メニュー
Manage your project's brain — export/import decisions, architecture notes, and project context.
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
Auto-generate concise, visually stunning README.md with project auto-scanning, badges, and 3 style modes.
Generate unit/integration tests with smart edge case analysis (Zero Token Skeleton + Smart Mode).
Persistent team profiles — carry your coding style, rules, and bug-fix knowledge across projects. 3-tier memory (Hot/Warm/Cold) with TF-IDF search.
Deploy local websites to the internet instantly via Cloudflare Tunnel. Zero hosting, zero domain needed.
Suggests suitable tech stack based on project requirements using local database.
Analyzes market trends, hot features, and user expectations.
| name | brain-manager |
| description | Manage your project's brain — export/import decisions, architecture notes, and project context. |
Manages the .agent/brain/ directory — your project's persistent memory. It stores architecture decisions, tech stack choices, conventions, and lessons learned so AI agents always have context.
python .agent/skills/brain-manager/scripts/brain.py add-decision "Use PostgreSQL over MongoDB for relational data needs"
python .agent/skills/brain-manager/scripts/brain.py show
python .agent/skills/brain-manager/scripts/brain.py export --output brain_backup.json
python .agent/skills/brain-manager/scripts/brain.py import --input brain_backup.json
| File | Purpose |
|---|---|
brain/project_context.json | Core project metadata and settings |
brain/decisions.jsonl | Architecture Decision Records (ADR) |
brain/conventions.md | Coding conventions and style guide |
When an agent starts working, it reads project_context.json to understand: