What is github-figure-bed?

A skill for storing images in a GitHub repository and returning CDN or Markdown links to them. A figure bed is a repository used to host images for documents, blogs, or other projects.

Use it to upload, list, search, or delete images in a GitHub repository and obtain links through jsDelivr, jsDelivr Mirror, or GitHub's raw files.

It removes the need to upload images through a website or manually build links, while helping prevent duplicate filenames.

github-figure-bed — Skill for Claude Code and Codex by wu529778790

Install

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.

Any agent

npx skills add wu529778790/shenzjd-skills --skill github-figure-bed

Clone the repo

git clone --depth 1 https://github.com/wu529778790/shenzjd-skills

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/wu529778790/shenzjd-skills/github-figure-bed/github.svg)](https://agentmods.dev/skills/wu529778790/shenzjd-skills/github-figure-bed)

Your own site

<a href="https://agentmods.dev/skills/wu529778790/shenzjd-skills/github-figure-bed"><img src="https://agentmods.dev/badge/skills/wu529778790/shenzjd-skills/github-figure-bed/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/wu529778790/shenzjd-skills/github-figure-bed"><img src="https://agentmods.dev/badge/skills/wu529778790/shenzjd-skills/github-figure-bed.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 156 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,584 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00156	$0.02584
Opus 5	$0.00078	$0.01292
Sonnet 5	$0.00031	$0.00517
Haiku 4.5	$0.00016	$0.00258

Measured 3d ago against content hash 87b09c5e768b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

github-figure-bed 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 3d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/delete.sh, scripts/list.sh, scripts/setup.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

github-figure-bed/SKILL.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GitHub Figure Bed

把本地图片上传到任意 GitHub 仓库（图床），生成可直接粘贴的 CDN 链接（Markdown / 纯 URL），并支持删除、列表管理。不依赖前端，任何环境（含整理素材时）都能用。

Overview

图床 = 任意 GitHub 仓库 + 一个图片目录（默认 blog/）。本 skill 通过 gh api 调用 GitHub Contents API（与网页版图床同一接口），把图片上传到目标仓库，并返回 CDN 加速链接。支持多 CDN、多文件、子目录、重名保护。

零配置体验：首次使用运行 scripts/setup.sh 一键初始化 —— 自动引导登录、检测/创建仓库、读取仓库配置并与 img.shenzjd.com 项目网页端联动、探测分支、生成本地缓存。之后用户只需对 AI 说「上传 xxx.png 到图床」，无需手动配置任何东西。

配置路径：远程配置固定读取仓库 .img.shenzjd.com/config.json（与 img.shenzjd.com 网页端一致）；旧仓库的 .imgx-config/config.json 仍兼容读取，但新写入一律用新路径。

可视化后台：不想用命令行时，直接打开 img.shenzjd.com 网页端 —— 同一个图床仓库，拖拽上传（压缩/水印/WebP）、图片管理（预览/删除/链接复制）、可视化设置（分支/目录/CDN）。网页端改配置后，重跑 setup.sh 即可同步到 AI 侧。

When to Use

User wants to upload local images to a GitHub-hosted figure bed and get CDN links
User wants a markdown image link like ![name](https://cdn.jsdelivr.net/gh/...@main/...) for blog/docs
User wants to delete an image from the figure bed repo
User wants to list/search images already in the figure bed repo
User mentions 图床 / 上传图片 / CDN 链接 / jsdelivr / jsdmirror / 图片托管
User asks to organize assets and host them (AI cannot use the web UI, this skill covers that gap)

When NOT to Use:

User has a figure bed web app with its own upload flow and can use it directly
Target repo is not a GitHub repo (e.g. local-only or other platforms)
gh CLI is not installed or not authenticated (install and gh auth login first)

Core Pattern

Step 0: 首次使用 — 一键初始化 (setup.sh)

新用户首次使用（或不确定配置是否就绪时），先运行：

scripts/setup.sh

它会自动完成，全程不需要用户手动配置：

登录引导：检测到未登录时运行 gh auth login，把输出的授权链接和 one-time code 展示给用户，引导在浏览器完成授权（只需一次）
自动获取 Owner：取当前登录的 GitHub 用户名，无需手填
仓库就绪：检测默认仓库 img.shenzjd.com；不存在则自动创建（public），并写入宣传/使用说明 README
配置联动（核心）：读取仓库的 .img.shenzjd.com/config.json（与 img.shenzjd.com 项目网页端共用同一份配置），自动继承 branch/directory/cdn；仓库没有配置时，初始化一份项目格式配置写回仓库（网页端即可直接使用）
分支探测：自动找出图片目录实际所在分支（规避 default_branch 与图片分支不一致的坑）
配置落盘：写入本地缓存 ~/.config/github-figure-bed/config.env，三个操作脚本自动读取，之后零参数直接使用
自测：上传一张 1x1 测试图并删除，验证全链路

Read the full file on GitHub · 159 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

3d ago Changed · +7 lines · +2 tokens per session 87b09c5e768b
11d ago First seen · 152 lines · 154 tokens per session scan A 6afbe2c66f0d

Subscribe to this mod's changes

github-figure-bed is a skill published in the GitHub repository wu529778790/shenzjd-skills (0 stars, last pushed 4d ago), licensed MIT. It adds 156 tokens to every session and 2,584 once invoked, about $0.0008 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 2026-08-31.

Claude Code Documents ai-skills ai-tools copilot cursor-rules docker

video-timeline

Turn a final TTS audio track (with its timed transcript) into an editable story timeline (xlsx) for a human to fill with images, slides, and video clips. Audits the audio against timing best practices first, then maps each finding to a visual offset, and QA-scores the timeline objectively. Use when a finished…

Elumenotion/GuideAnts · 81 tokens

transcript-to-pdf

Convert a GuideAnts / Code-Executor markdown conversation transcript into a styled, print-ready PDF with a cover page, role-badged turns, full tool-call inputs (heredoc-aware) and highlighted code. Use when the user wants to export, archive, or share a conversation log as a polished PDF document.

Elumenotion/GuideAnts · 71 tokens

opencite

Use this skill for "search for papers", "find citations", "look up a DOI", "get BibTeX", "download PDF", "convert PDF to markdown", "find canonical papers", "convert identifiers", "batch download papers", "configure opencite", "literature review", "find related papers", "what papers cite this", "export references"…

neuromechanist/research-skills · 111 tokens

github-figure-bed