菜单
Source collection and ideation for lecture materials. After confirming topic/audience/purpose, performs web research (Korean and English) and writes research_notes.md. Responds to "research topic", "collect sources" . Stage 1 of the lecture workflow.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Runs the full project sync pipeline — lifecycle update, audit, L0→L1 publish, commit, push, and PR creation.
Runs the full project sync pipeline — lifecycle update, audit, L0→L1 publish, commit, push, and PR creation.
Turn a topic or your own materials into a single self-contained, interactive HTML report — top tabs, clickable reference drawers, dense tables, comparison heatmaps, inline SVG, in-page search, a light/dark theme toggle, and multilingual support. Use when: user says "/explain-me", "/reportme", "make a report", "create report", "explain this topic". Inspired by beret21/reportme.
Document Production Workflow for co-deck — generates searchable, themed handbooks as static sites (GitHub Pages). Three modes: standalone handbook, lecture companion (reads co-deck slide_deck.md), full course site. Responds to "make handbook", "create handbook", "build course site", "companion handbook" (triggered by Korean phrases too). H-Stage pipeline (H-0 through H-7). Independent from the 11-Stage slide pipeline.
Turn a topic or your own materials into a single self-contained, interactive HTML report — top tabs, clickable reference drawers, dense tables, comparison heatmaps, inline SVG, in-page search, a light/dark theme toggle, and multilingual support. Use when: user says "/explain-me", "/reportme", "make a report", "create report", "explain this topic". Inspired by beret21/reportme.
Pre-edit fact-forcing quality gate. Ensures agents investigate a file's importers, schemas, and scope constraints before making changes. Part of the 3-layer enforcement model (Hook → Prompt → Skill).
| name | research |
| scope | co-deck |
| version | 1.2.0 |
| description | Source collection and ideation for lecture materials. After confirming topic/audience/purpose, performs web research (Korean and English) and writes research_notes.md. Responds to "research topic", "collect sources" . Stage 1 of the lecture workflow. |
| status | active |
| owner | research |
| last_reviewed | "2026-06-19T00:00:00.000Z" |
| prerequisites | none |
Researches the lecture topic via web search (Korean + English) and organizes findings into research_notes.md — the primary input for the Storyline Agent. Invoked at Stage 1, after the lecture topic and audience are confirmed.
research_notes.md does not yet existConfirm the following with the user before starting (skip anything already mentioned):
Use WebSearch and web_fetch to collect:
Search in both Korean and English. Always record source URLs.
Organize collected content into the structure below and save to the workspace.
# Research Notes: [Topic]
## Lecture Overview
- Topic:
- Audience:
- Purpose:
- Length (slide count):
## Core Messages (3-5)
Key points the audience must take away.
1.
2.
3.
## Key Concepts & Content
### [Concept/Section 1]
[Summary]
### [Concept/Section 2]
[Summary]
## Data / Statistics
- [Figure] — Source: [URL]
- [Figure] — Source: [URL]
## Case Studies
### [Case 1]
[Description]
## References
- [Title](URL)
- [Title](URL)
Korean example (when the lecture targets a Korean audience, write actual content in Korean):
# Research Notes: Securities Industry in the AX Era ## Lecture Overview - Topic: Securities Industry Changes in the AX (AI Transformation) Era - Audience: Securities company executives and practitioners - Purpose: Providing insights and strategic directions - Length (Slide count): 60
presentations/<project>/research_notes.md with sections: Lecture Overview, Core Messages, Key Concepts & Content, Data / Statistics, Case Studies, References. See Step 3 template above for full structure.
storyline — consumes research_notes.md output from this skill