541 tagged ctf, measured the same way as everything else here.
Browse within: cybersecurity 195claude-code-skill 142antigravity-skills 138caveman 138malware-analysis 131disassembly 123firmware-analysis 122cursor-skills 92codex-cli 89deepseek-harness 87ai-tools 53openclaw 53ctf-tools 46mitre-attack 41
Skill Claude CodeCodex
HackerOne bounty program scope-guard workflow — reads program scope, enforces scope and program rules, then hands each in-scope asset to pentest-flow.
Skill Claude Code
Provides cryptography attack techniques for CTF challenges. Use when attacking encryption, hashing, signatures, ZKP, PRNG, or mathematical crypto problems involving RSA, AES, ECC, lattices, LWE, CVP, number theory, Coppersmith, Pollard, Wiener, padding oracle, GCM, key derivation, or stream/block cipher weaknesses.
Skill Claude Code
A cryptography skill for solving capture-the-flag challenges, which are security puzzles that require finding and exploiting weaknesses. It covers algorithms, attacks, mathematical techniques, and zero-knowledge proofs.
Skill Claude Code
A guide to analysing game software made with Unity or Unreal, changing values in memory, examining Lua scripts, and inspecting graphics shaders. Cheat Engine is a Windows tool for scanning and modifying a running program's memory.
Skill Claude CodeCodex
Use this skill when Claude Code needs to drive local IDA Pro or Hex-Rays through the IDA-CLI AI-only JSONL kernel, run IDAPython/idalib analysis from a CLI subprocess, collect artifacts, use AI helper APIs, persist caches, merge mutation records, or inspect binaries without opening IDA GUI panels.
NUSGreyhats/ctf-agent-workstation
Skill Claude CodeCodex
Use when a single file falls into one of three trip-up cases the model reliably gets wrong without a recipe: (1) Corrupted-header repair where magic bytes / IHDR / SOI / EOI / CRC / central-directory fields have been clobbered and need precise byte-level reconstruction (PNG height-restore, JPEG marker repair, ZIP EOCD…
Skill Claude CodeCodex
Manage a preinstalled local Minecraft Java client asynchronously for CTF and automation workflows. Use when an agent needs to launch Minecraft in offline mode with alternate usernames, inspect Minecraft logs, focus or type into the X11 game window, send chat or slash commands quickly, or join a multiplayer server by…
Skill Claude Code
Web exploitation: SQLi, XSS, SSTI, SSRF, CSRF, XXE, JWT, OAuth/OIDC, SAML, prototype pollution, file-upload/path-traversal, HTTP smuggling, cache poisoning, Web3/Solidity, auth/parser differentials. Dispatch on manifest + framework signals.
Skill Claude CodeCodex
Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens"…
Asaiuta/reverse-workbench-skill
Skill Claude CodeCodex
Use when analyzing suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules, sandboxing, and anti-analysis behavior.
Skill Codex
Reverse engineering of compiled, packed, virtualized, or obfuscated targets for authorized CTF challenges. Use when the task is to understand, decompile, disassemble, or unpack an unknown executable across ELF, PE, Mach-O, APK, WASM, firmware, bytecode, or custom-VM targets.
Skill Claude CodeCodex
Execute web-application assessment from setup and recon through injection, access control, auth/session issues, API, and SSRF chains.
JesusConwellpy/secagent-skills
Skill Claude CodeCodex needs its repo
Local LLM-Wiki knowledge system. Bootstrap a structured wiki, write entries using precise templates, full-text search, cross-agent knowledge sharing, cross-session inheritance.
Skill Claude Code
The core decision loop for driving any TryHackMe room. Use at the START of every room, whenever the user asks "what next", and whenever progress stalls. Teaches classify -> observe -> hypothesize -> test -> decide, so the approach is chosen from what the room is actually teaching rather than defaulting to…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: