SuperAPI AI Directory

image-lowlight-enhance

Design & creation

View repository

Updated 10-16 06:46

About this skill

Image lowlight enhancement (image-lowlight-enhance)

Overview

Intelligent brightness boost and dark-area detail recovery for low-light/night scene/underexposed images. Covers night scene shooting brightening, low-light environment photo repair, underexposure rescue, and backlight/high-contrast scene fill light; brightens dark areas while keeping highlights from overexposing, with automatic suppression of noise in dark areas. Only requires image_url, no prompt needed.

Before execution, the user should clearly know: this Skill will read Meitu credentials, call the local meitu CLI, send the user-provided image URL to Meitu OpenAPI for processing, and write the result to ./output/ or $VISUAL/output/image-lowlight-enhance/。

API Mapping

  • Low-light/night scene image enhancement:image_lowlight_enhance

Dependencies

  • meitu-cli: >=2.0.6(npm install -g meitu-cli@latest)
  • Credentials:CONFIG AKSK → meitu tools update; EXEC AKSK → actual execution (see root CONFIG.md)
  • Environment variables:MEITU_OPENAPI_TOOL_TASK_MODE=command

Path alias:$VISUAL = {OPENCLAW_HOME}/workspace/visual/

Core Workflow

Preflight → Execute → Deliver

Preflight

  1. meitu --version ≥ 2.0.6 (otherwise npm install -g meitu-cli@latest)
  2. Confirm that meitu tools updatehas been run (using CONFIG AKSK)
  3. Current AKSK = EXEC, and MEITU_OPENAPI_TOOL_TASK_MODE=command
  4. Resolve output_dir: openclaw.yaml → ./output/ |else → $VISUAL/output/image-lowlight-enhance/;mkdir -p

Execute

Trigger signals / routing rules

Scenario Decision keywords Route
Too dark / night scene / underexposed Too dark, night scene, brighten, low light, backlight, underexposed image_lowlight_enhance

Decision order:

  1. image_url missing → ask follow-up
  2. Only route: call image_lowlight_enhance

Single API tool: call when parameters are complete; after a failure, retry once and then return an error; do not fall back across tools. If the image itself is properly exposed → call normally and tell the user "the original image is properly exposed; after enhancement it may be too bright." Extremely underexposed (pure black) → call normally; the effect may be limited.

Parameter definitions

Parameter Type Required Range Default value Description
image_url STRING Yes -- -- Image address. If missing → prompt "Please provide the image to be enhanced"

Tool invocation

meitu image-lowlight-enhance \
  --skill_name skill_image-lowlight-enhance \
  --image_url <image_url> \
  --json \
  --download-dir {output_dir}

Error degradation

Scenario Handling method
image_url missing Prompt "Please provide the image to be enhanced"
image_url inaccessible Directly return an invalid image link error; do not retry
The image itself is properly exposed Call normally and inform "the original image is properly exposed; after enhancement it may be too bright"
Extremely underexposed (pure black) Call normally; the effect may be limited; inform the user
image_lowlight_enhance call failed Retry once; if it still fails, return an error
Content compliance interception Return a compliance prompt; do not retry
Video input Reject; only images are supported

Deliver

  • Directly use the output_dir resolved by Preflight
  • From downloaded_files[0].saved_path read the downloaded file path
  • mv {downloaded_files[0].saved_path} {output_dir}/{YYYY-MM-DD}_{descriptive}_image-lowlight-enhance.jpg

Output

  • Format: JPEG/PNG (keep the original format)
  • Naming:{YYYY-MM-DD}_{descriptive}_image-lowlight-enhance.jpg
  • Location: project → ./output/, one-time → $VISUAL/output/image-lowlight-enhance/

Baseline Task ID

See references/task-id-baseline.md for the corresponding row.