github-research — Claude Code skill: what it does, how to install
Finds open-source repositories matching research topics, inspects their codebases, and produces an integration blueprint. Useful when tracking down implementations of algorithms.
npx skills add lingzhi227/agent-research-skills --skill github-research -a claude-codeWhat github-research does
The skill takes an output directory from deep-research (such as paper_db.jsonl or code_repos.md) and processes it through a six-phase pipeline. It begins by extracting URLs, topics, and keywords. Then it runs multi-source queries through gh api and Papers With Code to gather between 50 and 200 relevant repositories.
All automation relies on Python 3 standard-library scripts located in ~/.claude/skills/github-research/scripts/. These scripts rank the candidates, run shallow clones on the top 8 to 15 repositories, parse dependencies, and search for specific patterns in the code. The run ends with a comparison matrix and a catalog of reusable components inside ./github-research-output/{slug}/.
You need an authenticated GitHub CLI (gh) tool ready in your path. Otherwise, discovery scripts fail immediately when calling the API. Running this without an existing deep-research folder will not work either, because phase 1 requires initial research notes to generate search queries.
What it helps with
- find open-source implementations of a research paper using its title or arXiv identifier
- rank candidate GitHub repositories by stars, code structure, and dependency footprint
- build a cross-repo comparison matrix for algorithms in a specific domain
- assemble an integration blueprint with a catalog of reusable code modules
Example prompts for the agent
- /github-research ./deep-research-output/llm-agents
- Find GitHub implementations for paper 2401.12345 and compare their code structure
- Which open-source repos implement this consensus algorithm?
How to install github-research
1Skills CLI (Vercel)
npx skills add lingzhi227/agent-research-skills --skill github-research -a claude-code2Manually: put the files in place
~/.claude/skills/github-research/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/github-research/
1Skills CLI (Vercel)
npx skills add lingzhi227/agent-research-skills --skill github-research -a codex2Manually: put the files in place
.agents/skills/github-research/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add lingzhi227/agent-research-skills --skill github-research -a cursor2Manually: put the files in place
.cursor/skills/github-research/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install lingzhi227/agent-research-skills github-research2Manually: put the files in place
.github/skills/github-research/SKILL.md1Skills CLI (Vercel)
npx skills add lingzhi227/agent-research-skills --skill github-research -a gemini-cli2Platform CLI
gemini skills install https://github.com/lingzhi227/agent-research-skills --path skills/github-researchManually: put the files in place
.devin/skills/github-research/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add lingzhi227/agent-research-skills --skill github-research -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about github-research
How to install github-research in Claude Code?
Run npx skills add lingzhi227/agent-research-skills --skill github-research -a claude-code.
What does the github-research skill do?
It executes a six-phase workflow that discovers repositories matching research papers, clones the top candidates, analyzes their architecture, and produces an integration plan.
What prerequisites are needed to run this skill?
It requires Python 3, a configured GitHub CLI (gh) for API queries, and an output folder from deep-research containing files like paper_db.jsonl.
