Not in the top 1,000 by GitHub stars
okooo5km/Skills4U
Skills here
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/chatwoot/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
c7187fbd2a16 → c7187fbd2a16
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → c7187fbd2a16
No earlier version was observed for comparison.
skills/chinese-copyright-application/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
c7187fbd2a16 → c7187fbd2a16
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → c7187fbd2a16
No earlier version was observed for comparison.
skills/grid25/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
c7187fbd2a16 → c7187fbd2a16
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → c7187fbd2a16
No earlier version was observed for comparison.
skills/orchard/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
c7187fbd2a16 → c7187fbd2a16
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → c7187fbd2a16
No earlier version was observed for comparison.
skills/post-optimizer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
c7187fbd2a16 → c7187fbd2a16
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → c7187fbd2a16
No earlier version was observed for comparison.
skills/sketch-image-prompt/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
c7187fbd2a16 → c7187fbd2a16
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → c7187fbd2a16
No earlier version was observed for comparison.
skills/video-storyboard/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
c7187fbd2a16 → c7187fbd2a16
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → c7187fbd2a16
No earlier version was observed for comparison.
skills/xiaohongshu-expert/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
c7187fbd2a16 → c7187fbd2a16
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → c7187fbd2a16
No earlier version was observed for comparison.
skills/zipic/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
c7187fbd2a16 → c7187fbd2a16
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → c7187fbd2a16
No earlier version was observed for comparison.
Heat
1.5- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- chatwoot
skills/chatwoot - chinese-copyright-application
skills/chinese-copyright-application - grid25
skills/grid25 - orchard
skills/orchard - post-optimizer
skills/post-optimizer - sketch-image-prompt
skills/sketch-image-prompt - video-storyboard-designer
skills/video-storyboard - xiaohongshu-expert
skills/xiaohongshu-expert - zipic
skills/zipic
How it works
chatwoot
When your agent uses it
Use the official Chatwoot CLI to inspect and operate Chatwoot conversations, messages, contacts, inboxes, labels, teams, help center articles, webhooks, reports, and raw Application API paths. Use when Codex needs to call Chatwoot APIs, work with a self-hosted Chatwoot domain, fetch customer feedback, summarize recent conversations, send replies or private notes, assign/label/close conversations, or guide a user through installing and authenticating the Chatwoot CLI.
What it loads into context
Frontmatter
109 tokensAlways available to the agent
SKILL.md
1,079 tokensWhen the skill is activated
Reference documents
622 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Rule
- Setup Check
- Config
- Common Workflows
- Customer Feedback
Files
SKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesSKILL.mdcore4,331 bytesagents/openai.yamlasset206 bytesreferences/cli.mddoc2,564 bytes
Read SKILL.md
# Chatwoot
## Rule
Use the official `chatwoot` CLI. If the CLI is missing or unauthenticated, stop and guide the user through install/auth first.
Do not bypass the CLI with raw REST calls, Rails runner, database queries, or server-side container access unless the user explicitly asks for a fallback path after seeing the install/auth instructions. Boss picked the CLI route; respect it.
For self-hosted deployments, prompt for or discover:
- Base URL: the Chatwoot instance URL, for example `https://chatwoot.example.com`
- Account ID: the numeric account ID from the Chatwoot dashboard URL or `chatwoot auth status`
Never store or print the API access token in skill files, docs, shell history examples, or final answers.View the complete source on GitHubchinese-copyright-application
When your agent uses it
中国软件著作权申请材料生成工具。申请表直接输出 Markdown 提交,源程序/用户手册/设计说明书三份生成 LaTeX 并编译为 PDF。自动分析项目代码,生成四份材料(前后各30页共60页源程序、含页眉页脚的用户手册和设计说明书、Markdown 申请表),并做版本号一致性、模块覆盖双向核验、字数限制等信息一致性校验。适用于微信小程序、Web应用、移动App、桌面应用等各类软件项目。当用户提到软件著作权、软著申请、版权登记时必须使用此 Skill。当用户要为任何软件项目准备著作权材料、生成软著文档时也应使用。
What it loads into context
Frontmatter
187 tokensAlways available to the agent
SKILL.md
5,632 tokensWhen the skill is activated
Reference documents
7,571 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 核心原则
- v1.1 关键变更
- 快速开始
- 工作流程
- 统一 LaTeX 排版规范
- 特殊项目类型处理
- LaTeX 环境依赖
- 参考文档
Scripts executed separately
references/build-script-template.shscripts/analyze_and_generate_source.py
Files
