ワンクリックで
review-insights
Scan all CLAUDE.md files and agent_dev/README.md for `# Insights` sections. Present consolidated insights for human review.
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。
メニュー
Scan all CLAUDE.md files and agent_dev/README.md for `# Insights` sections. Present consolidated insights for human review.
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
Use when working with datasets, creating data directories, or building descriptive statistics notebooks. Triggers on data loading, dataset setup, or exploratory data analysis tasks.
Use when creating, editing, or executing Jupyter notebooks (.ipynb files). Covers jupytext pairing, notebook execution, and output verification.
Use when creating plots, charts, or visualizations with matplotlib or seaborn. Defines plotting style standards.
Review a session plan for scope creep and unnecessary complexity before execution begins. Combines scope-check and simplicity-audit. Run after Plan Mode, before any code is written.
Use before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores intent, requirements, and design before implementation.
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
| name | review-insights |
| description | Scan all CLAUDE.md files and agent_dev/README.md for `# Insights` sections. Present consolidated insights for human review. |
| disable-model-invocation | true |
| allowed-tools | Read, Glob, Grep, Bash(find *) |
Scan the project for all accumulated insights and present them for review.
Find all files with Insights sections
CLAUDE.md files in the project (excluding node_modules, .venv)agent_dev/README.mdExtract # Insights sections
# Insights or ## Insights headingPresent consolidated output
Ask the user