メニュー
Conduct deep research with multi-source search, evidence compilation, and structured report generation.
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
Control message formatting and writing style for Lark/Feishu conversations.
Create, query, edit, and manage Feishu Bitable (multidimensional spreadsheets) via lark-cli base — apps, tables, fields, records, views, dashboards, forms, workflows.
Manage Feishu calendar events via lark-cli — create/update/delete events, manage attendees, query free/busy and suggest available time slots, find and book meeting rooms.
List Feishu group chat members and resolve chat metadata via lark-cli.
Create a Feishu cloud document from Lark-flavored Markdown via lark-cli, with optional folder or wiki placement.
Comment management and media (image/file) operations on Feishu cloud documents via lark-cli.
| name | deep-research |
| description | Conduct deep research with multi-source search, evidence compilation, and structured report generation. |
| triggers | {"intent_patterns":["research|调研|调查|分析|analysis|market"],"tool_signals":["web_search","web_fetch"],"context_signals":{"keywords":["调研","研究","analysis","research"]},"confidence_threshold":0.6} |
| priority | 8 |
| exclusive_group | research |
| max_tokens | 200 |
| cooldown | 300 |
| requires_tools | ["bash"] |
| output | {"format":"markdown","artifacts":true,"artifact_type":"document"} |
Multi-source search, evidence compilation, and structured report generation for any research topic.
| Intent | Command | Key Params |
|---|---|---|
| Basic research | $PYTHON $SKILL_DIR/run.py --topic '...' | --topic (required) |
| Custom queries | $PYTHON $SKILL_DIR/run.py --topic '...' --queries '[...]' | --queries |
| Advanced depth | $PYTHON $SKILL_DIR/run.py --topic '...' --depth advanced | --depth |
$PYTHON $SKILL_DIR/run.py --topic 'Research topic' --queries '["keyword1","keyword2"]' --max_results 5 --depth basic
| Param | Type | Required | Description |
|---|---|---|---|
| topic | string | yes | Research topic |
| queries | string[] | no | Search keywords; defaults to 3 auto-generated queries |
| max_results | int | no | Results per query, default 5 |
| depth | string | no | basic or advanced |
| fetch_urls | string[] | no | Additional URLs to fetch full text from |
Returns JSON containing searches (search results), fetched_pages (fetched pages), and summary_prompt (synthesis prompt).
The LLM organizes results into a structured report: Problem, Findings/Evidence, Confidence Level, Impact/Recommendations.