LICENSEasset1,063 bytesREADME.mddoc3,864 bytesSKILL.mdcore19,944 bytesSKILL.mdcore19,944 bytesSKILL.mdcore19,944 bytesSKILL.mdcore19,944 bytesreferences/application-form-template.mddoc3,676 bytesreferences/build-script-template.shruns1,883 bytesreferences/design-doc-template.texasset9,040 bytesreferences/requirements.mddoc18,658 bytesreferences/source-code-template.texasset2,050 bytesreferences/user-manual-template.texasset4,371 bytesscripts/analyze_and_generate_source.pyruns23,602 bytes
Read SKILL.md
# 中国软件著作权申请材料生成
## 核心原则
- **申请表**:直接输出 Markdown(`.md`)文件提交,不参与 LaTeX 编译。
- **源程序、用户手册、设计说明书**:生成 `.tex` 文件,用 XeLaTeX 编译为 PDF。
## v1.1 关键变更
- 申请表载体由 LaTeX→PDF 改为 Markdown(PDF 文本提取带换行造成的录入问题)
- 主要功能字数:200 字 → **500–1000 字(建议 500–600)**
- 新增**版本号一致性核验**(信息收集阶段就要查项目里的 version 字符串与目标版本号是否一致)
- 新增**遗留代码识别**(mockData/util.js 模板/logs 等不应进入鉴别材料)
- 设计说明书 §4 详细设计强制 **6 段结构** + **模块覆盖双向对应**View the complete source on GitHubgrid25
When your agent uses it
25宫格选题助手(grid25)。帮用户为任意行业生成爆款内容选题关键词,渲染可交互的 25宫格抽签工具,并可直接搜索真实平台热门选题方向。 以下任意一条即触发: - 用户说"帮我做选题"、"内容选题"、"内容方向"、"25宫格"、"选题助手"、"grid25" - 用户问某个行业/产品/赛道该拍什么内容、做什么选题 - 用户想做小红书/抖音/视频号/B站的内容规划 - 用户提到"爆款选题"、"内容策划"、"选题库"、"内容关键词" - 用户说"帮我分析一下XX行业的内容方向" - 消息包含 "grid25搜索选题:"(用户点了宫格里的「帮我找选题」按钮) - 用户点击了宫格里的「换个行业」按钮(触发 sendPrompt)
What it loads into context
Frontmatter
390 tokensAlways available to the agent
SKILL.md
1,779 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 工作流程
- Step 5 — 搜索真实选题(也用脚本渲染)
- 换行业
Scripts executed separately
assets/widget.min.jsscripts/render.py
Files
SKILL.mdcore5,781 bytesSKILL.mdcore5,781 bytesSKILL.mdcore5,781 bytesassets/widget.min.jsruns9,394 bytesreferences/results-template.htmlasset3,381 bytesreferences/widget-template.htmlasset129 bytesscripts/render.pyruns1,938 bytes
Read SKILL.md
# grid25 — 25宫格选题助手
三层宫格:**核心行业(1格)× 行业要素(8格)× 场景/人群(16格)**,摇骰子抽组合,一键搜索验证热度。
所有 widget 渲染通过 `scripts/render.py` 完成——**禁止手写 HTML**,直接跑脚本拿输出。
---
## 工作流程
### Step 1 — 问行业
用 `ask_user_input_v0` 工具直接问,**不要渲染 widget**。
View the complete source on GitHuborchard
When your agent uses it
Use the local Orchard app to interact with macOS Apple apps and services: Calendar, Reminders, Clock, Mail, Contacts, Notes, Music, Weather, Messages, Location/Maps, and Apple Shortcuts. Two execution paths reach the same running Orchard.app: the `orchard` CLI (default — use this if you have a Bash/shell tool, e.g. Claude Code, Codex CLI, Cursor) and a stdio MCP server, `orchard mcp`, exposed as prefixed MCP tools (fallback for sandboxes that cannot run the macOS CLI, e.g. Claude Cowork, bridged through Claude Desktop). Use when a task asks to read or manage local calendar events, reminders, Apple Mail, contacts, notes, iMessage/SMS, Apple Music playback/library, weather, current time/timezones, geocoding, routes, current location, or local Shortcuts.
What it loads into context
Frontmatter
241 tokensAlways available to the agent
SKILL.md
4,989 tokensWhen the skill is activated
Reference documents
14,925 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Which Channel
- Quick Start (CLI)
- Known Pitfalls (CLI)
- Core Rules
- Calendar and Reminder Date Safety (Orchard 0.6.3+)
- Common Workflows (CLI)
- Troubleshooting (CLI)
- MCP Channel (No Bash — e.g. Claude Cowork)
Scripts executed separately
scripts/resolve-orchard.sh
Files
SKILL.mdcore20,160 bytesSKILL.mdcore20,160 bytesSKILL.mdcore20,160 bytesSKILL.mdcore20,160 bytesSKILL.mdcore20,160 bytesSKILL.mdcore20,160 bytesSKILL.mdcore20,160 bytesSKILL.mdcore20,160 bytesSKILL.mdcore20,160 bytesSKILL.mdcore20,160 bytesSKILL.mdcore20,160 bytesagents/openai.yamlasset188 bytesreferences/commands.mddoc26,140 bytesreferences/mcp-tools.mddoc30,265 bytesscripts/resolve-orchard.shruns2,472 bytes
Read SKILL.md
# Orchard
Orchard exposes 52 Apple-app tools (Calendar, Reminders, Mail, Notes, Messages, Music, Weather, Contacts, Clock, Location/Maps, Shortcuts) through one running Orchard.app, reachable over two transports that carry the same tool set. **Default to the CLI.** Read "Which Channel" below first — it costs you nothing to check and prevents wasted turns.
## Which Channel
Decide by looking at your own tool list first. Having a Bash tool is NOT enough to prove you can reach the CLI — sandboxed agents (e.g. Claude Cowork) have a Bash that runs inside an isolated Linux VM where the macOS CLI does not exist, while Orchard's MCP tools are still bridged in by the host.
- **You have a Bash/shell tool** (Claude Code, Codex CLI, Cursor, or any terminal-capable agent — the large majority of sessions) → try the **CLI first**. Continue to "Quick Start" below. It is cheaper than MCP (this file plus one on-demand reference beats preloading 52 MCP schemas), and it self-documents via `--help`.
- **You have no Bash/shell tool at all** → skip straight to `references/mcp-tools.md` and call the Orchard MCP tools (names ending in `__calendar_info`, `__mail_read`, etc.) directly. "Quick Start", "Known Pitfalls", and "Common Workflows" below are written for the CLI and do not apply to you. "Core Rules" still applies — read it, it describes the tools, not the transport.
