plain language, not just provide the English original. Format: `译文（English original，通俗解释）`. Calibrate annotation depth to the target audience: general readers need more notes than technical readers. Only add notes where genuinely needed; do not over-annotate obvious terms.
@@ -250,6 +251,20 @@ Each step reads the previous step's file and builds on it.
 
 Final translation is always at `translation.md` in the output directory.
 
+After the final translation is written, do a lightweight image-language pass:
+
+1. Collect image references from the translated article
+2. Identify likely text-heavy images such as covers, screenshots, diagrams, charts, frameworks, and infographics
+3. If any image likely contains a main text language that does not match the translated article language, proactively remind the user
+4. The reminder must be a list only. Do not automatically localize those images unless the user asks
+
+Reminder format (use whatever image syntax the article already uses — standard markdown or wikilink):
+```text
+Possible image localization needed:
+- ![example cover](attachments/example-cover.png): likely still contains source-language text while the article is now in target language
+- ![example diagram](attachments/example-diagram.png): likely text-heavy framework graphic, check whether labels need translation
+```
+
 Display summary:
 ```
 **Translation complete** ({mode} mode)
@@ -261,6 +276,8 @@ Final: {output-dir}/translation.md
 Glossary terms applied: {count}
 ```
 
+If mismatched image-language candidates were found, append a short note after the summary telling the user that some embedded images may still need image-text localization, followed by the candidate list.
+
 ## Extension Support
 
 Custom configurations via EXTEND.md. See **Preferences** section for paths and supported options.