Token导航 LogoToken导航

Agent Skill · 研究检索

photo-management(照片管理)

用于辅助图像生成、图片编辑、视觉素材处理或图像模型工作流。它适合让 Agent 根据文本生成图片、处理背景、整理视觉提示词或调用相关图像工具。使用时需要确认输入图片、版权来源、输出格式和模型限制;涉及人物、品牌、商品或公开展示素材时,应额外核对授权、真实性和内容合规边界。

photo-management 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 62,939。

总安装 324周安装 13GitHub Stars 11下载 105核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:photo-management(照片管理)
来源仓库:https://github.com/peterbamuhigire/skills-web-dev
仓库路径:skills/photo-management
安装命令:
npx skills add https://github.com/peterbamuhigire/skills-web-dev --skill photo-management
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/peterbamuhigire/skills-web-dev --skill photo-management

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于辅助图像生成、图片编辑、视觉素材处理和图像模型工作流。适合让 Agent 根据文本生成图片、处理背景或整理视觉提示词。使用时需要确认输入图片、版权来源、输出格式和模型限制。涉及人物、品牌或公开展示素材时,应核对授权、真实性和内容合规边界。

photo-management 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/photo-management

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/peterbamuhigire/skills-web-dev --skill photo-m…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

photo-management 怎么安装?

在终端执行 npx skills add https://github.com/peterbamuhigire/skills-web-dev --skill photo-management。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

photo-management 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

photo-management 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

photo-management 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

photo-management 用的人多吗?

公开数据是累计安装 324 次,近一周安装 13 次,下载 105 次,GitHub 11 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

photo-management 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
photo-management

照片管理 · 本页

32411需要联网未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Platform Notes

  • Optional helper plugins may help in some environments, but they must not be treated as required for this skill.

Photo Management

Use When

  • Manage photo uploads, previews, storage, and deletion across the app. Use when building any photo upload UI or API, and always apply client-side compression via image-compression before upload.
  • The task needs reusable judgment, domain constraints, or a proven workflow rather than ad hoc advice.

Do Not Use When

  • The task is unrelated to photo-management or would be better handled by a more specific companion skill.
  • The request only needs a trivial answer and none of this skill's constraints or references materially help.

Required Inputs

  • Gather relevant project context, constraints, and the concrete problem to solve.
  • Confirm the desired deliverable: design, code, review, migration plan, audit, or documentation.

Workflow

  • Read this SKILL.md first, then load only the referenced deep-dive files that are necessary for the task.
  • Apply the ordered guidance, checklists, and decision rules in this skill instead of cherry-picking isolated snippets.
  • Produce the deliverable with assumptions, risks, and follow-up work made explicit when they matter.

Quality Standards

  • Keep outputs execution-oriented, concise, and aligned with the repository's baseline engineering standards.
  • Preserve compatibility with existing project conventions unless the skill explicitly requires a stronger standard.
  • Prefer deterministic, reviewable steps over vague advice or tool-specific magic.

Anti-Patterns

  • Treating examples as copy-paste truth without checking fit, constraints, or failure modes.
  • Loading every reference file by default instead of using progressive disclosure.

Outputs

  • A concrete result that fits the task: implementation guidance, review findings, architecture decisions, templates, or generated artifacts.
  • Clear assumptions, tradeoffs, or unresolved gaps when the task cannot be completed from available context alone.
  • References used, companion skills, or follow-up actions when they materially improve execution.

Evidence Produced

CategoryArtifactFormatExample
CorrectnessPhoto upload + lifecycle test planMarkdown doc covering upload, preview, deletion, and storage-cleanup scenariosdocs/photos/lifecycle-tests.md
Data safetyPhoto storage and retention noteMarkdown doc covering bucket layout, signed URL TTL, and retention policydocs/photos/storage-retention.md

References

  • Use the links and companion skills already referenced in this file when deeper context is needed.

Overview

Standardize photo upload UX, storage, and deletion patterns for all modules (DPC shops, assets, products, staff, etc.). Always compress images before upload using the Image Compression skill.

Security Baseline (Required)

Always load and apply the Vibe Security Skill for upload flows (XSS, CSRF, file validation, path traversal, and access control are mandatory).

Cross-Platform: Upload code runs on Windows (dev) and Linux (staging/production). Use forward-slash paths in PHP. Check is_dir() before mkdir(). File permissions: use 0755 for directories, 0644 for files. Never hardcode Windows paths in upload logic.

Entity Photo Rules (Mandatory)

A) People / Individual Entities (1 photo max)

Examples: distributor, client, customer, employee, student, patient, member.

  • Limit: 1 photo per individual.
  • Default image: uploads/<entity>/default.jpg (always present).
  • Card list view: Use a social media-style card (like staff-list.php) with:

- Circular avatar. - Banner background: uploads/<entity>/background.jpg. - Status + quick actions.