If you have Bash but `scripts/resolve-orchard.sh --route` reports `missing_app`, check your tool list for Orchard MCP tools before concluding anything:
- **Orchard MCP tools ARE in your tool list** → your shell is sandboxed away from the user's Mac (Claude Cowork's Linux VM is the typical case), but the host has bridged Orchard's MCP server in. Switch to the MCP channel: read `references/mcp-tools.md` and use those tools. Do not tell the user anything is broken — nothing is.View the complete source on GitHubpost-optimizer
When your agent uses it
将平实、准确的内容改写成有网感、能引发互动的社交媒体文案。适用于 Twitter/X、小红书、即刻等平台的短文案优化。当用户希望优化推文、笔记、短帖子,或者想让功能描述/产品更新变得更抓人眼球时,使用此 skill。也适用于用户给出一个主题、一段草稿、或一组功能点,希望生成一条有活人感的推文。不适用于长文章、博客、正式文档。
What it loads into context
Frontmatter
125 tokensAlways available to the agent
SKILL.md
4,018 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 一句话定义
- 核心理念:活人感 = 讲故事
- 适用场景
- 不适用
- 工作流程
- 讲故事的技巧库
- 语气校准:像朋友发消息
- 平台适配指南
- 风格护栏 — 防止改过头
- 改写示例
- 特殊情况处理
Files
SKILL.mdcore14,202 bytes
Read SKILL.md
# Post Optimizer — 讲故事,不写 changelog
## 一句话定义
把「正确但无聊」的内容,变成一个让人想读完的**故事**。
## 核心理念:活人感 = 讲故事
人不爱看功能列表,但爱听故事。
每一个产品更新、每一个技术决策、每一条生活感悟背后,都有一个故事——某个问题困扰了你,某个灵感突然出现,某次纠结之后做了一个取舍。**把这个故事讲出来,活人感就自然来了。**
对比一下:
View the complete source on GitHubsketch-image-prompt
When your agent uses it
Transforms article content or summaries into minimalist hand-drawn style JSON prompts for AI image generation tools. Use this skill whenever the user wants to create any kind of visual from text content — including banners, article illustrations, inline diagrams, infographics, or concept visuals. Trigger on requests like "turn this into a visual", "create an image prompt", "make an illustration for this", "generate a diagram from this article", "I need a sketch for this section", or any request combining content analysis with image/visual prompt generation. Always use this skill when the user provides text content and wants an AI-ready image prompt output.
What it loads into context
Frontmatter
560 tokensAlways available to the agent
SKILL.md
3,021 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 工作流程
- Final Prompt 规范
- 语言规则
Files
SKILL.mdcore10,388 bytes
Read SKILL.md
# Sketch Image Prompt
将文字内容转化为极简手绘风格图像提示词,供 Midjourney、Stable Diffusion 等 AI 绘图工具直接使用。
## 工作流程
### 第一步:询问尺寸比例
用户提供内容后,**必须先询问尺寸比例**,再进行分析:
> "请问这张图的尺寸比例是?
>
> 横屏:
> - **16:9** — 横向展示 / Twitter / 社交媒体View the complete source on GitHubvideo-storyboard-designer
When your agent uses it
专业 AI 视频分镜设计师。当用户想要创作视频、制作分镜脚本、生成 AI 视频提示词、规划视频内容结构时,必须使用此 skill。 覆盖所有视频类型:短视频、广告片、教育内容、品牌视频、Vlog、微电影等。 即使用户只说"帮我做个视频"或"我想拍 XX 主题的内容",也应触发此 skill。 输出专业分镜设计 + 可直接用于 即梦(Seedance 2.0) / Sora / Kling / Runway / Veo 等主流 AI 视频工具的提示词,其中即梦 Seedance 2.0 支持多模态 @ 引用语法专项输出。
What it loads into context
Frontmatter
171 tokensAlways available to the agent
SKILL.md
7,104 tokensWhen the skill is activated
Reference documents
10,455 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 第一步:读取上下文,判断已知信息
- 第二步:用户访谈(把专业问题翻译成普通人语言)
- 第三步:主题 → 风格自动推导
- 第四步:分镜设计
- 第五步:配乐设计
- 第六步:输出分镜文档
- 第七步:可选增强项
- 提示词质量原则
- 参考文件
Files
SKILL.mdcore23,288 bytesreferences/music-design.mddoc13,302 bytesreferences/prompt-examples.mddoc6,914 bytesreferences/seedance-jimeng.mddoc9,768 bytesreferences/shot-types.mddoc6,129 bytes
Read SKILL.md
# Video Storyboard Designer
像顶级导演一样思考,用普通人听得懂的语言问问题,输出创意专业的分镜 + AI 视频提示词。
---
## 第一步:读取上下文,判断已知信息
在开口问问题之前,先从对话中提取已有信息:
- 主题/内容方向已知?✓ 跳过
- 视频用途/发布平台已提及?✓ 跳过
- 时长/比例已说明?✓ 跳过
**只问用户真正需要回答的问题,不重复已知。**View the complete source on GitHubxiaohongshu-expert
When your agent uses it
小红书运营专家——从0到1全流程指导。覆盖账号定位、内容创作、标题优化、封面设计、SEO搜索优化、推荐算法拆解、涨粉策略、变现路径、数据分析、平台规则合规、内容发布前审核、账号健康度诊断等全维度。 当用户提到以下任何场景时必须使用此 skill:小红书运营、小红书笔记、小红书涨粉、小红书变现、小红书账号、小红书定位、小红书标题、小红书封面、小红书SEO、小红书算法、小红书限流、小红书爆款、小红书选题、小红书带货、小红书直播、小红书蒲公英、笔记转写、内容种草、买手电商、笔记审核、账号诊断、账号健康度。 即使用户只说"帮我写一篇小红书"、"我想做小红书"、"小红书怎么运营"、"帮我优化这篇笔记"、"帮我看看这篇笔记有没有问题"、"我的账号是不是有问题",也应触发。 当用户提到"种草"、"笔记"、"博主"、"达人"、"限流"、"没流量"、"违规"等关键词且语境与小红书相关时也应触发。
What it loads into context
Frontmatter
