@mkterswingman/5mghost-wonder 0.0.1

package/skills/setup-5mghost-wonder/SKILL.md

@@ -0,0 +1,245 @@
+---
+name: setup-5mghost-wonder
+description: Use this skill when the user wants to install or set up wonder, says "安装 wonder", "设置 wonder", "install wonder", "setup wonder", or when wonder is not yet installed or configured. Also use when `wonder check` reports missing dependencies.
+---
+
+# Setup wonder — 企微文档 CLI 安装向导
+
+You are guiding the user through installing and configuring `wonder`, the WeCom document reader CLI.
+
+Execute each step in order using the Bash tool. Stop and ask for user interaction only when a step requires it (e.g., browser OAuth, QR code scan). After each detection step, only proceed to installation if the tool is missing.
+
+---
+
+## Step 1 — Check if wonder CLI is installed
+
+```bash
+wonder --version
+```
+
+**If missing**, install globally:
+
+```bash
+npm install -g @mkterswingman/5mghost-wonder
+```
+
+Verify:
+
+```bash
+wonder --version
+```
+
+---
+
+## Step 2 — mkterswingman Auth Login
+
+Check current status:
+
+```bash
+wonder auth status
+```
+
+If not logged in, run:
+
+```bash
+wonder auth login
+```
+
+A browser window will open for OAuth. Wait for the user to complete login, then verify:
+
+```bash
+wonder auth status
+```
+
+For headless or CI environments, use PAT instead:
+
+```bash
+wonder auth login --pat
+```
+
+---
+
+## Step 3 — WeCom Cookie (企微扫码)
+
+Check current cookie status:
+
+```bash
+wonder wecom status
+```
+
+If expired or missing, run:
+
+```bash
+wonder wecom cookie
+```
+
+This launches the local Chrome/Edge browser via CDP. The user must scan the QR code in the browser using their WeCom mobile app. Wait for the user to confirm they have scanned and logged in, then verify:
+
+```bash
+wonder wecom status
+```
+
+---
+
+## Step 4 — Detect and install docx skill
+
+Check plugin cache first:
+
+```bash
+ls ~/.claude-internal/plugins/cache/anthropic-agent-skills/document-skills/*/skills/docx/SKILL.md 2>/dev/null | head -1
+```
+
+Check user skills:
+
+```bash
+ls ~/.claude-internal/skills/docx/SKILL.md 2>/dev/null
+```
+
+**If neither exists**, download from GitHub:
+
+```bash
+mkdir -p ~/.claude-internal/skills/docx
+curl -fsSL https://raw.githubusercontent.com/anthropics/skills/main/skills/docx/SKILL.md \
+  -o ~/.claude-internal/skills/docx/SKILL.md
+```
+
+Confirm:
+
+```bash
+ls -lh ~/.claude-internal/skills/docx/SKILL.md
+```
+
+---
+
+## Step 5 — Detect and install pptx skill
+
+Check plugin cache first:
+
+```bash
+ls ~/.claude-internal/plugins/cache/anthropic-agent-skills/document-skills/*/skills/pptx/SKILL.md 2>/dev/null | head -1
+```
+
+Check user skills:
+
+```bash
+ls ~/.claude-internal/skills/pptx/SKILL.md 2>/dev/null
+```
+
+**If neither exists**, download from GitHub:
+
+```bash
+mkdir -p ~/.claude-internal/skills/pptx
+curl -fsSL https://raw.githubusercontent.com/anthropics/skills/main/skills/pptx/SKILL.md \
+  -o ~/.claude-internal/skills/pptx/SKILL.md
+```
+
+Confirm:
+
+```bash
+ls -lh ~/.claude-internal/skills/pptx/SKILL.md
+```
+
+---
+
+## Step 6 — Detect and install LibreOffice
+
+```bash
+which soffice
+```
+
+**If missing**, install by platform:
+
+**macOS:**
+
+```bash
+brew install --cask libreoffice
+```
+
+**Windows:**
+
+```bash
+winget install LibreOffice.LibreOffice
+```
+
+Or download manually: https://www.libreoffice.org/download
+
+**Linux (Debian/Ubuntu):**
+
+```bash
+sudo apt install -y libreoffice
+```
+
+**Linux (Fedora/RHEL):**
+
+```bash
+sudo dnf install -y libreoffice
+```
+
+Verify after install:
+
+```bash
+which soffice && soffice --version
+```
+
+---
+
+## Step 7 — Detect and install pandoc
+
+```bash
+which pandoc
+```
+
+**If missing**, install by platform:
+
+**macOS:**
+
+```bash
+brew install pandoc
+```
+
+**Windows:**
+
+```bash
+winget install pandoc
+```
+
+**Linux (Debian/Ubuntu):**
+
+```bash
+sudo apt install -y pandoc
+```
+
+**Linux (Fedora/RHEL):**
+
+```bash
+sudo dnf install -y pandoc
+```
+
+Verify after install:
+
+```bash
+pandoc --version | head -1
+```
+
+---
+
+## Step 8 — Final verification
+
+Run the built-in health check:
+
+```bash
+wonder check
+```
+
+All items should show ✅. If any item fails, re-run the relevant step above.
+
+---
+
+## Reference links
+
+| Dependency | Source |
+|-----------|--------|
+| docx skill | https://github.com/anthropics/skills/tree/main/skills/docx |
+| pptx skill | https://github.com/anthropics/skills/tree/main/skills/pptx |
+| LibreOffice | https://www.libreoffice.org/download |
+| pandoc | https://pandoc.org/installing.html |

