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-portrait-generategit 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-portrait-generate)<a href="https://agentmods.dev/skills/meitu/meitu-skills/image-portrait-generate"><img src="https://agentmods.dev/badge/skills/meitu/meitu-skills/image-portrait-generate/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-portrait-generate"><img src="https://agentmods.dev/badge/skills/meitu/meitu-skills/image-portrait-generate.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 | $0.00075 | $0.01805 |
| Opus 5 | $0.00037 | $0.00903 |
| Sonnet 5 | $0.00015 | $0.00361 |
| Haiku 4.5 | $0.00007 | $0.00180 |
Grade A, and why
image-portrait-generate 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 12d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Image Portrait Generate
Overview
从参考图（人像/宠物）生成高精度写真，覆盖单人/宠物/多人写真（证件照/形象照/艺术照/发型调整/场景变换）和双人合影合成。支持 2K/4K 分辨率。仅在用户明确要求写真生成或双人合照合成时触发，不用于泛化的“合影”“团体照”闲聊场景。
API Mapping
- 单人/宠物/多人写真（主）：
image_gummy_edit_v45 - 单人/宠物写真降级（兜底）：
image_mint_portrait_edit_2k - 双人合影合成：
image_groupphoto2_edit - model 映射：
auto（默认）/gummy_pro→v45 /mint_portrait→mint_2k
Dependencies
- meitu-cli:
>=2.0.6 - 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：
$VISUAL={OPENCLAW_HOME}/workspace/visual/
Core Workflow
Preflight → Execute → Deliver
Preflight
meitu --version≥ 2.0.6- 已用 CONFIG AKSK 跑过
meitu tools update - 当前 AKSK = EXEC，
MEITU_OPENAPI_TOOL_TASK_MODE=command - output_dir：openclaw.yaml →
./output/｜else →$VISUAL/output/image-portrait-generate/；mkdir -p
Execute
触发信号 / 路由规则
核心维度：输入图片数 + 合影信号。
| 场景 | 判定关键词 | 图片数 | 路由 |
|---|---|---|---|
| 双人合影 | 合影、合照、两个人合成 | 恰好 2 | image_groupphoto2_edit |
| 双人合影但不足 2 张 | 合影 | 1 | 提示"请提供两张人像照片" |
| 双人合影但超过 2 张 | 合影 | >2 | 取前 2 张 + 告知 |
| 单人 / 宠物写真 | 写真、证件照、形象照、发型、宠物写真 | 1 或 >1 | image_gummy_edit_v45 → image_mint_portrait_edit_2k |
| 多人写真（3 人+） | 团体照、3 人写真 | 1（多人图） | image_gummy_edit_v45（不降级） |
| 意图不明 + 2 张图 | -- | 2 | 默认走单人写真 |
参数定义
| 参数 | 类型 | 必填 | 范围 | 默认 | 说明 |
|---|---|---|---|---|---|
image_list |
ARRAY[STRING] | 是 | 1–N 张 | -- | 人像/宠物图片 URL 数组 |
prompt |
STRING | 是 | -- | -- | 写真描述；缺失时根据上下文自动生成 |
size |
STRING | 否 | 2K / 4K | 2K | 输出分辨率（仅 image_gummy_edit_v45 支持） |
API 映射说明：
image_gummy_edit_v45（主）：image_list[0]→image_url（API 本身支持多人），prompt/size直传image_mint_portrait_edit_2k（降级）：image_list[0]→image_url，prompt直传image_groupphoto2_edit（双人合影）：image_list数组（必须恰好 2 张），prompt→instruction（非中英文自动翻译为中文）；固定参数lora_key=multi_duorenhezhao_2k、rsp_media_type=url
证件照 + 指定底色（蓝/白/红）：在 prompt 中写入底色要求（如"蓝色纯色背景证件照"）。
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.
- 12d ago First seen · 133 lines · 75 tokens per session scan A 9e5bcc7b1a6b
image-portrait-generate is a skill published in the GitHub repository meitu/meitu-skills (32 stars, last pushed 14d ago), licensed MIT. It adds 75 tokens to every session and 1,805 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.