メニュー
Read-only local macOS Things queries and summaries when the user asks about their Things tasks, Today list, Inbox, projects, tags, completed or logbook history, or task search. Read-only, never writes.
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。
SOC 職業分類に基づく
Operate Linux servers over SSH: Debian/Ubuntu systemd setup and maintenance, distro-aware health and intrusion audits, SSH, firewall and container exposure, swap, and proxy/VPN setup or tuning including Snell repair. Use for unclear or possibly compromised hosts as well as known hosts. Not for macOS network problems; Snell evidence-only audits belong to surge, and the REALITY+HY2 stack belongs to sing-box-reality-hy2.
Start or continue a practical Web full-stack app on a React + TanStack Router + Vite + Convex stack — a dashboard, SaaS, internal tool, or product prototype needing a coherent stack choice, scaffold command, auth/data boundary, and first usable feature. Not for isolated changes to an existing feature, and not for Next.js/SSR/SEO sites, React Native, or payment flows; a live-built Next.js Convex app belongs to convex:quickstart.
Deploy, repair, and validate a narrow sing-box stable stack: VLESS REALITY Vision on TCP/443 plus Hysteria2 on UDP/443. Use for Debian/Ubuntu systemd VPS setup, Linux system-level TUN, cross-platform client configs, migration off Clash/Mihomo, REALITY/HY2 testing, or a 科学上网/翻墙/梯子 request when the user is open to this REALITY+HY2 stack. Surge-related macOS network triage and Snell audits belong to the surge skill.
macOS network triage when Surge is installed, active, or plausibly in the network path: Surge CLI, profile syntax, Enhanced Mode / System Proxy / DNS failures, policy routing and smoke tests, Tailscale coexistence, and Snell VPS evidence audits with repair plans. Server-side execution belongs to linux-server; REALITY+HY2 deployment belongs to sing-box-reality-hy2.
Set up scheduled agent work where the agent itself runs each check and nothing is deployed: do something later, keep checking until something changes, watch for something to finish and report it, or follow up periodically. Use when the user asks to schedule, loop, keep watching, or be reminded later — decide the scheduling shape first, then create it with the harness's own scheduling mechanism. Not for deploying durable monitoring infrastructure — that is end-to-end-monitoring.
Use when the user wants to review or summarize Feishu/Lark meetings over a date range, such as 总结这两周的会 or a meeting weekly report: find minute_tokens, pull transcript files, inspect coverage and duplicate evidence, build Chinese prompts, and optionally fan summaries out to Amp. Do not use for a single minute_token or single-meeting lookup (that is the lark skill), or for turning chat history into a report corpus — that is lark-chat-corpus.
| name | things |
| description | Read-only local macOS Things queries and summaries when the user asks about their Things tasks, Today list, Inbox, projects, tags, completed or logbook history, or task search. Read-only, never writes. |
| metadata | {"version":"3"} |
把用户的口语问题翻成一次 things_query.py 查询。用户要改 Things，说明这是只读工具，问他要不要另开一个写入动作，得到明确同意后再走这个 skill 之外的写入方式，不在这里替他改。
入口是 scripts/things_query.py，通过 uv run --script 跑，路径按这个 skill 目录的绝对路径解析。collection、filter、flag 的权威清单是 --help。
SKILL_DIR=/absolute/path/to/things
uv run --script "$SKILL_DIR/scripts/things_query.py" --collection today --format json
uv run --script "$SKILL_DIR/scripts/things_query.py" --help
用户不说 collection 名，也不说 flag。听意图，选最小够用的 collection 加 filter。能猜就猜，查错代价小，再查一次就行，不用停下来问。
| 用户会说 | collection + filter |
|---|---|
| 今天要干嘛、手头有啥 | --collection today |
| 收件箱里有啥没整理 | --collection inbox |
| 有 deadline 的、快到期 | --collection deadlines |
| 找关于 X 的任务 | --collection todos --search X |
| X 这事办完没、这周做完了啥 | --collection completed --search X |
| 翻旧账、历史归档流水 | --collection logbook |
| 某个项目或 tag 下的 | --collection projects 或 --collection tags |
| 接下来排期、明天要做的 | --collection upcoming |
| 最近加的、这周新增 | --collection todos --last 1w |
这张表是常见映射，不是全集。翻不准或用户问了别的，跑 --help 看还有哪些 collection 和 filter，比如按状态筛的 --status、限量的 --limit、带 UUID 的 --include-uuid。用户说「today」「明天」「昨天」这类相对日子时，先跑 date '+%Y-%m-%d %H:%M:%S %Z %z' 确认本机日期和时区。本工具按 collection 取，没有任意某一天的精确过滤，「明天」落到 upcoming，「昨天完成的」落到 completed。Things Today 是预测视图，不是简单的 start_date == 今天，语义细节看 reference。
--count-only 给数量，别一上来倒出全部任务。notes、UUID、数据库路径，用户明确要 notes 才加 --include-notes。date 拿到的本机绝对日期，比如「按本机 的 Today 列表」。结果是 Things Today 预测视图而非精确日期过滤时，点明这一点。日期语义、today() 漏算的未生成重复任务、数据库路径、权限报错，读 references/things-semantics.md。