Skip to content
store
github-deep-research

Open source alternatives to github-deep-research

23 open source AI Skills apps to use instead, best rated first.

Top picks

  1. G

    github-ops

    Launch

    github-ops is an agent skill from the ECC collection by affaan-m, listed on skills.sh. It manages a GitHub repository with a focus on community health, CI reliability and the experience of contributors. It covers triaging issues by classify

  2. O

    opensource-pipeline

    Launch

    opensource-pipeline is an agent skill from the ECC collection by affaan-m, listed on skills.sh. It prepares a private project for safe public release through a three-stage pipeline. The fork stage strips secrets from a copy. The sanitise st

  3. A

    andrej-karpathy-skills

    Launch

    andrej-karpathy-skills is a single CLAUDE.md file from the multica-ai project that is meant to improve how Claude Code behaves on coding tasks. It is derived from Andrej Karpathy's public observations about LLM coding pitfalls. The file dis

  4. M

    microsoft/markitdown

    Launch

    markitdown-mcp is the MCP server package for MarkItDown, Microsoft's tool for converting many file formats to Markdown for language models. It is a lightweight server that runs over stdio, Streamable HTTP or SSE, and exposes one tool, conve

  5. O

    od-contribute

    Launch

    od-contribute is an agent skill in the OpenDesign project that provides a guided, one-click contribution flow to the OpenDesign repository, written so that people without a coding background can send a real pull request. It is locked to the

  6. M

    modelcontextprotocol/server-everything

    Launch

    Everything is a Model Context Protocol server that exercises the features of the MCP protocol. It is not meant to be a useful server for everyday work. Its purpose is to be a test server for people who build MCP clients, so that they can ch

More AI Skills apps

See all
7
M

modelcontextprotocol/server-filesystem

Direct local file system access

Launch
8
M

modelcontextprotocol/server-memory

Knowledge graph-based persistent memory for maintaining context

Launch
9
N

netdata/netdata#Netdata

Discovery, exploration, reporting and root cause analysis over Netdata metrics

Launch
10
L

Learn Claude Code

by shareAI-lab - A really interesting analysis of how coding agents like Claude

Launch
11
C

career-ops

Job-search skill collection for JD evaluation, ATS resumes, portal scans

Launch
12
S

Sequential Thinking

Dynamic and reflective problem-solving through thought sequences

Launch
13
R

Reactive Resume

A one-of-a-kind resume builder that keeps your privacy in mind

Launch
14
E

elie222/inbox-zero

Inbox Zero features on top of Gmail, such as finding emails

Launch
15
S

simple-issue-description

Turn a rough bug report, feature request, support note

Launch
16
C

Compound Engineering Plugin

by EveryInc - A very pragmatic set of well-designed agents, skills

Launch
17
S

SuperClaude

by SuperClaude-Org

Launch
18
M

MCP Toolbox for Databases

MCP Toolbox for Databases enables your agent to connect to your database

Launch
19
A

awslabs/mcp

Suite of servers for integrating with AWS services and resources

Launch
20
R

Ralph for Claude Code

by Frank Bria - An autonomous AI development framework

Launch
21
M

mobilerun

Automate your mobile devices with natural language commands

Launch
22
O

openstatus

Manage monitors, status pages

Launch
23
C

Claude Squad

by smtg-ai - A terminal app

Launch

About github-deep-research

G

github-deep-research

Conduct multi-round deep research on any GitHub Repo

github-deep-research is an agent skill from the DeerFlow project that researches a single GitHub repository in several rounds and writes a report in Markdown. It is for requests that need more than a README summary, such as a comprehensive analysis of a project, a timeline of how it developed, a competitive comparison with other tools, or an in-depth review. The research runs in stages: first the GitHub API for the repository's basic facts, then broader discovery through web search, then a deeper investigation, and finally a dive into the points that need explaining. Each round is guided by a query strategy that moves from broad to narrow, so later searches follow what the earlier ones found. Web search and page fetching are used alongside the API to cross-check claims. The skill is useful for engineers evaluating a dependency, researchers following a project, and product teams comparing tools. It passes Gen Agent Trust Hub and Socket on skills.sh, and Snyk shows a warning. Install it with npx skills add https://github.com/bytedance/deer-flow --skill github-deep-research.

View github-deep-researchAll AI Skills apps
Price
Free
Made by
bytedance
Category
AI Skills
Website
github.com/bytedance/deer-flow/github-deep-research