  • Detail view: Show the avatar prominently with edit/upload UI near it.

B) Non‑People Entities (3 photos max)

Examples: products, farms, vehicles, animals, crops, stock items, buildings, assets, shops.

  • Limit: 3 photos per entity.
  • Default image: uploads/<entity>/default.jpg.
  • Card list view: Use a banner-style card (like dpcs.php):

- Banner image = random pick among the 3 photos. - If none, use default.jpg.

  • Detail view: show minimal gallery (3-photo grid) above tabs (like dpc-details.php).

Quick Reference

  • UI upload flow: compress → preview → auto-upload → reload gallery
  • Storage: per-module folders in uploads/ with defaults
  • Deletion: confirm → delete DB row → delete file
  • Limits: hide upload UI when max count reached

Core Instructions

  1. Always apply compression

- Load and use image-compression rules. - Use window.prepareImageUpload() for client-side compression.

  1. Validate on server

- Enforce file type and size limits. - Verify franchise ownership before write/delete.

  1. Keep UX minimal

- Auto-upload on file selection. - Use SweetAlert2 for errors and confirmations.

  1. Respect limits

- 1 photo for people; 3 photos for non-people entities. - Hide upload UI when limit reached.

Minimalistic Detail Page Pattern (3‑Photo Entities)

Follow the dpc-details.php approach:

  • Photo section above tabs, compact, 3 columns.
  • Auto-upload on file selection (no explicit “Upload” button).
  • Upload UI hidden when 3 photos exist.
  • Lightbox preview on click.
  • Delete button overlay only when permission is granted.

Card List Pattern

Non‑People Entities (banner cards)

  • Banner image = random pick among the 3 photos.
  • If none, fallback to default.jpg.
  • Keep the card minimal: image + name + status + 1–2 meta lines.

People Entities (social cards)

  • Use background.jpg as banner.
  • Circular avatar (photo or default.jpg).
  • Name + role/position + 1–2 meta lines.
  • Actions inline (view/edit) with compact buttons.
  • Ensure the avatar overlap is visible (no clipping): set card overflow: visible or position avatar inside banner with position: absolute and higher z-index.
  • Prefer overlapping only the avatar (not the text): apply negative margin to the avatar itself, keep header text flow normal.

Key Patterns

Upload (client)

  • Input change → compress → size check → FormData → POST → reload gallery.

Gallery (client)

  • Render a grid with a max of 3 items.
  • Hide uploader when full.
  • Show delete button only for authorized users.

API (server)

  • GET: return photo list with URLs.
  • POST: validate, store, insert DB row.
  • DELETE: validate ownership, remove DB row and file.

API Response Format (Align with Maduuka)

Use the standard JSON envelope used across the app:

  • Success:

- success: true, message, data, timestamp

  • Validation error:

- success: false, message, errors

Keep payloads lean: return only id, file_name, file_path, created_at.

Database Schema Tips (Maduuka Best Practice)

  • Store relative file path (e.g., uploads/dpc-photos/abc.jpg).
  • Index (franchise_id, entity_id) for fast retrieval.
  • Store created_by, created_at for auditability.
  • Prefer soft delete only if required by audit rules; otherwise hard delete with file cleanup.

Security & Efficiency

  • Verify franchise ownership on every read/write/delete.
  • Enforce allowed MIME types and extensions server-side.
  • Use unique filenames (timestamp + random suffix), never trust original names.
  • Cap size after compression; reject oversized images.
  • Clean up orphaned files if DB insert fails.
  • Use transactions for multi-step delete (DB + file).
  • Return 404 for missing records and 403 for cross-franchise access.

Tips & Tricks (Efficiency + UX)

  • Use object-fit: cover for all thumbnails.
  • Use consistent sizes (e.g., 3-column grid with fixed height) to avoid layout shift.
  • Use loading="lazy" for card images in large lists.
  • Cache the photo list per entity on load; only refresh after upload/delete.
  • Use unique file names (timestamp + random suffix) to avoid collisions.
  • Always store relative file paths in DB.
  • Avoid re-uploading if the same file is selected twice; reset input after upload.
  • Prefer CDN/local caching headers for read-heavy image endpoints where applicable.

Reference Files

  • Use image-compression/SKILL.md for compression defaults and rules.

Common Pitfalls

  • Skipping compression (breaks bandwidth/storage goals).
  • Missing franchise_id filter on queries.
  • Leaving upload UI visible when max photos already exist.
  • Using native alert() instead of SweetAlert2.

Examples

  • DPC photo management: api/dpc-photos.php + client gallery pattern.
  • Asset photo management: api/asset-photos.php + client gallery pattern.

平台分布

Codex

35.94%
按下载量换算38

Claude

26.43%
按下载量换算28

Cursor

19.26%
按下载量换算20

Gemini CLI

9.72%
按下载量换算10

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills