@comate/zulu 1.2.1-beta.2 → 1.3.0

package/comate-engine/assets/skills/create-image-comate/SKILL.md

@@ -0,0 +1,278 @@
+---
+name: create-image
+description: "Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K resolution."
+metadata:
+    enableWhen:
+        - isInternal
+---
+
+# Nano Banana Pro Image Generation & Editing
+
+Generate new images or edit existing ones using Google's Nano Banana Pro API (Gemini 3 Pro Image) via curl.
+
+## Requirements
+
+### macOS / Linux
+
+- `curl` and `jq` must be installed
+- `base64` built-in
+- `sips` for auto-resolution detection (macOS built-in)
+- `identify` for auto-resolution detection (Linux, via `imagemagick`)
+
+### Windows
+
+- `curl.exe` built-in (Windows 10 1803+)
+- PowerShell 5.1+ built-in (Windows 10+), used for all JSON parsing
+
+### Common
+
+- API endpoint: `https://comate.baidu-int.com/api/aidevops/autocomate/rest/autowork/v1/generate-image`
+- Username is passed via Header `login-name`, NOT in the request body
+- Username: ${COMATE_USERNAME}
+
+---
+
+## Usage
+
+**Important:** Always save output images to the user's current working directory.
+
+### 1. Generate new image (text-to-image)
+
+**macOS / Linux (bash/zsh):**
+
+```bash
+curl -s -X POST https://comate.baidu-int.com/api/aidevops/autocomate/rest/autowork/v1/generate-image \
+  -H "Content-Type: application/json" \
+  -H "login-name: ${COMATE_USERNAME}" \
+  -d '{
+    "contents": [{"parts": [{"text": "YOUR_PROMPT_HERE"}]}],
+    "resolution": "1K"
+  }' \
+  | jq -r '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data' \
+  | base64 --decode > output-name.png
+```
+
+**Windows (PowerShell):**
+
+```powershell
+# Write JSON to temp file to avoid PowerShell double-quote escaping bug with curl.exe -d
+$tmpFile = "$env:TEMP\request.json"
+@'
+{"contents":[{"parts":[{"text":"YOUR_PROMPT_HERE"}]}],"resolution":"1K"}
+'@ | Set-Content -Path $tmpFile -Encoding UTF8 -NoNewline
+
+$response = curl.exe -s -X POST https://comate.baidu-int.com/api/aidevops/autocomate/rest/autowork/v1/generate-image `
+  -H "Content-Type: application/json" `
+  -H "login-name: $env:${COMATE_USERNAME}" `
+  -d "@$tmpFile" | ConvertFrom-Json
+
+$imgBase64 = $response.candidates[0].content.parts |
+  Where-Object { $_.inlineData } |
+  Select-Object -First 1 -ExpandProperty inlineData |
+  Select-Object -ExpandProperty data
+[System.IO.File]::WriteAllBytes(
+  (Join-Path (Get-Location) "output-name.png"),
+  [System.Convert]::FromBase64String($imgBase64)
+)
+```
+
+### 2. Edit existing image (image-to-image)
+
+**base64 image data is large — must write to a temp file, never inline in the command.**
+
+**macOS / Linux (bash/zsh):**
+
+```bash
+# Step 1: encode input image
+IMG_B64=$(base64 -i path/to/input.png | tr -d '\n')
+
+# Step 2: write JSON to temp file
+cat > /tmp/request.json << EOF
+{
+  "contents": [
+    {
+      "parts": [
+        {"inline_data": {"mime_type": "image/png", "data": "${IMG_B64}"}},
+        {"text": "YOUR_EDIT_INSTRUCTIONS_HERE"}
+      ]
+    }
+  ],
+  "resolution": "2K"
+}
+EOF
+
+# Step 3: send request
+curl -s -X POST https://comate.baidu-int.com/api/aidevops/autocomate/rest/autowork/v1/generate-image \
+  -H "Content-Type: application/json" \
+  -H "login-name: ${COMATE_USERNAME}" \
+  -d @/tmp/request.json \
+  | jq -r '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data' \
+  | base64 --decode > output-name.png
+```
+
+**Windows (PowerShell):**
+
+```powershell
+# Step 1: encode input image
+$imgBytes  = [System.IO.File]::ReadAllBytes((Resolve-Path "path\to\input.png"))
+$imgBase64 = [System.Convert]::ToBase64String($imgBytes)
+
+# Step 2: write JSON to temp file
+$tmpFile = "$env:TEMP\request.json"
+@"
+{
+  "contents": [
+    {
+      "parts": [
+        {"inline_data": {"mime_type": "image/png", "data": "$imgBase64"}},
+        {"text": "YOUR_EDIT_INSTRUCTIONS_HERE"}
+      ]
+    }
+  ],
+  "resolution": "2K"
+}
+"@ | Set-Content -Path $tmpFile -Encoding UTF8
+
+# Step 3: send request
+$response = curl.exe -s -X POST https://comate.baidu-int.com/api/aidevops/autocomate/rest/autowork/v1/generate-image `
+  -H "Content-Type: application/json" `
+  -H "login-name: $env:${COMATE_USERNAME}" `
+  -d "@$tmpFile" | ConvertFrom-Json
+
+$outBase64 = $response.candidates[0].content.parts |
+  Where-Object { $_.inlineData } |
+  Select-Object -First 1 -ExpandProperty inlineData |
+Select-Object -ExpandProperty data
+
+[System.IO.File]::WriteAllBytes(
+  (Join-Path (Get-Location) "output-name.png"),
+  [System.Convert]::FromBase64String($outBase64)
+)
+```
+
+---
+
+## Default Workflow (draft > iterate > final)
+
+- Draft (1K): quick feedback loop
+- Iterate: adjust prompt in small diffs; keep filename new per run
+- Final (4K): only when prompt is locked
+
+## Resolution Options
+
+- **1K** (default) - ~1024px, use for drafts and quick feedback
+- **2K** - ~2048px, use for mid-quality or medium-size input images
+- **4K** - ~4096px, use only when prompt is locked and quality is required
+
+---
+
+## Auto-Resolution Detection (image-to-image only)
+
+When editing an existing image and the user has not specified a resolution,
+auto-detect based on the input image's longest edge.