422 tokensAlways available to the agent
SKILL.md
2,363 tokensWhen the skill is activated
Reference documents
14,970 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 你的核心能力
- 工作流程
- 核心知识概览(快速参考)
- 回复风格
- 特殊场景处理
Files
SKILL.mdcore8,050 bytesreferences/account-positioning.mddoc5,554 bytesreferences/algorithm-and-seo.mddoc7,895 bytesreferences/content-audit.mddoc12,807 bytesreferences/content-creation.mddoc8,059 bytesreferences/monetization.mddoc6,161 bytesreferences/operations.mddoc8,191 bytes
Read SKILL.md
# 小红书运营专家 Skill
你现在是一位资深小红书运营专家,拥有从0到1打造百万粉丝账号的实战经验,精通平台算法、内容创作、商业变现的全链路。你的知识体系融合了系统方法论和2024-2026年平台最新规则。
## 你的核心能力
你能帮用户解决小红书运营中的一切问题,包括但不限于:
**起步阶段**:账号定位、赛道选择、人设打造、目标用户分析
**创作阶段**:选题策划、标题优化、封面设计指导、正文结构、话题标签、SEO关键词布局
**审核阶段**:发布前内容合规检查、敏感词排查、AI内容标注指导、广告合规审查
**运营阶段**:发布时间策略、互动运营、数据分析、账号健康度诊断、限流排查与恢复、涨粉策略
**变现阶段**:品牌合作、蒲公英平台、直播带货、买手橱窗、知识付费、私域引流
View the complete source on GitHubzipic
When your agent uses it
Local image compression and Zipic-app expert for macOS and native Windows. Uses the Zipic CLI with JSON results, per-file saved_pct and exit codes; URL Scheme is a limited fallback. Use for compressing, optimizing or shrinking images, batch compression, conversion to WebP/AVIF/HEIC/JXL (including lossless JPEG XL), exporting PDF pages as images, hitting a target file size ("under 500 KB", "max 2 MB"), SVG optimization, resizing, presets and compression history. Also use for Zipic pricing, Pro features, activation, free-tier limits, troubleshooting, comparisons, CLI setup and workflow integration. Requires the installed Zipic GUI in the same execution environment. Windows uses the packaged zipic.exe alias and PowerShell; macOS uses Zipic.app. Format support and integrations differ by platform.
What it loads into context
Frontmatter
309 tokensAlways available to the agent
SKILL.md
2,642 tokensWhen the skill is activated
Reference documents
19,026 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Platform and shell
- Compress
- When the CLI fails
- Fallback: URL Scheme
- SVG and presets quick notes
- Zipic-usage questions
Scripts executed separately
scripts/detect.ps1scripts/detect.sh
Files
CHANGELOG.mddoc17,743 bytesLICENSEasset1,281 bytesSKILL.mdcore10,492 bytesSKILL.mdcore10,492 bytesSKILL.mdcore10,492 bytesSKILL.mdcore10,492 bytesSKILL.mdcore10,492 bytesSKILL.mdcore10,492 bytesSKILL.mdcore10,492 bytesSKILL.mdcore10,492 bytesevals/evals.jsonasset17,543 bytesreference/cli.mddoc34,368 bytesreference/resources.mddoc5,178 bytesreference/url-scheme.mddoc7,954 bytesreference/windows.mddoc11,821 bytesscripts/detect.ps1runs3,222 bytesscripts/detect.shruns3,471 bytes
Read SKILL.md
# Zipic
Image compression on macOS and Windows, 100% on-device. Drive the installed GUI via its CLI; URL Scheme is a fallback when the CLI is unavailable.
## Platform and shell
Identify the OS, architecture and shell **where commands execute**, rather than the user's desktop OS. Keep the GUI, CLI and input/output paths on the same host and user account.
- **macOS**: use `zipic` and POSIX shell syntax. If missing, run `bash "<skill-dir>/scripts/detect.sh"`.
- **Native Windows**: read [reference/windows.md](reference/windows.md) before setup or compression. Use PowerShell and `zipic.exe`; run `& "<skill-dir>\scripts\detect.ps1"` to resolve the executable and verify its version. The packaged CLI is `ZipicCli.exe`, exposed as the `zipic.exe` app execution alias; the GUI's `Zipic.exe` is a different executable.
- **WSL**: there is no Linux Zipic binary. Use Windows PowerShell through WSL interop with paths converted by `wslpath -w`, following the Windows reference. A Linux container or remote Linux host without Windows interop cannot invoke the Windows GUI.
Resolve `<skill-dir>` from this loaded skill's location; script paths are not relative to the user's project. On Windows use `& $exe` for a resolved executable, `$env:NAME` for environment variables, quoted paths and argument arrays. Do not copy Bash continuations, `open`, `brew` or `/tmp` paths into PowerShell.
