メニュー
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
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
Convert VTT meeting transcripts from meetings/incoming/ into structured markdown notes in meetings/
Tracks Architecture Decision Records (ADRs) in docs/adrs/. Creates, lists, and updates ADRs following project conventions. TRIGGER when: user wants to record, review, or update an architectural decision.
Check and align a repo's .claude/settings.json and CLAUDE.md with team conventions. Use when the user wants to standardize a repo, align conventions, check settings, or bootstrap Claude Code config in a new project.
Set up and maintain Gmail Multiple Inboxes with auto-discovered sender filters. Scans the user's Gmail to discover senders, suggests inbox categories, generates a Google Apps Script that creates labels and filters. Use this skill for: organizing Gmail, setting up multiple inboxes, managing Gmail labels and filters, categorizing email senders, updating inbox filters with new senders, or unsubscribing from noisy emails. Trigger phrases: "Gmail sections", "inbox categories", "email organization", "sender filters", "multiple inboxes", "clean up my inbox".
Morning review and prioritization of Things todos. Use this skill every morning, or whenever the user asks to review, triage, categorize, or prioritize their Things tasks. Also trigger when the user says things like 'what should I work on today', 'organize my todos', 'morning routine', or 'daily review'.
Generate or update distributed STRUCTURE.md index files across a repo to help LLMs orient quickly in project structure and to make large knowledge repositories easier to navigate and summarize.
| name | review-work |
| description | Use when completing tasks, implementing major features, or before merging to verify work meets requirements |
Dispatch a code-reviewer subagent to catch issues before they cascade. The reviewer gets precisely crafted context for evaluation — never your session's history. This keeps the reviewer focused on the work product, not your thought process, and preserves your own context for continued work.
1. Get git SHAs:
BASE_SHA=$(git merge-base HEAD origin/main)
HEAD_SHA=$(git rev-parse HEAD)
2. Dispatch code-reviewer subagent:
Use the Agent tool to dispatch a code-reviewer subagent, filling the template at references/code-reviewer.md
Placeholders:
{WHAT_WAS_IMPLEMENTED} - What you just built{PLAN_OR_REQUIREMENTS} - What it should do{BASE_SHA} - Starting commit{HEAD_SHA} - Ending commit{DESCRIPTION} - Brief summary