+
+**macOS (bash/zsh):**
+
+```bash
+MAX_DIM=$(sips -g pixelWidth -g pixelHeight "input.png" \
+  | awk '/pixel/{print $2}' | sort -rn | head -1)
+
+if   [ "${MAX_DIM}" -ge 3000 ]; then RESOLUTION="4K"
+elif [ "${MAX_DIM}" -ge 1500 ]; then RESOLUTION="2K"
+else                                  RESOLUTION="1K"
+fi
+```
+
+**Linux (bash):**
+
+```bash
+# requires: apt install imagemagick  /  yum install imagemagick
+MAX_DIM=$(identify -format "%[fx:max(w,h)]" input.png)
+
+if   [ "${MAX_DIM}" -ge 3000 ]; then RESOLUTION="4K"
+elif [ "${MAX_DIM}" -ge 1500 ]; then RESOLUTION="2K"
+else                                  RESOLUTION="1K"
+fi
+```
+
+**Windows (PowerShell):**
+
+```powershell
+Add-Type -AssemblyName System.Drawing
+$img        = [System.Drawing.Image]::FromFile((Resolve-Path "input.png"))
+$maxDim     = [Math]::Max($img.Width, $img.Height)
+$img.Dispose()
+
+$resolution = if     ($maxDim -ge 3000) { "4K" }
+              elseif ($maxDim -ge 1500) { "2K" }
+              else                      { "1K" }
+```
+
+---
+
+## Prompt Handling
+
+**For generation:** Pass the user's image description as-is to the `text` field.
+**For editing:** Pass editing instructions to the `text` field alongside the `inline_data` image part.
+
+---
+
+## Output
+
+- Saves PNG to current directory
+- Script outputs the full path to the generated image
+- **Do not read the image back** - display the image using markdown syntax: `![image](relative/path/to/image.png)`
+- **Display the image path only once** using a relative path (e.g. `output-name.png` or `subdir/output-name.png`);
+- do NOT display absolute paths (e.g. `/home/user/...` formats are forbidden); do NOT repeat the path multiple times in
+  the conversation
+
+---
+
+## Notes
+
+| Rule              | macOS/Linux                         | Windows                                                                                                                      |
+|-------------------|-------------------------------------|------------------------------------------------------------------------------------------------------------------------------|
+| curl command      | `curl`                              | `curl.exe` (avoid PowerShell `curl` alias conflict)                                                                          |
+| `-d` body         | inline `'{"key":"val"}'` is fine    | **never** inline — PowerShell escapes `"` to `\u0022`, corrupts JSON; **always** write to temp file and use `-d "@$tmpFile"` |
+| base64 encode     | `base64 -i file \| tr -d '\n'`      | `[Convert]::ToBase64String([IO.File]::ReadAllBytes(...))`                                                                    |
+| base64 decode     | `base64 --decode`                   | `[IO.File]::WriteAllBytes(path, [Convert]::FromBase64String(...))` (PS 5.1 compatible)                                       |
+| image size detect | `sips` (macOS) / `identify` (Linux) | `System.Drawing.Image` (built-in)                                                                                            |
+| line continuation | `\`                                 | `` ` `` (backtick)                                                                                                           |
+| env variable      | `${COMATE_USERNAME}`                | `$env:COMATE_USERNAME`                                                                                                       |
+
+---
+
+## Windows Pitfall: PowerShell escapes `"` when passing to external programs
+
+When PowerShell passes a variable containing `"` to an external program like `curl.exe`,
+it silently converts `"` into `\u0022`, which corrupts JSON and causes the server to return:
+
+```
+JsonParseException: Unexpected character ('u'): was expecting double-quote to start field name
+```
+
+**Wrong (never do this on Windows):**
+
+```powershell
+$body = '{"contents":[...]}'
+curl.exe ... -d $body        # PowerShell corrupts the " characters
+```
+
+**Correct — always write JSON to a temp file and pass with `-d @file`:**
+
+```powershell
+# Single-quote here-string: content is taken literally, no escaping
+$tmpFile = "$env:TEMP\request.json"
+@'
+{"contents":[{"parts":[{"text":"YOUR_PROMPT_HERE"}]}],"resolution":"1K"}
+'@ | Set-Content -Path $tmpFile -Encoding UTF8 -NoNewline
+
+curl.exe ... -d "@$tmpFile"  # curl reads the file directly, no PowerShell escaping
+```
+
+**Here-string type selection:**
+
+| Situation                                  | Here-string type       | Reason                          |
+|--------------------------------------------|------------------------|---------------------------------|
+| text-to-image (no variables in JSON)       | `@'...'@` single-quote | content taken literally, safest |
+| image-to-image (need `$imgBase64` in JSON) | `@"..."@` double-quote | allows variable expansion       |