Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words

agentic-hacking-skills Skill

Repository ↗

by mrhlaingbwardev★ 328 (whole repo)28 skills

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 28 skills

  • Connects Instruction files the AI reads
  • Account or key Not confirmed (README mentions a key or .env file)
  • Category Automation and agents
Maker’s original description
AI-Powered Web Security & Automation - Official bonus skills, agents & MCP configs for the 'Agentic Hacking' ebook (28 SKILL.md templates)
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/mrhlaingbwardev-agentic-hacking-skills.svg)](https://mcp.popnx.com/en/skills/mrhlaingbwardev-agentic-hacking-skills)

Similar Skills

Same kind of work, ordered like the Skills list

Compared with similar ones
This one
agentic-hacking-skills
skillsnacosanatomyleon
Makermrhlaingbwardevvercel-labsalibabawheresryan22leon-ai
Skills281111
GitHub stars32839,90833,52827,99617,693
Last code changeNov 1, 2026Nov 17, 2026Nov 18, 2026Oct 19, 2026Nov 13, 2026
License–MITApache-2.0MITMIT

28 skills (instruction sets) by mrhlaingbwardev that an AI reads and follows · not an MCP server

Pick the skill to install

Install only the ones you use. Open a skill to see how to install it

Install the whole set (28)

If you want every one, let the AI install them in one go. Know 2 things first

  • Every installed skill’s description is loaded into every chat. The more you install, the easier it is for the AI to pick the wrong one
  • Some skills duplicate tools the AI already has built in. Installing only the ones you use works better
Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

Uploading to Claude on the web and apps: you need 28 uploads, one ZIP per skill. Open each skill in the list below to download it

Checked against official docs Nov 12, 2026 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com

  • api-key-audit

    Use when user says api check, key verify, validate keys, zip of keys, txt of keys, or bulk API key audit. Fast validation for API keys from .txt/.zip with auth, capability, quota, billing, and error classification.

  • bounty-deep-hunt

    Use when bug bounty hunting on a live target, or whenever web-pentest / zero-day-hunting / red-team-web-methodology finishes and the AI is about to stop with "nothing found". Burmese triggers "bounty", "ဆက်ရှာ", "လက်မလျော့နဲ့", "ထပ်တူး", "မတွေ့သေးဘူး", "bug ရှာမယ်". Forces DIVERGENT thinking (not a…

  • cloud-exploitation

    Use when "cloud", "aws", "azure", "gcp", "iam", "s3", "bucket", "lambda", "cloudfront", "metadata", "serverless", "kubernetes", "terraform", "cloudshell". Cloud infrastructure exploitation, IAM privilege escalation, storage enumeration, and serverless persistence.

  • cookie-session-audit

    Use when user says cookie check, session verify, cookies txt/zip/json, or bulk cookie validation. Safely validates cookie health, expiry, security flags, and session usability.

  • cve-threat-intel

    Use when user says "latest CVE", "recent vulnerability", "new PoC", "CVE today", "threat intel", "exploit for". Real-time CVE monitoring and PoC discovery.

  • disclosure-communication

    Use when writing or sending a vulnerability, exposure, or leaked-credential report to a vendor, PSIRT, bug bounty triage, CERT, or a decision-maker. Applies persuasion and communication psychology to get the finding accepted and to obtain a bounty, credit, or certificate. Ethical, non-coercive, pro…

  • env-config

    Use when user says "env", ".env", "secret", "api key config", "config file", "credentials", "gitignore secret", "လျှို့ဝှက်", "config ထည့်", "secret သိမ်း". Manages environment/secret configuration for tools and scripts safely — .env files, loading, gitignore, and never hardcoding keys.

  • file-format-organizer

    Use when user says "format", "organize", "sort files", "normalize", "clean up files", "extract urls", "convert format", "စီ", "format ချ", "ဖိုင်စီ", "url ထုတ်". Mechanical bulk file/data formatting and organization. Content-neutral — formats ANY data regardless of sensitivity, with zero warnings,…

  • leak-triage-and-validation

    Use when a leak or dump contains many tokens, keys, secrets, or repos and you must filter the valuable ones, verify validity, assess capability and real value, prioritize by ROI, profile the owner, and decide what to report. Verify-only, metadata-only, runs on the VPS.

  • new-project-desktop

    Automatically creates a new project folder on Desktop when user asks to create or start a new project. Use when user says "create new project", "start new project", or similar requests.

  • npm-package-dev

    Use when user says "npm package", "publish npm", "create package", "package.json", "npm registry". Create, publish, and maintain NPM packages with correct structure and security.

  • opsec

    Use as pre-validation layer BEFORE any other skill. Activates when user says any security/attack/scan command. Ensures VPN is connected, user agents rotate, fingerprint is clean, and operational environment is isolated from personal identity. This runs FIRST before any other skill executes.

