القائمة
根据文字、参考图、公网图片 URL 或本地照片制作可直接打印裁剪的证件照。只要用户提到证件照、报名照、护照照、白底/蓝底/红底换底、1寸/2寸、证件照排版、证件照打印、或想把普通照片变成证件照，都应使用这个 skill。默认优先处理用户已有照片；只有缺图或用户明确要求时，才调用 Liblib 的文生图或图生图。
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | id-photo-maker |
| description | 根据文字、参考图、公网图片 URL 或本地照片制作可直接打印裁剪的证件照。只要用户提到证件照、报名照、护照照、白底/蓝底/红底换底、1寸/2寸、证件照排版、证件照打印、或想把普通照片变成证件照，都应使用这个 skill。默认优先处理用户已有照片；只有缺图或用户明确要求时，才调用 Liblib 的文生图或图生图。 |
把证件照制作变成稳定、可重复的执行流程：先判断输入来源，再收集缺失参数，然后按需走 Liblib 生图或本地照片处理，最后输出可直接打印裁剪的静态排版页。
Works best with bash and Python 3.11+. Liblib API calls use only Python stdlib. Photo processing needs Pillow and rembg, ideally inside this skill's local .venv.
A4 和 6寸 两种打印页。必须收集：
按需收集：
AccessKey / SecretKey.env.local如果缺少这些信息，主动追问。优先一问一答，不要一口气抛太多问题。
文字描述，没有现成照片
scripts/generate_via_liblib.py text2img ...scripts/process_local_photo.py ...scripts/render_print_sheet.py ...本地照片
scripts/process_local_photo.py ...scripts/render_print_sheet.py ...公网图片 URL
sourceImage 传给 Liblib，成功后再做后处理和排版。prompt 使用纯英文。clean studio lightingfront-facing personrealistic faceformal ID photocentered compositionplain backgroundhigh detailno watermarkcontrolType: depth | pose | line | IPAdaptercontrolImage: <public URL>~/.copilot/skills/id-photo-maker/.env.localAccessKey 与 SecretKeyLIBLIB_ACCESS_KEY=... / LIBLIB_SECRET_KEY=... 的形式写入 .env.localSecretKey。如果 skill 目录有 .venv/bin/python，优先用它；否则用 python3。
python3 ~/.copilot/skills/id-photo-maker/scripts/generate_via_liblib.py \
text2img \
--prompt "front-facing young woman, formal chinese id photo, clean studio light, realistic face, centered composition, plain background, high detail, no watermark" \
--aspect-ratio portrait \
--output-dir /tmp/id-photo-run/generated
python3 ~/.copilot/skills/id-photo-maker/scripts/generate_via_liblib.py \
img2img \
--prompt "formal id photo, realistic face, centered composition, clean studio light, no watermark" \
--source-image-url "https://example.com/reference.png" \
--output-dir /tmp/id-photo-run/generated
python3 ~/.copilot/skills/id-photo-maker/scripts/process_local_photo.py \
/tmp/id-photo-run/generated/liblib-1.png \
--size 1寸 \
--background white \
--framing standard \
--output-dir /tmp/id-photo-run/processed
python3 ~/.copilot/skills/id-photo-maker/scripts/render_print_sheet.py \
--photo /tmp/id-photo-run/processed/id-photo.png \
--size 1寸 \
--pages a4,6inch \
--output-dir /tmp/id-photo-run/print
默认交付：
id-photo.png：标准尺寸成片metadata.json：尺寸、背景、构图、来源与导出信息print-a4.htmlprint-6inch.htmlindex.html：打印页入口scripts/id_photo_common.py - shared size presets, color parsing, and download helpersscripts/credential_store.py - .env.local credential read/writescripts/liblib_client.py - Liblib API signing, request, polling, and downloadscripts/generate_via_liblib.py - CLI for text2img / img2imgscripts/process_local_photo.py - local / URL photo processing, background replacement, and exportscripts/render_print_sheet.py - A4 / 6寸 printable HTML sheet generationreferences/size-presets.md - supported presets and physical dimensionsreferences/workflow-rules.md - routing, prompt, and questioning rulesreferences/liblib-auth.md - AK/SK signing model and request rulesassets/print.css - print-safe stylesheetrequirements.txt - Python dependenciesConvert rough business requirements into complete, implementation-ready solution blueprints in Chinese. Use this whenever the user asks for 业务实现方案, 技术方案, 架构设计, PRD转实现, 需求拆解, 数据模型, 状态流转, 接口设计, or wants a coding agent to build directly from a high-level requirement, even if the input is incomplete.
Review C#, ASP.NET Core, and .NET 10 pull requests or code diffs with a practical checklist focused on correctness, nullability, async/await, EF Core, DI, security, performance, observability, and tests. Use this skill whenever the user asks for a C#/.NET code review, PR review, diff review, checklist-based review, best-practices validation, 架构审查, or wants actionable findings instead of style-only comments.
Investigate whether a news item, rumor, screenshot claim, social post, statement, image/video description, or link is true, partly true, misleading, false, or still unverified. Use this skill whenever the user asks to 辟谣, 事实核查, 查证真假, verify a claim, analyze a screenshot/link/post, or wants a source-backed judgment instead of a quick opinion, especially for politics, disasters, war, public safety, medicine, finance, law, and other high-risk topics.
Classify complex user requests into the right execution loop, define stop conditions, validation checks, token/cost boundaries, and whether to execute or only plan based on current permissions. Use for multi-step coding tasks, automation, monitoring, scheduled work, quality gates, repeated iteration, vague complex goals, or any request where Codex should decide between turn-based, goal-based, time-based, or proactive loops. Do not use for simple factual questions or tiny one-step edits.
Export Markdown files to polished, print-ready PDFs and set up reusable local export scripts. Use this skill whenever the user wants Markdown converted to PDF, asks for one-click export automation, needs reusable styling presets, or wants to tune margins, fonts, images, or page layout for resumes, reports, manuals, proposals, or summaries. Default to a script-based workflow instead of a one-off manual conversion.
从本地照片文件夹中按专业摄影标准筛选出值得精修的照片。先生成联络表，再做多轮挑片，最后把终选片复制到“精修”文件夹。macOS 默认走原生 JXA，Linux 和 Windows 可走 Python Pillow 后端。