All skills
bytedance avatar

/github-deep-research

@9809af1
by Bytedance Inc.bytedance/deer-flow83k stars
11,552

Conduct multi-round deep research on any GitHub Repo. Use when users request comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of GitHub. Produces structured markdown reports with executive summaries, chronological timelines, metrics analysis, and Mermaid diagrams. Triggers on Github repository URL or open source projects.

Use this Skill: https://skilld.dev/gh/bytedance/deer-flow/github-deep-research

This session only. Nothing lands on disk.

assetsreport_template.md

≈895 tokens on demand. Your agent reads this file only when SKILL.md points to it.

[!NOTE] Generate this report in user's own language.

{TITLE}

  • Research Date: {DATE}
  • Timestamp: {TIMESTAMP}
  • Confidence Level: {CONFIDENCE_LEVEL}
  • Subject: {SUBJECT_DESCRIPTION}

Repository Information

  • Name: {REPOSITORY_NAME}
  • Description: {REPOSITORY_DESCRIPTION}
  • URL: {REPOSITORY_URL}
  • Stars: {REPOSITORY_STARS}
  • Forks: {REPOSITORY_FORKS}
  • Open Issues: {REPOSITORY_OPEN_ISSUES}
  • Language(s): {REPOSITORY_LANGUAGES}
  • License: {REPOSITORY_LICENSE}
  • Created At: {REPOSITORY_CREATED_AT}
  • Updated At: {REPOSITORY_UPDATED_AT}
  • Pushed At: {REPOSITORY_PUSHED_AT}
  • Topics: {REPOSITORY_TOPICS}

Executive Summary

{EXECUTIVE_SUMMARY}

IMPORTANT: Include inline citations using [citation:Title](URL) format after each claim. Example: "The project gained 10k stars in 3 months citation:GitHub Stats."


Complete Chronological Timeline

PHASE 1: {PHASE_1_NAME}

{PHASE_1_PERIOD}

{PHASE_1_CONTENT}

PHASE 2: {PHASE_2_NAME}

{PHASE_2_PERIOD}

{PHASE_2_CONTENT}

PHASE 3: {PHASE_3_NAME}

{PHASE_3_PERIOD}

{PHASE_3_CONTENT}


Key Analysis

IMPORTANT: Support each analysis point with inline citations [citation:Title](URL).

{ANALYSIS_SECTION_1_TITLE}

{ANALYSIS_SECTION_1_CONTENT}

{ANALYSIS_SECTION_2_TITLE}

{ANALYSIS_SECTION_2_CONTENT}


Architecture / System Overview

flowchart TD
    A[Component A] --> B[Component B]
    B --> C[Component C]
    C --> D[Component D]

{ARCHITECTURE_DESCRIPTION}


Metrics & Impact Analysis

Growth Trajectory

{METRICS_TIMELINE}

Key Metrics

Metric Value Assessment
{METRIC_1} {VALUE_1} {ASSESSMENT_1}
{METRIC_2} {VALUE_2} {ASSESSMENT_2}
{METRIC_3} {VALUE_3} {ASSESSMENT_3}

Comparative Analysis

Feature Comparison

Feature {SUBJECT} {COMPETITOR_1} {COMPETITOR_2}
{FEATURE_1} {SUBJ_F1} {COMP1_F1} {COMP2_F1}
{FEATURE_2} {SUBJ_F2} {COMP1_F2} {COMP2_F2}
{FEATURE_3} {SUBJ_F3} {COMP1_F3} {COMP2_F3}

Market Positioning

{MARKET_POSITIONING}


Strengths & Weaknesses

Strengths

{STRENGTHS}

Areas for Improvement

{WEAKNESSES}


Key Success Factors

{SUCCESS_FACTORS}


Sources

Primary Sources

{PRIMARY_SOURCES}

Media Coverage

{MEDIA_SOURCES}

Academic / Technical Sources

{ACADEMIC_SOURCES}

Community Sources

{COMMUNITY_SOURCES}


Confidence Assessment

High Confidence (90%+) Claims: {HIGH_CONFIDENCE_CLAIMS}

Medium Confidence (70-89%) Claims: {MEDIUM_CONFIDENCE_CLAIMS}

Lower Confidence (50-69%) Claims: {LOW_CONFIDENCE_CLAIMS}


Research Methodology

This report was compiled using:

  1. Multi-source web search - Broad discovery and targeted queries
  2. GitHub repository analysis - Commits, issues, PRs, activity metrics
  3. Content extraction - Official docs, technical articles, media coverage
  4. Cross-referencing - Verification across independent sources
  5. Chronological reconstruction - Timeline from timestamped data
  6. Confidence scoring - Claims weighted by source reliability

Research Depth: {RESEARCH_DEPTH} Time Scope: {TIME_SCOPE} Geographic Scope: {GEOGRAPHIC_SCOPE}


Report Prepared By: Github Deep Research by DeerFlow Date: {REPORT_DATE} Report Version: 1.0 Status: Complete

Source: SKILL.md on GitHub

2 warnings16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    The skill is a professional research tool designed to analyze GitHub repositories using official APIs and standard web investigation methods. It contains a self-contained Python script for API interactions and follows security best practices for credential handling.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: MEDIUM · 1 issue

  • Runlayer7mo

    3/3 files flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 9809af1. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 7 months ago
  • API
  • github
  • research
  • web-search
  • analysis
  • markdown
  • reporting
  • competitive-analysis
  • timeline

README badge

README badge for bytedance/deer-flow/github-deep-research

Conducts multi-round research on GitHub repositories using GitHub API, web search, and web fetch to produce structured markdown reports with timelines, metrics, and architecture diagrams. Targets comprehensive analysis workflows such as competitive analysis, project history reconstruction, and open source investigation.

Generated from the current SKILL.md.

What sources does this skill use to conduct research?
The skill combines GitHub API data, web searches, and web fetches, prioritizing official docs and repos over social media. It follows a four-round methodology: GitHub API queries first, then broad discovery, deep investigation, and finally a deep dive into commit history and issues.
Can this skill analyze private repositories?
The SKILL.md does not specify whether private repos are supported. GitHub API access depends on authentication and permissions, which are not detailed in the skill documentation.
What format are the research reports in?
Reports are structured markdown files with an executive summary, chronological timeline, metrics analysis, Mermaid diagrams, and confidence-scored claims. The output file is saved as `research_{topic}_{YYYYMMDD}.md`.
Does this skill verify the accuracy of claims it finds?
Yes. The skill requires triangulating claims across 2+ independent sources, distinguishing fact from opinion, and assigning confidence scores (High 90%+, Medium 70-89%, Low 50-69%) based on source quality and corroboration.

Generated from the current SKILL.md. These answers refresh after source changes.