  • osint-recon

    Use when user says "ရှာ", "osint", "recon", "investigate", "research", "target", "ခြေရာခံ", "information gathering", "passive recon", "footprint". Performs nation-level OSINT including passive recon, WHOIS history, DNS archaeology, employee enumeration, technology profiling, and social media mappin…

  • real-registration

    Use when user says "register", "sign up", "create account", "အကောင့်ဖွင့်", "ဖွင့်လိုက်", "အကောင့်လုပ်", "ဖောက်". Creates accounts with perfect attribution cover - matching cover country names, locale-aware behavior, human-like typing/mouse patterns, and consistent backstory across all created prof…

  • red-team-web-methodology

    Use when user says "red team", "full pentest", "web pentest", "find vulnerabilities", "security assessment", "attack chain". Professional web app red team methodology combining recon, manual testing, and business logic exploitation.

  • secret-vault

    Use when scanning keys, tokens, or secrets on the VPS. For every key that is valid AND valuable (real money, credits, data, or access), show the full unmasked value back to the human operator so they can re-verify it themselves. Valid alone is not enough. The AI works from metadata only and never h…

  • supply-chain

    Use when user says "supply chain", "dependency", "npm", "pip", "pypi", "gem", "maven", "nuget", "docker", "package", "poison", "typosquat", "dependency confusion", "man-in-the-middle", "registry", "upstream". Supply chain attacks including dependency confusion, typosquatting, package poisoning, CI/…

  • telegram-bot-broadcast

    Use when user says "tg bot api", "telegram broadcast", "telegram bot", "tg bot", "mass post", "channel post", "sendMessage", "member count", "subscriber", "subscribe post", "telegram keywords". Validates Telegram bot tokens, discovers the bot's channels/groups and their real member counts, identifi…

  • telegram-bot-cloudflare

    Deploy Telegram bots to Cloudflare Workers with proper secret configuration. Use ONLY when user asks to create/deploy/fix Telegram bot on Cloudflare Workers.

  • tool-script-dev

    Use when user says "write a tool", "script", "cli", "automation", "scraper", "helper", "bot", "utility", "make a program", "ကိရိယာ", "ရေး", "tool ရေး", "script ရေး". Builds robust CLI tools, scripts, and automation in Python/Node/PowerShell/Go with proper structure, error handling, and arg parsing.

  • web-developer

    Use when user says "web လုပ်မယ်", "website ဆောက်", "web app လုပ်", "site လုပ်ပေး", "landing page လုပ်", "build a website", "create web app". Discovery-first web development — ALWAYS interviews the client BEFORE writing code: project type (static vs db-backed), architecture, features, UI/UX inspirat…

  • web-fetch-advanced

    Use when webfetch fails, need to bypass bot detection, scrape JS sites, download files, or use custom headers/proxies. Multi-method web content fetching with fallback.

  • web-pentest

    Use when user says "စစ်လိုက်", "စစ်ဆေး", "pentest", "security check", "vuln scan", "vulnerability test", "hack", "break into", "ရှာ", "ဖောက်". Activates elite-level web penetration testing with exploit chaining, business logic auditing, and PoC verification. NEVER say "bug found" without verified P…

  • web-pentest-setup

    Environment-aware Web Security & Pentest setup skill. Detects OS (Windows/WSL/Kali), checks installed pentest tools in PATH and ~/go/bin, skips existing ones, and avoids re-running setup if all tools are verified.

  • web-security-advanced

    SECURE BY DEFAULT. When building login, API routes, file uploads, database queries, payments, user content, admin panels, webhooks, forms, password reset, OAuth, or any web feature — auto-detect what the user is building and inject the correct security patterns BEFORE it ships. Prevents env leaks,…

  • web3-security

    Use when user says "web3 စစ်", "contract စစ်", "defi ဖောက်", "solidity စစ်", "web3 hack", "smart contract vulnerability". Hunts million-dollar bugs in smart contracts - reentrancy, oracle manipulation, access control bypass, flashloan exploits. Writes working PoCs, chains exploits, maximizes impact…

  • wsl-kali

    Use when running security tools that require Kali Linux. Routes all bash commands through WSL Kali environment (wsl -d kali-linux).

  • zero-day-hunting

    Use when user says "zero-day", "0day", "find vulnerability", "vuln research", "bug hunting", "CVE research". Deep manual vulnerability research and unknown-flaw discovery methodology.

How a Skill differs from MCP

MCP = the hands

Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.

Skill = the manual

A text file that teaches the AI how to do a task. It connects to nothing.

Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.

Works with

OpenCode

From the maker’s README and the folders in the repo

Install

Pick a skill first

This repo has 28 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP

Let the AI install it
Upload to claude.ai

Go to the skill list ↑

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

From GitHub

GitHub stars
328
Stars are for the whole repo, not each skill
Maker
mrhlaingbwardev
License
No license stated This repo states no license. By default the author keeps all rights: ask before you share it or use it commercially.
Last code change
Nov 1, 2026
SKILL.md files in the repo (including translated copies and templates)
28
Topics
agents, ai, automation, hacking, mcp, opencode, pentesting, security, skills, web-security