package/skills/use-5mghost-wonder/SKILL.md

@@ -0,0 +1,240 @@
+---
+name: use-5mghost-wonder
+description: Use this skill when the user shares a URL containing "doc.weixin.qq.com", mentions 企微文档, 企业微信文档, 在线表格, 腾讯文档, wecom doc, wechat doc, wecom document, or asks you to read a WeCom document. Activate automatically on any doc.weixin.qq.com link.
+---
+
+# use-5mghost-wonder — 企微文档读取操作指南
+
+## Session Initialization (first use only per session)
+
+The **first time** you encounter a WeCom document URL in a session, run these checks before processing the document. Remember you have already done this — do not repeat in subsequent calls within the same session.
+
+```bash
+# 1. Check for updates
+wonder update
+
+# 2. Check WeCom cookie status
+wonder wecom status
+```
+
+If `wonder wecom status` reports that the cookie is expired or missing:
+
+```bash
+wonder wecom cookie
+```
+
+Wait for the user to complete the QR code scan in the browser, then verify:
+
+```bash
+wonder wecom status
+```
+
+Proceed only after cookie is valid.
+
+---
+
+## URL Type Routing
+
+Identify the document type from the URL path prefix:
+
+| URL prefix | Type | Action |
+|-----------|------|--------|
+| `sheet/e3_` | xlsx spreadsheet | Two-step: meta → tab data |
+| `doc/w3_` | docx document | Download → parse with docx skill |
+| `doc/e2_` | docx document | Download → parse with docx skill |
+| `slide/p3_` | pptx presentation | Download → parse with pptx skill |
+| `smartpage/a1_` | Smart page | ❌ Not supported in v1 |
+| `mind/m4_` | Mind map | ❌ Not supported in v1 |
+
+---
+
+## xlsx Workflow (`sheet/e3_`)
+
+### Step 1 — Get metadata
+
+```bash
+wonder read <url>
+```
+
+Output is a JSON with tab list and row/column counts:
+
+```json
+{
+  "type": "sheet",
+  "title": "文档标题",
+  "tabs": [
+    { "name": "Sheet1", "rows": 50, "cols": 12 },
+    { "name": "汇总", "rows": 20, "cols": 8 }
+  ]
+}
+```
+
+Decide which tab(s) to read based on the user's question and the metadata.
+
+### Step 2 — Read specific tab
+
+```bash
+wonder read <url> --tab <tab-name>
+```
+
+Output is a structured JSON:
+
+```json
+{
+  "tab": "Sheet1",
+  "maxRow": 50,
+  "maxCol": 12,
+  "cells": [
+    { "row": 1, "col": 1, "text": "标题" },
+    { "row": 3, "col": 4, "image": { "path": "/path/to/xl/media/image1.png", "width": 200, "height": 150 } }
+  ],
+  "merges": [
+    { "startRow": 1, "startCol": 1, "endRow": 1, "endCol": 3 }
+  ]
+}
+```
+
+Consume this JSON directly to answer the user's question.
+
+### Viewing embedded images
+
+Image cells have a `path` field pointing to the local extracted file. Use the Read tool to view:
+
+```
+Read("/Users/<you>/Downloads/5mghost-wonder/media/image3.png")
+```
+
+**Note:** Images are full-resolution originals (up to several MB each). Only load images the user specifically asks about.
+
+---
+
+## docx Workflow (`doc/w3_`, `doc/e2_`)
+
+### Step 1 — Download
+
+```bash
+wonder read <url>
+```
+
+Output:
+
+```json
+{ "type": "doc", "path": "/Users/<you>/Downloads/5mghost-wonder/filename.docx" }
+```
+
+### Step 2 — Read content
+
+**Read text** (recommended first step):
+
+```bash
+pandoc <path> -o /tmp/wonder-doc-output.md && cat /tmp/wonder-doc-output.md
+```
+
+**View full-page layout with images** (when layout matters):
+
+```bash
+soffice --headless --convert-to pdf --outdir /tmp/ <path>
+```
+
+Then use the Read tool on the generated PDF.
+
+**Access embedded images** (when individual images are needed):
+
+```bash
