メニュー
This skill should be used when the user asks to "process inbox", "auto process", "file this note", "triage inbox", "route this to the right place", or needs to automatically move notes from 0-Inbox to their correct PARA destination.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/JSai23/claude-tooling --skill auto-process-aコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
Pre-flight checks and launch for agent loops. Validates branch state, session prompts, creates loop directory structure, and launches run.sh in a tmux session. Use when the user wants to start a new agent loop in the current repo.
Cross-repo visibility for agent loops. Lists running, completed, and crashed loops. Reads the registry and per-repo tracking logs. Shows tmux attach commands. Use when checking what loops are active, what ran recently, or loop details.
SKILL.md を表示中
SOC 職業分類に基づく
| name | auto-process-a |
| type | action |
| description | This skill should be used when the user asks to "process inbox", "auto process", "file this note", "triage inbox", "route this to the right place", or needs to automatically move notes from 0-Inbox to their correct PARA destination. |
| argument-hint | [filename(s)] or blank for all inbox |
Action skill — Inbox processing workflow: read intent, determine destination, confirm, file, update living docs.
Process inbox items: read intent, classify, file, rename, connect, and update living docs. Designed for the librarian agent but usable standalone.
0-Inbox/0-Inbox/Read the note. Check frontmatter for intent signals left by the writer or thinker:
| Field | Meaning |
|---|---|
filing-hint | Suggested destination (area name, project name, "resource", "unsure") |
context | Freeform context — what prompted this, what it relates to |
source: thinker | Came from a synthesis session — handle with care |
type | dump, note, clip, edit |
tags | Knowledge role: seed, thread, tool, question, insight |
If no intent signals, classify from content.
Filing cascade (first match wins):
When filing-hint exists, treat as strong signal but verify.
qmd vsearch "key content from the note" --files
Auto-file when:
filing-hint aligns with search resultsAsk the user when:
filing-hint: unsure or missing with no clear matchPreserve the raw capture before modifying. Rename to YYYY-MM-DD_descriptive-slug.md but keep frontmatter and content as-is — naming is the one thing we always enforce, even on raw archives:
mkdir -p "04-archive/inbox"
cp "0-Inbox/original-name.md" "04-archive/inbox/YYYY-MM-DD_slug.md"
type: note if missing (keep original type if appropriate)created: YYYY-MM-DD using today's date if missing#seed, #thread, #tool, #question, #insight)status (draft, refining, or omit for stable)filing-hint, context, source — they served their purposeRename to YYYY-MM-DD_descriptive-slug.md, then move to destination:
mv "0-Inbox/original-name.md" "2-Areas/area-name/YYYY-MM-DD_slug.md"
Read the parent MOC or project brief. Add the note with annotation:
- [[YYYY-MM-DD_slug]] — brief description of what the note covers
For thinker synthesis (source: thinker):
## Related sectionsFind related notes via semantic search and structural analysis. Add ## Related section if strong connections exist. Only add connections that are clear and useful.
For notes with type: edit:
targets array from frontmatterAfter processing, show summary:
## Inbox Processing Report
### Filed
- "Raw thoughts on agents" → 2-Areas/ai-dev-ecosystem/2025-02-07_agent-thoughts.md
- "Market data notes" → 1-Projects/polymarket-framework/2025-02-07_market-data.md
### Living Docs Updated
- 00_ai-dev-ecosystem.md — added link to agent-thoughts
- 00_polymarket-framework.md — added link to market-data
### Connections Found
- agent-thoughts ↔ agentic-primitives (shared concepts)
### Needs Attention
- "Ambiguous note" — couldn't determine destination, left in inbox
Reindex semantic search:
qmd update