skills/review/SKILL.md
TwinMind review and maintenance engine. Use for vault health checks, seed card review, index verification/rebuild, MOC management, and vault status summaries. Triggers on: 'vault status', '知識庫狀況', 'health report', '健康報告', 'verify index', '檢查索引', 'rebuild index', '重建索引', 'review seeds', '有哪些 seed', 'update MOC', or any request about knowledge base maintenance and overview.
npx skillsauth add VolderLu/TwinMind reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
知識庫的維護和回顧工具。大多數操作是唯讀的(看看知識庫的狀態),但索引修復/重建會修改檔案。
唯讀操作不需觸發 post-op。索引修復/重建完成後透過 Bash tool 執行 node .claude/twinmind/bin/tm-post-op.mjs --layer both --event '{"event_type":"INDEX_REBUILT","event_context":{}}' 觸發 post-op pipeline。
從 vault-index.json 產出摘要,不掃描檔案:
| 項目 | 來源 |
|------|------|
| 卡片總數 | stats.total_cards |
| 類型分佈 | 遍歷 notes 按 type 分組計數 |
| 成熟度分佈 | 遍歷 notes 按 status 分組計數 |
| 前 5 大領域 | stats.domains 依計數降序取前 5 |
| 活躍專案數 | projects 中 status == "active" 的數量 |
| 最後更新 | stats.last_updated |
空 vault(total_cards == 0):「知識庫目前還沒有卡片,試著分享一個想法或知識吧!」
幫助使用者發展未成熟的知識卡片——seed 是剛記錄但還沒充分發展的想法。
摘要統計:seed 總數、佔比(%)、seed 最多的領域。
篩選與排序(支援指定 domain):
發展建議(依優先序取第一個符合的):
無 seed → 「所有卡片已超越 seed 階段」
四項健康指標的整合分析。空 vault 不適用。
完整指標定義和評級規則,請讀取 references/health-indicators.md。
指標摘要:
評級:0 警告 = 良好、1-2 = 尚可、≥3 = 需要關注
vault-index.json 所有 notes 的 pathCards/ 和 Sources/ 的 .md 檔案孤兒移除:從 notes 移除、更新 stats、清理 links_to/linked_from 引用。 未追蹤新增:讀取 frontmatter,生成 summary,加入 notes 和 stats。
既有 index 有資料時先確認再覆寫。掃描所有 .md、重建 notes/stats/links、保留 projects/areas。寫入前執行九項一致性不變式驗證,發現不一致時在記憶體中修正後再寫入,並在摘要中報告修正項目。完整程序請讀取 references/index-rebuild.md。
檢查 Inbox 中過期的 pending 項目,提醒使用者處理:
從 vault-index.json 的 inbox 篩選 status == "pending" 的項目
讀取 config.md 的 memo_stale_days(預設 7)
計算每個 pending 項目的存在天數(今天 - created)
列出超過 memo_stale_days 的項目,標記為「過期」
顯示格式:
📥 Inbox 過期項目(超過 7 天未處理):
- 📝 memo: <text>(<created>,已 N 天)
- 💡 idea: <text>(<created>,已 N 天)
建議:升格(promote)、捨棄(dismiss)、或保留
無過期項目 → 「Inbox 沒有過期項目」
檢查長時間未完成的 active actions:
從 vault-index.json 的 standalone_actions 篩選 status == "active"
讀取 config.md 的 action_stale_days(預設 14)
對每個 active action,讀取其檔案取得 created 日期
列出超過 action_stale_days 的 actions
顯示格式:
⚡ 過期 Actions(超過 14 天未完成):
- <title>(<created>,已 N 天)tasks: <done>/<total>
建議:繼續推進、拆分為專案、或標記完成
無過期 action → 「沒有過期的行動」
testing
TwinMind task engine — manages standalone tasks (life chores, errands, quick todos). Use this skill when the user mentions a simple, concrete thing they need to do that doesn't belong to any project or action. Classic triggers: short imperative sentences like '買牛奶', '繳電費', '回覆 email', '預約牙醫', or explicit task operations like '加個待辦', 'add task', 'task done', '完成 task', '刪除 task', 'delete task', '列出 tasks', 'list tasks', '待辦清單'. The distinguishing feature of a standalone task is that it's too small for an Action and not tied to any project. If the user mentions a project name, route to twinmind:project. If it's a multi-step endeavor, consider twinmind:action instead.
tools
Initialize a new TwinMind vault in the current directory. Creates TwinMind.md configuration and vault directory structure from templates. Use when starting a fresh knowledge vault or setting up TwinMind in a new project.
development
Classifies user knowledge-base input into one of 9 intent categories (capture, inbox, query, project, action, task, area, review, connect) using signal words, priority rules, compound intent handling, and fuzzy fallback matching. Invoke BEFORE dispatching to any twinmind:* skill when the user provides knowledge-base input. Do NOT skip this step — the session startup skeleton only has a summary table; this skill has the complete rules needed for accurate classification.
data-ai
Searches stored cards by domain, type, status, or keyword. Recommends semantically related cards using AI language understanding. Queries inbox, action, task, area, and project data from the vault index. Use when the user asks to search, find, list, filter, or browse cards, or wants recommendations for related content. Triggers: '搜尋', '找', 'search', 'find', '列出', 'list', '有沒有', '跟X相關的', '有幾張', 'how many', '統計'.