Agent skill · Backend & API

github-deep-research

Multi-round deep research on any GitHub repo via API.

HezaoHezaogithub.com/HezaoHezaoGitHub ↗
claude-codecan modify filesMIT
Install
npx skills add HezaoHezao/poirot --skill github-deep-research --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 1
SKILL.md size: 5 KB
Bundled scripts: none
Declared author: Adapted from deer-flow (Bytedance, MIT)
Allowed tools: -bash-web_search-browse_page-write_file
Path: poirot/backend/agents/skill/builtin_skills/research/github-deep-research/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 139
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# GitHub Deep Research Multi-round research combining GitHub API, `web_search`, and `browse_page` to produce comprehensive markdown reports on any GitHub repository. > **Poirot note:** The original deer-flow skill uses a bundled > `scripts/github_api.py` helper. Poirot doesn't bundle that script, so this > version uses `bash` with `curl` to the GitHub API directly + `gh` CLI when > available. ## When to Use - User provides a GitHub repository URL - User asks for comprehensive analysis, timeline reconstruction, competitive analysis, or in-depth investigation of an open source project - User wants to understand a project's architecture, history, or community ## Research Workflow - Round 1: GitHub API (repo metadata, README, file tree, contributors, commits) - Round 2: Discovery (web search for overview, competitors) - Round 3: Deep Investigation (architecture, timeline, community sentiment) - Round 4: Deep Dive (commit history, issues/PRs for feature evolution) ## Round 1 — GitHub API ### Setup ```bash # Resolve owner/repo from remote URL REMOTE_URL=$(git remote get-url origin 2>/dev/null || echo "") # Or user provides owner/repo directly OWNER="owner" REPO="repo" ``` ### Repo metada

What's inside
Steps it walks through
  1. When to Use
  2. Research Workflow
  3. Round 1 — GitHub API
  4. Setup
  5. Repo metadata via curl
  6. Via gh CLI (if available)
  7. Round 2 — Discovery (3-5 websearch)
  8. Round 3 — Deep Investigation (5-10 websearch + browsepage)
  9. Round 4 — Deep Dive
  10. Report Structure
  11. Confidence Scoring
  12. Citation Format
  13. Output
  14. Best Practices
Commands it runs
Resolve owner/repo from remote URL
Or user provides owner/repo directly
Repo summary
curl -s "https://api.github.com/repos/$OWNER/$REPO" | python3 -c "
import sys, json
r = json.load(sys.stdin)
README
curl -s "https://api.github.com/repos/$OWNER/$REPO/readme" | python3 -c "
import sys, json, base64
Recent commits
More from poirot
All skills →
About this skill
What does the github-deep-research skill do?

Multi-round deep research on any GitHub repo via API.

How do I install it?

Run `npx skills add HezaoHezao/poirot --skill github-deep-research --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From HezaoHezao/poirot, a repository with 139 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going