本文へ移動
cccskills
無料GitHub で公開

pb-week-plan

Turn your scattered to-do lists and notes into one prioritised plan for the week, with at most 3 must-do items per day. Use for "plan my week", "what should I do this week", "sort my to-dos", "weekly plan from my notes". Nothing leaves your computer unless you opt in to steps 4 or 8.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md2.5 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Plan my week

What you get: one prioritised plan for this week, built from your scattered to-do lists and notes.

Inputs

  • Folders with your to-dos and notes — you name them
  • A calendar file (.ics) — optional, exported from your calendar app
  • A save folder — asked once; default ./pb-week-plan-<date>/

Steps

  1. Ask once — save folder, folders with to-dos and notes, optional calendar file → run-log.md — the folders exist
  2. Read the to-dos and notes → inbox.md, every open item with its source file and line — at least one item, otherwise stop and ask
  3. memb-skill — search open commitments and deadlines → added to inbox.md tagged [memB] — skipped and logged if memB is not installed
  4. github — only if you opt in and gh (external) is installed: your own open pull requests → added to inbox.md — your choice recorded
  5. Read the calendar file → calendar.md with the fixed appointments — skipped if none was given
  6. concise-planning — inbox.md and calendar.md → week-plan.md, per day Must (max 3), Should, Could — every line traces to a line in inbox.md or calendar.md; nothing invented
  7. Show week-plan.md in full and apply your edits until you approve — approval logged
  8. memb-skill — optional, ask first: store the approved Must items — memory ids logged

Nothing in this plan is sent anywhere, so there is no GO step. It only reads the files you named and writes into the save folder, except the opt-in steps 4 (gh queries GitHub) and 8 (writes memB).

Run log: run-log.md in the save folder. One line per step as it completes (N. done|skipped|failed — file — check result). If a check fails, stop, write the failure into the log and tell the user.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Use when manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Use when a hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Reference for how BDB structures autonomous software engineering work — the seven-node dispatcher graph (Architect, TechLead, UI/UX, Engineering, Media/EventTech, Reviewer, Shipping) that /startcycle-graph actually runs. Use when you need the high-level lifecycle framing without inventing your own process.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Tools are how AI agents interact with the world. A well-designed tool is the difference between an agent that works and one that hallucinates, fails silently, or costs 10x more tokens than necessary. This skill covers tool design from schema to error handling.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

agenttrail: live map of a multi-agent build in the browser: which plan component is being worked on, by which agent or harness, what is done and what is stuck. Use when a multi-agent pipeline starts (/startcycle, /startcycle-graph, /teamwork-preview) or after a plan-canvas approve, when the user asks to see what the agents are doing ("live map", "build board", "who is running now"), or by yourself whenever a multi-agent run is under way — no user prompt needed.

日本語の概要は準備中です。原文の説明を表示しています。

hybridlabor-api/aos62026年10月12日 更新

hybridlabor-api のスキルをすべて見る

このスキルの問題を報告する