View the complete source on GitHubSkills included
- chatwoot
- chinese-copyright-application
- grid25
- orchard
- post-optimizer
- sketch-image-prompt
- video-storyboard-designer
- xiaohongshu-expert
- zipic
Repository facts
- License
- MIT
- Created
- Mar 4, 2026
- Last pushed
- Oct 15, 2026
- Forks
- 30
- Open issues
- 1
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 36 notes
skills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chatwoot/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-copyright-application/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-copyright-application/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/chinese-copyright-application/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/grid25/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/grid25/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/orchard/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 9 dangerous shell commandsin 6 files: chinese-copyright-application/references/requirements.md:451 chinese-copyright-application/SKILL.md:44 chatwoot/SKILL.md:32 and 3 more
- 92 network referencesin 13 files: zipic/reference/resources.md:9 zipic/evals/evals.json:51 orchard/references/commands.md:106 and 10 more
- 3 obfuscation signalsin 1 file: grid25/assets/widget.min.js:7
- 1 instruction override signalin 1 file: orchard/SKILL.md:25
- 7 executable scriptsin 7 files: chinese-copyright-application/references/build-script-template.sh:1 chinese-copyright-application/scripts/analyze_and_generate_source.py:1 grid25/assets/widget.min.js:1 and 4 more
- 4 references to secretsin 3 files: chatwoot/SKILL.md:62 chatwoot/references/cli.md:5 chinese-copyright-application/scripts/analyze_and_generate_source.py:78
- No requests to vote in Hot
Show all 116 signals by file
skills/chatwoot/SKILL.md
- Network accessline 16
- Base URL: the Chatwoot instance URL, for example `https://chatwoot.example.com` - Dangerous shell operationline 32
curl -fsSL https://chwt.app/install-cli | sh - Network accessline 32
curl -fsSL https://chwt.app/install-cli | sh - Network accessline 50
- Base URL: their self-hosted Chatwoot URL, for example `https://chatwoot.example.com` - Access to secretsline 62
[Credential-related source omitted] - Access to secretsline 72
[Credential-related source omitted]
skills/chatwoot/references/cli.md
- Access to secretsline 5
[Credential-related source omitted] - Dangerous shell operationline 10
curl -fsSL https://chwt.app/install-cli | sh - Network accessline 10
curl -fsSL https://chwt.app/install-cli | sh - Network accessline 30
- `https://developers.chatwoot.com/cli` - Network accessline 31
- `https://github.com/chatwoot/cli` - Network accessline 90
chatwoot api -X POST /webhooks --data '{ "name": "daily-feedback-events", "url": "https://example.com/chatwoot/webhook", - Network accessline 91
"name": "daily-feedback-events", "url": "https://example.com/chatwoot/webhook", "subscriptions": ["conversation_created", "message_created"] - Network accessline 92
"url": "https://example.com/chatwoot/webhook",
skills/chinese-copyright-application/SKILL.md
- Dangerous shell operationline 44
- macOS:`brew install --cask basictex && sudo tlmgr update --self && sudo tlmgr install ctex xecjk fancyhdr lastpage fancyvrb tabularx enumitem float xcolor longtable collection-fontsrecommended` - Network accessline 44
- macOS:`brew install --cask basictex && sudo tlmgr update --self && sudo tlmgr install ctex xecjk fancyhdr lastpage fancyvrb tabularx enumitem float xcolor longtable collection-fontsrecommended` - Linux:`sudo apt install texlive-xetex texl - Dangerous shell operationline 45
- Linux:`sudo apt install texlive-xetex texlive-lang-chinese texlive-latex-extra texlive-fonts-recommended` - Network accessline 46
- Windows:引导用户安装 TeX Live 完整版(https://www.tug.org/texlive/)
skills/chinese-copyright-application/references/build-script-template.sh
skills/chinese-copyright-application/references/requirements.md
- Dangerous shell operationline 451
sudo tlmgr update --self - Dangerous shell operationline 452
sudo tlmgr install ctex xecjk fancyhdr lastpage fancyvrb tabularx enumitem float xcolor longtable collection-fontsrecommended - Dangerous shell operationline 457
sudo apt install texlive-xetex texlive-lang-chinese texlive-latex-extra texlive-fonts-recommended - Network accessline 460
**Windows**: 安装 TeX Live 完整版(https://www.tug.org/texlive/),或 MiKTeX - Network accessline 461
安装 TeX Live 完整版(https://www.tug.org/texlive/),或 MiKTeX
skills/chinese-copyright-application/scripts/analyze_and_generate_source.py
skills/grid25/assets/widget.min.js
- Executable scriptline 1
Executable file - Possible obfuscationline 7
const css=`*{box-sizing:border-box}.ds{width:64px;height:64px;perspective:180px;cursor:pointer;user-select:none}.dc{width:64px;height:64px;position:relative;transform-style:preserve-3d}.dc.idle{animation:dFl 5s ease-in-out infinite}.dc.spin - Possible obfuscationline 12
R.innerHTML=`<div style="max-width:540px;margin:0 auto;padding:1.75rem 1.25rem;font-family:var(--font-sans)"><div style="display:flex;gap:32px;align-items:flex-start"><div style="flex:0 0 88px;display:flex;flex-direction:column;align-items: - Network accessline 20
function gc(i){const cs=cls(),a=document.getElementById('GA'),cr=cs[i].getBoundingClientRect(),ar=a.getBoundingClientRect();return{x:cr.left-ar.left+cr.width/2,y:cr.top-ar.top+cr.height/2}} function bcp(a,b,o){const mx=(a.x+b.x)/2,my=(a.y+b - Network accessline 22
function drawL(){const sv=document.getElementById('SV'),ga=document.getElementById('GA');sv.innerHTML='';sv.setAttribute('viewBox',`0 0 ${ga.offsetWidth} ${ga.offsetHeight}`);const c=gc(12),p2=gc(s2),p3=gc(s3),cp1=bcp(c,p2,32),cp2=bcp(p2,p3 - Possible obfuscationline 24
window._roll=function(){if(going)return;going=true;s2=-1;s3=-1;document.getElementById('SV').innerHTML='';cls().forEach(c=>c.classList.remove('csr2','csr3'));document.getElementById('RC').style.display='none';document.getElementById('BT').s
skills/grid25/scripts/render.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/orchard/SKILL.md
- Instruction override signalline 25
- **Orchard MCP tools ARE in your tool list** → your shell is sandboxed away from the user's Mac (Claude Cowork's Linux VM is the typical case), but the host has bridged Orchard's MCP server in. Switch to the MCP channel: read `references/m
skills/orchard/references/commands.md
- Dangerous shell operationline 42
eval "orchard calendar info --help" - Network accessline 106
orchard calendar create --title "Event title" --start 2026-06-03T15:00:00+08:00 --end 2026-06-03T16:00:00+08:00 --calendar-id CALENDAR_ID --location "Office" --notes "Agenda" --url "https://example.com/meeting" - Network accessline 111
--location "Office" \ --notes "Agenda" \ --url "https://example.com/meeting" \ - Network accessline 112
--notes "Agenda" \ --url "https://example.com/meeting" \ --alarms 15,60 \ - Network accessline 113
--url "https://example.com/meeting" \ - Network accessline 120
orchard calendar update --event-id EVENT_ID --title "New title" --start 2026-06-03T16:00:00+08:00 --end 2026-06-03T17:00:00+08:00 --json orchard calendar update --event-id EVENT_ID --calendar-id CALENDAR_ID --json orchard calendar update -- - Network accessline 121
orchard calendar update --event-id EVENT_ID --calendar-id CALENDAR_ID --json orchard calendar update --event-id EVENT_ID --url "https://example.com/meeting" --alarms 15,60 --json orchard calendar update --event-id EVENT_ID --url "" --alarms - Network accessline 122
orchard calendar update --event-id EVENT_ID --url "https://example.com/meeting" --alarms 15,60 --json
skills/orchard/scripts/resolve-orchard.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/zipic/CHANGELOG.md
skills/zipic/LICENSE
- Network accessline 25
Note: This skill wraps the Zipic app's public URL Scheme API. Zipic itself is a separate product by its respective owner; this skill does not include or redistribute the Zipic application. See https://zipic.app for app licensing. - Network accessline 27
redistribute the Zipic application. See https://zipic.app for app licensing.
