メニュー
Use when the user asks "what should I work on", "what's next", "highest priority", "next item", or invokes /compass-rose:next-item. Reads local issue files and recommends the highest-priority open item.
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。
SOC 職業分類に基づく
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/rjroy/vibe-garden --skill next-item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。
SKILL.md を表示中
Use when extracting knowledge from .lore/ artifacts into the reference wiki. Converts work artifacts (retros, specs, plans, research, notes) into structured wiki pages grouped by knowledge type. Reads Markdown or HTML sources and writes Markdown by default. Triggers include "ingest this", "extract knowledge from", "add this to the wiki", "update the reference from", and "populate the field guide".
This skill is used when the project wiki needs a health check. Triggers include 'lint the wiki', 'check wiki health', 'run field-guide lint', 'are there stale wiki pages', 'find orphaned pages', 'check for contradictions in the wiki'.
Use when asking questions about the project wiki, querying accumulated knowledge, searching project decisions or lessons. Triggers include "query the wiki", "what does the wiki say about", "search project knowledge", and natural language questions directed at the field-guide wiki.
| name | next-item |
| description | Use when the user asks "what should I work on", "what's next", "highest priority", "next item", or invokes /compass-rose:next-item. Reads local issue files and recommends the highest-priority open item. |
| allowed-tools | Bash, Read, Glob |
You are in Next Item Recommendation mode. Read local issue files, sort by priority and age, and recommend what to work on next.
Use Glob to find all issue files:
.lore/work/issues/*.html
If no files exist, tell the user there are no issues tracked yet and suggest /compass-rose:add-item.
For each file, extract the following meta tags and the page title. The most efficient approach is a single grep pass:
grep -h 'name="status"\|name="priority"\|name="size"\|name="date"\|<title>' .lore/work/issues/*.html
Fields to collect per file:
status — keep only files where this is openpriority — P0, P1, P2, P3, or absentsize — any value present (e.g. S, M, L, XL)date — ISO date stringtitle — from the <title> tagIf no open issues exist after filtering, say so clearly and suggest /compass-rose:add-item.
Sort the open issues by:
Display the top 2–3 as a table:
| # | Title | Priority | Size | Date |
|---|------------------------------|----------|------|------------|
| 1 | Fix session expiry handling | P0 | S | 2026-03-12 |
| 2 | Add export to CSV | P1 | M | 2026-02-28 |
| 3 | Improve error messages | P1 | S | 2026-04-01 |
Follow with a recommendation paragraph: name the top item, its priority, and a plain-language rationale for why it ranks first (priority level, age, or both if relevant).
If two items tie on priority, note that date broke the tie.
No open issues: State that clearly. Suggest /compass-rose:add-item to create the first one.
Missing priority on some items: Treat them as lower than P3. Mention in the output that some items have no priority set.
Missing date on some items: Sort them after dated items within the same priority band.
/compass-rose:add-item — create a new issue/compass-rose:backlog — review the full backlog/compass-rose:reprioritize — adjust priorities across the backlog