+mkdir -p /tmp/wonder-doc-unpack && cp <path> /tmp/wonder-doc-unpack/doc.zip && unzip -o /tmp/wonder-doc-unpack/doc.zip -d /tmp/wonder-doc-unpack/
+```
+
+Then use Read tool on files in `/tmp/wonder-doc-unpack/word/media/`.
+
+---
+
+## pptx Workflow (`slide/p3_`)
+
+### Step 1 — Download
+
+```bash
+wonder read <url>
+```
+
+Output:
+
+```json
+{ "type": "slide", "path": "/Users/<you>/Downloads/5mghost-wonder/filename.pptx" }
+```
+
+### Step 2 — Read content
+
+**Read text** (recommended first step):
+
+```bash
+pandoc <path> -o /tmp/wonder-slide-output.md && cat /tmp/wonder-slide-output.md
+```
+
+**View slide layout**:
+
+```bash
+soffice --headless --convert-to pdf --outdir /tmp/ <path>
+```
+
+Then use the Read tool on the generated PDF.
+
+**Access embedded images**:
+
+```bash
+mkdir -p /tmp/wonder-pptx-unpack && cp <path> /tmp/wonder-pptx-unpack/slide.zip && unzip -o /tmp/wonder-pptx-unpack/slide.zip -d /tmp/wonder-pptx-unpack/
+```
+
+Then use Read tool on files in `/tmp/wonder-pptx-unpack/ppt/media/`.
+
+### ⚠️ Known issue: python-pptx slice crash
+
+If you use python-pptx to process WeCom pptx files, **do not use slice syntax**:
+
+```python
+# ❌ This crashes on WeCom pptx
+for slide in prs.slides[:5]:
+    ...
+
+# ✅ Use iteration instead
+for slide in prs.slides:
+    ...
+```
+
+---
+
+## Unsupported types
+
+**smartpage (`smartpage/a1_`):**
+
+> 当前版本不支持智能文档（smartpage）。建议在浏览器中手动打开文档，选择"导出为 PDF"或"复制内容"。
+
+**mind (`mind/m4_`):**
+
+> 当前版本不支持思维导图（mind）。
+
+---
+
+## Known issues
+
+| Issue | Detail | Workaround |
+|-------|--------|-----------|
+| pptx slice crash | `prs.slides[:N]` → `AttributeError: 'list' object has no attribute 'rId'` | Use `for slide in prs.slides` |
+| Cookie expiry | Cookie valid for 7–30 days | Run `wonder wecom cookie` to refresh |
+| xlsx images are full-size | Original images can be up to 6 MB each | Only read images when user specifically needs them |
+| smartpage unsupported | Export API returns 0% progress forever | Manual browser export |
+
+---
+
+## CLI command reference
+
+```
+wonder read <url>                  # Auto-detect type; xlsx → metadata; doc/slide → download
+wonder read <url> --tab <name>     # xlsx: get full data for specified tab
+wonder read <url> --save <dir>     # Set output directory (default: ~/Downloads/5mghost-wonder/)
+
+wonder wecom status                # Check cookie validity
+wonder wecom cookie                # Refresh cookie via browser QR scan
+wonder update                      # Update to latest version
+wonder check                       # Health check for all dependencies
+wonder auth status                 # Check mkterswingman auth status
+```

package/skills.manifest.json

@@ -0,0 +1,36 @@
+{
+  "schemaVersion": 1,
+  "product": "5mghost-wonder",
+  "skills": [
+    {
+      "name": "setup-5mghost-wonder",
+      "source": { "type": "local", "path": "./skills/setup-5mghost-wonder" },
+      "targets": [
+        "claude",
+        "claude-internal",
+        "codex",
+        "codex-internal",
+        "gemini",
+        "gemini-internal",
+        "openclaw",
+        "workbuddy",
+        "codebuddy"
+      ]
+    },
+    {
+      "name": "use-5mghost-wonder",
+      "source": { "type": "local", "path": "./skills/use-5mghost-wonder" },
+      "targets": [
+        "claude",
+        "claude-internal",
+        "codex",
+        "codex-internal",
+        "gemini",
+        "gemini-internal",
+        "openclaw",
+        "workbuddy",
+        "codebuddy"
+      ]
+    }
+  ]
+}