skills/zipic/SKILL.md
- Network accessline 10
version: 2.5.0 author: 十里 & FRIDAY homepage: https://zipic.app - Network accessline 11
author: 十里 & FRIDAY homepage: https://zipic.app changelog: ./CHANGELOG.md - Network accessline 12
homepage: https://zipic.app - Network accessline 85
| `install_cli` | CLI binary missing — tell user: Zipic menu bar → "Install zipic CLI". Use Fallback below for now. | | `url_scheme` | Zipic < 1.9.5, no CLI exists — tell user to upgrade. Use Fallback below. | | `halt_no_app` | Zi - Network accessline 86
| `url_scheme` | Zipic < 1.9.5, no CLI exists — tell user to upgrade. Use Fallback below. | | `halt_no_app` | Zipic not installed — suggest `brew install --cask zipic` or https://zipic.app. | | `halt_not_macos` | This Bash detector i - Network accessline 87
| `halt_no_app` | Zipic not installed — suggest `brew install --cask zipic` or https://zipic.app. | - Network accessline 105
For pricing, Pro features, troubleshooting, activation, comparisons, etc. — load `reference/resources.md`. It indexes https://zipic.app, https://docs.zipic.app, the AI-friendly index at https://zipic.app/llms.txt, and per-topic deep links (
skills/zipic/evals/evals.json
- Network accessline 51
"name": "qa-pricing-and-pro-features", "prompt": "Zipic 多少钱?Pro 版相比免费版有什么功能?", "expected_output": "Skill triggers (because of the Q&A keywords in description). Agent consults reference/resources.md and/or fetches https://zipic.a - Network accessline 52
"prompt": "Zipic 多少钱?Pro 版相比免费版有什么功能?", "expected_output": "Skill triggers (because of the Q&A keywords in description). Agent consults reference/resources.md and/or fetches https://zipic.app or https://zipic.app/llms.txt, then answer - Network accessline 53
"expected_output": "Skill triggers (because of the Q&A keywords in description). Agent consults reference/resources.md and/or fetches https://zipic.app or https://zipic.app/llms.txt, then answers with: free tier 25 images/day, lifetime Pro - Network accessline 55
"expectations": [ "The Zipic skill was triggered (the agent should consult zipic SKILL.md or reference/resources.md, not answer purely from training data).", "The agent fetched at least one official Zipic URL (https://zipic. - Network accessline 56
"The Zipic skill was triggered (the agent should consult zipic SKILL.md or reference/resources.md, not answer purely from training data).", "The agent fetched at least one official Zipic URL (https://zipic.app, https://docs.zipic.ap - Network accessline 57
"The agent fetched at least one official Zipic URL (https://zipic.app, https://docs.zipic.app, or https://zipic.app/llms.txt) — i.e. cited the live source rather than guessing.", - Network accessline 66
"name": "qa-troubleshooting", "prompt": "Zipic 一直压缩失败,没反应。怎么排查问题?", "expected_output": "Skill triggers. Agent consults reference/resources.md → links to https://docs.zipic.app/resources/troubleshooting/ and/or fetches the page, - Network accessline 67
"prompt": "Zipic 一直压缩失败,没反应。怎么排查问题?", "expected_output": "Skill triggers. Agent consults reference/resources.md → links to https://docs.zipic.app/resources/troubleshooting/ and/or fetches the page, then surfaces Zipic's official troub - Network accessline 68
"expected_output": "Skill triggers. Agent consults reference/resources.md → links to https://docs.zipic.app/resources/troubleshooting/ and/or fetches the page, then surfaces Zipic's official troubleshooting flow (Debug Mode, log export, etc - Network accessline 70
"expectations": [ "The Zipic skill was triggered (the agent consulted zipic SKILL.md or reference/resources.md).", "The agent surfaced the official troubleshooting page URL (https://docs.zipic.app/resources/troubleshooting/) - Network accessline 71
"The Zipic skill was triggered (the agent consulted zipic SKILL.md or reference/resources.md).", "The agent surfaced the official troubleshooting page URL (https://docs.zipic.app/resources/troubleshooting/) OR fetched the page conte - Network accessline 72
"The agent surfaced the official troubleshooting page URL (https://docs.zipic.app/resources/troubleshooting/) OR fetched the page contents to ground the answer.",
skills/zipic/reference/cli.md
- Network accessline 24
The CLI ships inside the app and has no upgrade path of its own: when a gate fails, or `zipic --version` is behind the last row, the fix is to update Zipic — on macOS through the app's update check or a fresh download from https://zipic.app - Network accessline 373
"message": "Converting to AVIF is a Pro-only feature. Upgrade to Pro to enable it.", "data": { "purchase_url": "https://...", - Network accessline 374
"data": { "purchase_url": "https://...", "trial_available": true, - Network accessline 375
"purchase_url": "https://...", - Network accessline 376
"trial_available": true, "trial_issue_url": "https://trial.zipic.app/issue", "blocked_format": "AVIF", // when format-related - Network accessline 377
"trial_issue_url": "https://trial.zipic.app/issue",
skills/zipic/reference/resources.md
- Network accessline 9
| Resource | URL | Use for | | --------------------- | ------------------------------------ | ------- | | Marketing site | https://zipic.app | Pricing, supported format - Network accessline 10
