by shuvonsec
Generate Claude Code bug bounty skills from public HackerOne reports and GitHub writeups — 18 vuln classes, no private reports needed
# Add to your Claude Code skills
git clone https://github.com/shuvonsec/public-skills-builderGuides for using testing skills like public-skills-builder.
Last scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:45:34.607Z",
"npmAuditRan": true,
"pipAuditRan": true
}public-skills-builder is an open-source testing skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by shuvonsec. Generate Claude Code bug bounty skills from public HackerOne reports and GitHub writeups — 18 vuln classes, no private reports needed. It has 191 GitHub stars.
Yes. public-skills-builder passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/shuvonsec/public-skills-builder" and add it to your Claude Code skills directory (see the Installation section above).
public-skills-builder is primarily written in Python. It is open-source under shuvonsec on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other Testing skills you can browse and compare side by side. Open the Testing category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh public-skills-builder against similar tools.
No comments yet. Be the first to share your thoughts!
Top skills in this category by stars
Generate Claude Code bug bounty skills from public HackerOne reports and GitHub writeups — no private reports needed.
Feed it 500+ public bug bounty reports. Get back 18 ready-to-use Claude Code skill files — one per vulnerability class — packed with real-world techniques, payloads, and bypass patterns.
Quick Start · Output · Sources · Usage
Bug bounty reports are the best training data for hunting. This tool reads hundreds of disclosed HackerOne reports and community writeups, then uses Claude to distill them into structured skill files you can load directly into Claude Code.
No private reports required. Everything comes from public data.
git clone https://github.com/shuvonsec/public-skills-builder
cd public-skills-builder
python3 -m venv .venv
source .venv/bin/activate
pip install anthropic requests
cp .env.example .env
# Edit .env — add your ANTHROPIC_API_KEY
| Source | Auth needed | What it fetches |
|---|---|---|
| HackerOne public feed | None | Publicly disclosed reports |
| HackerOne REST API | H1 API key | Your own resolved reports |
| GitHub writeup repos | None (optional token) | 1,200+ community writeups |
One markdown skill file per vulnerability class, ready to load into Claude Code:
skills/
hunt-idor.md
hunt-ssrf.md
hunt-xss.md
hunt-rce.md
hunt-oauth.md
hunt-sqli.md
hunt-business-logic.md
... (18 vuln classes total)
README.md ← index of all skills
Each skill file contains:
# Public GitHub writeups only (just needs Claude API key)
python3 public_skills_builder.py --source github
# HackerOne public disclosed reports (no H1 key needed)
python3 public_skills_builder.py --source h1-public
# Everything — all sources, all vuln classes
python3 public_skills_builder.py --source all --limit 500
# Specific vuln classes only
python3 public_skills_builder.py --vuln-type idor ssrf xss oauth
# Specific H1 program
python3 public_skills_builder.py --source h1 --program shopify --limit 200
idor ssrf xss sqli rce auth-bypass oauth race-condition
business-logic graphql cache-poison xxe upload ssti csrf
subdomain llm-ai crypto
Once generated, load a skill into Claude Code by pointing it at the file:
claude
# Then: "Load skills/hunt-idor.md and help me hunt IDOR on target.com"
Or copy skill files into your Claude Code project's .claude/ directory so they load automatically.
ANTHROPIC_API_KEY — from console.anthropic.comH1_API_KEY — optional, from hackerone.com/settings/api_tokenGITHUB_TOKEN — optional, increases GitHub API rate limitsFor authorized security testing only. Only test targets within an approved bug bounty program scope.
MIT License · Built for bug hunters who learn from the community
Star if this saved you research time