Research Report

Turns markdown research results into a consolidated report with a smart table of contents. You point it at a directory of JSON files (from research you've already done), and it generates a Python script that builds a proper markdown doc with anchor links, summary metrics in the TOC, and categorized detail sections. The interesting bit is how it handles messy real world data: it'll skip uncertain values, deal with both flat and nested JSON structures, and collect orphaned fields into an "Other Info" bucket. Honestly most useful when you've automated research gathering and need a readable deliverable without manually wrangling dozens of JSON files into a coherent narrative.

skills.sh installs: 883
GitHub stars: 2.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add weizhena/deep-research-skills --skill research-report --agent claude-code

Installs into .claude/skills of the current project.

Files

Research Report - Summary Report

Trigger

/research-report

Workflow

Step 1: Locate Results Directory

Find */outline.yaml in current working directory, read topic and output_dir config.

Step 2: Scan Optional Summary Fields

Read all JSON results, extract fields suitable for TOC display (numeric, short metrics), e.g.:

github_stars
google_scholar_cites
swe_bench_score
user_scale
valuation
release_date

Use request_user_input to ask user:

Which fields to display in TOC besides item name?
Provide dynamic options list (based on actual fields in JSON)

Step 3: Generate Python Conversion Script

Generate generate_report.py in {topic}/ directory, script requirements:

Read all JSON from output_dir
Read fields.yaml to get field structure
Cover all field values from each JSON
Skip fields with values containing [uncertain]
Skip fields listed in uncertain array
Generate markdown report format: Table of contents (with anchor links + user-selected summary fields) + Detailed content (by field category)
Save to {topic}/report.md

SKILL.md on GitHub