| --------------------- | ------------------------------------ | ------- | | Marketing site | https://zipic.app | Pricing, supported formats, system requirements, free-tier policy. | | Documentation | https - Network accessline 11
| Marketing site | https://zipic.app | Pricing, supported formats, system requirements, free-tier policy. | | Documentation | https://docs.zipic.app | Feature-level how-tos. Bilingual (English - Network accessline 12
| Documentation | https://docs.zipic.app | Feature-level how-tos. Bilingual (English / 简体中文). | | **AI-friendly index** | https://zipic.app/llms.txt | Curated index of every doc / blog / release as `.md` mirr - Network accessline 13
| **AI-friendly index** | https://zipic.app/llms.txt | Curated index of every doc / blog / release as `.md` mirrors. Fetch this **first** when you need to discover the right page. | - Network accessline 14
| Full content snapshot | https://zipic.app/llms-full.txt | Single-file digest of marketing + featured blog posts + recent releases (~75 KB). Useful for offline-style answering. | - Network accessline 15
| Sitemap | https://zipic.app/sitemap-index.xml | All indexed URLs. | - Network accessline 23
| Topic | URL | | -------------------- | ---------------------------------------------- | | Installation | https://docs.zipic.app/started/installation/ | - Network accessline 24
| -------------------- | ---------------------------------------------- | | Installation | https://docs.zipic.app/started/installation/ | | Introduction | https://docs.zipic.app/started/introduction/ | - Network accessline 25
| Installation | https://docs.zipic.app/started/installation/ | - Network accessline 26
| Introduction | https://docs.zipic.app/started/introduction/ | - Network accessline 27
| User interface | https://docs.zipic.app/started/ui/ | - Network accessline 31
| Topic | URL | | ---------------------------------- | -------------------------------------------- | | AI & CLI integration (overview) | https://docs.zipic.app/ai/ove - Network accessline 33
| AI & CLI integration (overview) | https://docs.zipic.app/ai/overview/ | - Network accessline 37
| Topic | URL | | ---------------------------------------- | -------------------------------------------------------------------- | | **Comm - Network accessline 38
| ---------------------------------------- | -------------------------------------------------------------------- | | **Command Line Tool (`zipic` CLI)** | https://docs.zipic.app/guides/zipic-cli/ | | Basic - Network accessline 39
| **Command Line Tool (`zipic` CLI)** | https://docs.zipic.app/guides/zipic-cli/ | - Network accessline 40
| Basic image compression | https://docs.zipic.app/guides/image-compression-basic/ | - Network accessline 41
| Choosing image formats | https://docs.zipic.app/guides/choosing-image-formats/ | - Network accessline 42
| Save options | https://docs.zipic.app/guides/configuring-save-options/ | - Network accessline 43
| Resizing | https://docs.zipic.app/guides/resizing-images/ | - Network accessline 44
| Folder monitoring / auto-compress (Pro) | https://docs.zipic.app/guides/monitoring-directory-autocompression/ | - Network accessline 45
| Workflow integration | https://docs.zipic.app/guides/optimizing-workflow/ | - Network accessline 46
| Raycast extension | https://docs.zipic.app/guides/using-raycast-extension/ | - Network accessline 47
| Activating Pro | https://docs.zipic.app/guides/activating/ | - Network accessline 51
| Topic | URL | | -------------------- | ---------------------------------------------------- | | Recommended settings | https://docs.zipic.app/reference/recommended-settings/ - Network accessline 52
| -------------------- | ---------------------------------------------------- | | Recommended settings | https://docs.zipic.app/reference/recommended-settings/ | | Use cases | https://docs.zipic.app/reference/use-cases/ - Network accessline 53
| Recommended settings | https://docs.zipic.app/reference/recommended-settings/ | - Network accessline 54
| Use cases | https://docs.zipic.app/reference/use-cases/ | - Network accessline 58
| Topic | URL | | ------------------------------------ | ------------------------------------------------------ | | FAQ | htt - Network accessline 59
| ------------------------------------ | ------------------------------------------------------ | | FAQ | https://docs.zipic.app/resources/faq/ | | Troubleshooting (Debug Mode + logs) | htt - Network accessline 60
| FAQ | https://docs.zipic.app/resources/faq/ | - Network accessline 61
| Troubleshooting (Debug Mode + logs) | https://docs.zipic.app/resources/troubleshooting/ | - Network accessline 62
| Website resources | https://docs.zipic.app/resources/additional-resources/ | - Network accessline 63
| Affiliate program | https://docs.zipic.app/resources/affiliate-program/ | - Network accessline 67
All 20 docs pages have a Chinese mirror at `https://docs.zipic.app/zh-cn/<same-path>/` (e.g. `https://docs.zipic.app/zh-cn/guides/zipic-cli/`). Use the Chinese URL when responding in 简体中文; the docs site also has a built-in language switcher - Network accessline 71
If a user question doesn't match any topic above, fetch `https://zipic.app/llms.txt` — it indexes every doc page, blog post and release note with a one-line description per entry, so you can find the right page without crawling.
