# ljagiello/ctf-skills

Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more

Repository: https://github.com/ljagiello/ctf-skills
Canonical: https://ross.abutalabs.com/products/ctf-skills
Homepage: https://ljagiello.github.io/ctf-skills
Language: Python
License: MIT
License Family: permissive
Topics: agent-skills, claude-code-skills, ctf, security, claude-code, codex, codex-cli, gemini, gemini-cli, opencode, ctf-challenges, ctf-tools
Last push: 2026-08-25T03:49:07+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 15
- inputs: {"age_days": 213, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3104, forks 362 (observed 2026-08-28T04:07:43.693647+00:00)

## What it is
A collection of Agent Skills (SKILL.md files) that teach AI coding agents like Claude Code, Codex, and Gemini CLI how to solve Capture The Flag security challenges. It covers 9 categories including web exploitation, binary pwn, cryptography, reverse engineering, forensics, OSINT, malware analysis, and AI/ML attacks, with installer scripts for the required tooling.

## Use cases
- solve CTF challenges with an AI agent
- set up a CTF tooling environment before a competition
- learn cryptography attack techniques like RSA and lattice attacks
- do steganography and forensics on disk images and PCAPs
- practice binary exploitation and pwn with an LLM assistant
- run OSINT and web exploitation tasks via Claude Code

## When to choose
- you use an agent that supports the Agent Skills spec (Claude Code, Codex, Gemini CLI, opencode) and want CTF-solving capability
- you want a curated, categorized catalog of CTF techniques with prerequisite tooling scripts
- you're preparing for a CTF competition and want tools pre-installed

## When to avoid
- you need a standalone CTF tool rather than skills loaded into an AI agent
- you're looking for production security tooling rather than competition/educational material
- your agent runtime doesn't support the Agent Skills spec

## Facets
- artifact type: learning-resource
- maturity: active
- function: security, penetration-testing, reverse-engineering, osint, agent-framework, prompt-engineering
- domain: security, penetration-testing, artificial-intelligence, developer-tools, tutorials
- platform: cli, cross-platform, python
- tags: ctf, agent-skills, claude-code, capture-the-flag, pwn, cryptography, forensics, steganography, llm-agents

## Member repositories
- ljagiello/ctf-skills (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:43.693647+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:46:11.393363+00:00, confidence not recorded.
  - readme: https://github.com/ljagiello/ctf-skills (fetched 2026-08-28T04:07:43.693647+00:00, sha 02c32ccaeac0)
  - homepage: https://ljagiello.github.io/ctf-skills (fetched 2026-08-29T09:42:05.654135+00:00, sha 37d25b949416)
- Data as of 2026-08-30T08:39:29.467469+00:00.