Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add meitu/meitu-skills --skill image-lowlight-enhancegit clone --depth 1 https://github.com/meitu/meitu-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/meitu/meitu-skills/image-lowlight-enhance)<a href="https://agentmods.dev/skills/meitu/meitu-skills/image-lowlight-enhance"><img src="https://agentmods.dev/badge/skills/meitu/meitu-skills/image-lowlight-enhance/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/meitu/meitu-skills/image-lowlight-enhance"><img src="https://agentmods.dev/badge/skills/meitu/meitu-skills/image-lowlight-enhance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 5 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 9 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 11 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 17 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Rogue Agent · line 21 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.01382 |
| Opus 5.5 | $0.00030 | $0.00553 |
| Sonnet 5.5 | $0.00015 | $0.00276 |
| Haiku 4.5 | $0.00008 | $0.00138 |
Grade A, and why
image-lowlight-enhance scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
图片暗部增强（image-lowlight-enhance）
Overview
暗光/夜景/曝光不足图片的智能亮度提升与暗部细节恢复。覆盖夜景拍摄提亮、暗光环境照片修复、曝光不足挽救、逆光/高对比场景补光；保持亮部不过曝的前提下提亮暗部、暗部噪点自动抑制。仅需 image_url，不需要 prompt。
执行前应让用户清楚知道：本 Skill 会读取 Meitu 凭证、调用本地 meitu CLI、将用户提供的图片 URL 发送到 Meitu OpenAPI 处理，并把结果写入 ./output/ 或 $VISUAL/output/image-lowlight-enhance/。
API Mapping
- 暗光/夜景图片增强：
image_lowlight_enhance
Dependencies
- meitu-cli:
>=2.0.6（npm install -g meitu-cli@latest） - 凭证：CONFIG AKSK →
meitu tools update；EXEC AKSK → 实际执行（见根CONFIG.md） - 环境变量：
MEITU_OPENAPI_TOOL_TASK_MODE=command
路径别名：
$VISUAL={OPENCLAW_HOME}/workspace/visual/
Core Workflow
Preflight → Execute → Deliver
Preflight
meitu --version≥ 2.0.6（否则npm install -g meitu-cli@latest）- 确认已跑过
meitu tools update（用 CONFIG AKSK） - 当前 AKSK = EXEC，且
MEITU_OPENAPI_TOOL_TASK_MODE=command - 解析 output_dir：openclaw.yaml →
./output/｜else →$VISUAL/output/image-lowlight-enhance/；mkdir -p
Execute
触发信号 / 路由规则
| 场景 | 判定关键词 | 路由 |
|---|---|---|
| 太暗 / 夜景 / 曝光不足 | 太暗、夜景、提亮、暗光、逆光、曝光不足 | image_lowlight_enhance |
决策顺序：
image_url缺失 → 追问- 唯一路由：调用
image_lowlight_enhance
单 API 工具：参数齐全即调用，失败重试 1 次后返回错误；不做跨工具兜底。图片本身曝光正常 → 正常调用，告知用户"原图曝光正常，增强后可能偏亮"。极度欠曝（纯黑）→ 正常调用，效果可能有限。
参数定义
| 参数 | 类型 | 必填 | 范围 | 默认值 | 说明 |
|---|---|---|---|---|---|
image_url |
STRING | 是 | -- | -- | 图片地址。缺失 → 提示"请提供需要增强的图片" |
工具调用
meitu image-lowlight-enhance \
--skill_name skill_image-lowlight-enhance \
--image_url <image_url> \
--json \
--download-dir {output_dir}
错误降级
| 场景 | 处理方式 |
|---|---|
image_url 缺失 |
提示"请提供需要增强的图片" |
image_url 不可访问 |
直接返回图片链接无效错误，不重试 |
| 图片本身曝光正常 | 正常调用，告知"原图曝光正常，增强后可能偏亮" |
| 极度欠曝（纯黑） | 正常调用，效果可能有限，告知用户 |
image_lowlight_enhance 调用失败 |
重试 1 次，仍失败返回错误 |
| 内容合规拦截 | 返回合规提示，不重试 |
| 视频输入 | 拒绝，仅支持图片 |
Deliver
- 直接使用 Preflight 解析的 output_dir
- 从
downloaded_files[0].saved_path读取已下载文件路径 mv {downloaded_files[0].saved_path} {output_dir}/{YYYY-MM-DD}_{descriptive}_image-lowlight-enhance.jpg
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 121 lines · 76 tokens per session scan A 5c986016d729
image-lowlight-enhance is a skill published in the GitHub repository meitu/meitu-skills (36 stars, last pushed 2mo ago), licensed MIT. It adds 76 tokens to every session and 1,382 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
image-lowlight-enhance compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| image-lowlight-enhancemeitu/meitu-skills | Skill | 36 | 2mo ago | MIT | A | 76 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |