Batch populate summary fields using content analysis
中文简介正在准备中。当前显示原文说明。
Check for unprocessed files and suggest appropriate skills to handle them
中文简介正在准备中。当前显示原文说明。
安装前可以查看交给 AI 代理的指令内容。
Monitor for unprocessed files in the vault and suggest the appropriate skill to handle each.
/inbox-watcher # Check and classify all unprocessed files
/inbox-watcher --process # Check and auto-process with suggested skills
npm run inbox:check 2>/dev/null
If no inbox script output, fall back to scanning common drop locations:
# Check for files that may need processing
ls -t voicenotes/*.md 2>/dev/null | head -10
ls -t Attachments/*.pdf Attachments/*.pptx 2>/dev/null | head -10
Find markdown files that lack a type field in frontmatter (potential unprocessed content):
node .claude/scripts/graph-query.js --where="type=" --json 2>/dev/null
If graph-query.js does not support querying for empty/null type, use a Grep fallback:
# Find notes without a type field in frontmatter
find . -name "*.md" -not -path "./.claude/*" -not -path "./.obsidian/*" -not -path "./node_modules/*" -not -path "./Templates/*" -not -path "./Archive/*" | while read f; do
if \! head -20 "$f" | grep -q "^type:"; then echo "$f"; fi
done
For each unprocessed file, suggest the appropriate skill:
| File Pattern | Suggested Skill | Rationale |
|---|---|---|
voicenotes/*.md | /meeting or /daily | Voice transcriptions → meeting notes or daily entries |
Attachments/*.pdf | /pdf-to-page | PDFs → structured page notes |
Attachments/*.pptx | /pptx-to-page | PowerPoints → page notes with slide images |
*.csv in root | /csv-to-page or /csv-to-sql | Data files → markdown tables or SQLite |
Untyped .md at root | /incubator or manual triage | Loose notes need classification |
Email - *.md without type | /email | Email drafts needing frontmatter |
## Inbox Report — YYYY-MM-DD
### Unprocessed Files (N found)
| # | File | Type | Suggested Action |
|---|------|------|-----------------|
| 1 | voicenotes/2026-02-13... | Voice note | `/meeting` — transcribe to meeting note |
| 2 | Attachments/report.pdf | PDF | `/pdf-to-page` — extract to page |
### Quick Actions
- Process all: `/inbox-watcher --process`
- Process one: Run the suggested skill command
If --process flag is set, run npm run inbox:process and then invoke the suggested skill for each file sequentially, confirming with the user before each.
--process is explicitly requestedArchive/, Templates/, and .claude/还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Batch populate summary fields using content analysis
中文简介正在准备中。当前显示原文说明。
Batch auto-tag untagged notes using content analysis
中文简介正在准备中。当前显示原文说明。
Generate C4 architecture diagrams from system notes
中文简介正在准备中。当前显示原文说明。
Create and edit Obsidian Canvas files for architecture visualization
中文简介正在准备中。当前显示原文说明。
Check Outlook inbox and update daily note with message summary
中文简介正在准备中。当前显示原文说明。
Stage and commit vault changes with UK English conventional commit messages
中文简介正在准备中。当前显示原文说明。