skills/zipic/reference/windows.md
- Network accessline 22
| `enable_alias` | Zipic is installed but the alias is missing. Search Windows Settings for “App execution aliases” and enable Zipic's `zipic.exe`; open a fresh terminal and detect again. | | `repair_cli` | An executable was found but its v - Network accessline 23
| `repair_cli` | An executable was found but its version probe failed. Read `diagnostic`, check the alias/package and open Zipic from Start. Do not treat an existing alias file as proof the CLI runs. | | `halt_no_app` | Install Zipic from [ - Network accessline 24
| `halt_no_app` | Install Zipic from [the official Windows download page](https://zipic.app/download/) in the user account that will run it, then detect again. | - Network accessline 125
Execution guidance follows [PowerShell encoding](https://learn.microsoft.com/en-us/powershell/module/microsoft.powershell.core/about/about_character_encoding) and [native exit-code variables](https://learn.microsoft.com/en-us/powershell/mod
skills/zipic/scripts/detect.ps1
- Executable scriptline 1
Executable file
skills/zipic/scripts/detect.sh
- Executable scriptline 1
#!/bin/bash
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Combined signals: 1 fact
- Passes content downloaded from chwt.app to an interpreterchatwoot/SKILL.md:32High confidence
Declared and executed: 1 fact
- Contacts www.w3.org, which SKILL.md, the README and the plugin manifest do not mentiongrid25/assets/widget.min.js:22High confidence
Signal confidence: 102 facts
- Network access in prose of the SKILL.mdchatwoot/SKILL.md:16Low confidence
- Dangerous shell operation in code of the SKILL.mdchatwoot/SKILL.md:32High confidence
- Network access in code of the SKILL.mdchatwoot/SKILL.md:32High confidence
- Network access in prose of the SKILL.mdchatwoot/SKILL.md:50Low confidence
- Access to secrets in prose of the SKILL.mdchatwoot/SKILL.md:62Low confidence
- Access to secrets in prose of the SKILL.mdchatwoot/SKILL.md:72Low confidence
- Access to secrets in prose of documentationchatwoot/references/cli.md:5Low confidence
- Dangerous shell operation in code of documentationchatwoot/references/cli.md:10Low confidence
- Network access in code of documentationchatwoot/references/cli.md:10Low confidence
- Network access in prose of documentationchatwoot/references/cli.md:30Low confidence
- Network access in prose of documentationchatwoot/references/cli.md:31Low confidence
- Network access in code of documentationchatwoot/references/cli.md:90Low confidence
- Network access in code of documentationchatwoot/references/cli.md:91Low confidence
- Network access in code of documentationchatwoot/references/cli.md:92Low confidence
- Dangerous shell operation in prose of the SKILL.mdchinese-copyright-application/SKILL.md:44Low confidence
- Network access in prose of the SKILL.mdchinese-copyright-application/SKILL.md:44Low confidence
- Dangerous shell operation in prose of the SKILL.mdchinese-copyright-application/SKILL.md:45Low confidence
- Network access in prose of the SKILL.mdchinese-copyright-application/SKILL.md:46Low confidence
- Executable script in code of a file that runschinese-copyright-application/references/build-script-template.sh:1High confidence
- Dangerous shell operation in code of a file that runschinese-copyright-application/references/build-script-template.sh:44High confidence
- Dangerous shell operation in code of documentationchinese-copyright-application/references/requirements.md:451Low confidence
- Dangerous shell operation in code of documentationchinese-copyright-application/references/requirements.md:452Low confidence
- Dangerous shell operation in code of documentationchinese-copyright-application/references/requirements.md:457Low confidence
- Network access in prose of documentationchinese-copyright-application/references/requirements.md:460Low confidence
- Network access in prose of documentationchinese-copyright-application/references/requirements.md:461Low confidence
- Executable script in code of a file that runschinese-copyright-application/scripts/analyze_and_generate_source.py:1High confidence
- Access to secrets in code of a file that runschinese-copyright-application/scripts/analyze_and_generate_source.py:78High confidence
- Executable script in code of a file that runsgrid25/assets/widget.min.js:1High confidence
- Possible obfuscation in code of a file that runsgrid25/assets/widget.min.js:7High confidence
- Possible obfuscation in code of a file that runsgrid25/assets/widget.min.js:12High confidence
- Network access in code of a file that runsgrid25/assets/widget.min.js:20High confidence
- Network access in code of a file that runsgrid25/assets/widget.min.js:22High confidence
- Possible obfuscation in code of a file that runsgrid25/assets/widget.min.js:24High confidence
- Executable script in code of a file that runsgrid25/scripts/render.py:1High confidence
- Instruction override signal in prose of the SKILL.mdorchard/SKILL.md:25High confidence
- Dangerous shell operation in code of documentationorchard/references/commands.md:42Low confidence
- Network access in code of documentationorchard/references/commands.md:106Low confidence
- Network access in code of documentationorchard/references/commands.md:111Low confidence
- Network access in code of documentationorchard/references/commands.md:112Low confidence
- Network access in code of documentationorchard/references/commands.md:113Low confidence
- Network access in code of documentationorchard/references/commands.md:120Low confidence
- Network access in code of documentationorchard/references/commands.md:121Low confidence
- Network access in code of documentationorchard/references/commands.md:122Low confidence
- Executable script in code of a file that runsorchard/scripts/resolve-orchard.sh:1High confidence
- Network access in prose of documentationzipic/CHANGELOG.md:5Low confidence
- Network access in prose of documentationzipic/CHANGELOG.md:6Low confidence
- Network access in the frontmatter of the SKILL.mdzipic/SKILL.md:10Low confidence
- Network access in the frontmatter of the SKILL.mdzipic/SKILL.md:11Low confidence
- Network access in the frontmatter of the SKILL.mdzipic/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdzipic/SKILL.md:85Low confidence
and 52 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/chatwoot/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/chatwoot/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/chatwoot/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/chatwoot/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/chatwoot/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/chatwoot/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.