research-report

1# Research Report - Summary Report
2 
3## Trigger
4`/research-report`
5 
6## Workflow
7 
8### Step 1: Locate Results Directory
9Find `*/outline.yaml` in current working directory, read topic and output_dir config.
10 
11### Step 2: Scan Optional Summary Fields
12Read all JSON results, extract fields suitable for TOC display (numeric, short metrics), e.g.:
13- github_stars
14- google_scholar_cites
15- swe_bench_score
16- user_scale
17- valuation
18- release_date
19 
20Use request_user_input to ask user:
21- Which fields to display in TOC besides item name?
22- Provide dynamic options list (based on actual fields in JSON)
23 
24### Step 3: Generate Python Conversion Script
25Generate `generate_report.py` in `{topic}/` directory, script requirements:
26- Read all JSON from output_dir
27- Read fields.yaml to get field structure
28- Cover all field values from each JSON
29- Skip fields with values containing [uncertain]
30- Skip fields listed in uncertain array
31- Generate markdown report format: Table of contents (with anchor links + user-selected summary fields) + Detailed content (by field category)
32- Save to `{topic}/report.md`
33 
34**TOC Format Requirements**:
35- Must include every item
36- Each item displays: number, name (anchor link), user-selected summary fields
37- Example: `1. [GitHub Copilot](#github-copilot) - Stars: 10k | Score: 85%`
38 
39#### Script Technical Requirements (Must Follow)
40 
41**1. JSON Structure Compatibility**
42Support two JSON structures:
43…