Give this skill to your agent

Copy the prompt and paste it into Claude Code, Codex or any agent that can read a web page. It installs the skill and tells you what it does.

Install this skill for me.

Read https://cwyz.com/skills/ctf-skills-en
The raw SKILL.md is at https://cwyz.com/api/skills/ctf-skills-en/raw

Save it as ctf-skills/SKILL.md in my skills folder (Claude Code: ~/.claude/skills/ for every project, or .claude/skills/ for this project only).

Then tell me in two sentences what it does and when it applies. Do not run anything it describes until I say so.

Or unzip the download into ~/.claude/skills/ (every project) or .claude/skills/ in your project. A skill tells an agent what to do. Read it before you install it, especially one you did not write.

CTF Skills Has a Playbook Ready for Each Challenge Type

Use when working on CTF competitions or practice challenges (Web, binary exploitation, cryptography, reverse engineering, forensics, OSINT, etc.). Based on the open-source ctf-skills (MIT): a set of Skills split by challenge type, with tool installation scripts. For competitions, practice ranges, and authorized testing only.

Use caseLets the agent pull the matching solving approach and tools for each challenge type, so CTF work goes faster.

Machine translation. Read the original

CTF Skills Has a Playbook Ready for Each Challenge Type

Use this Skill when a user is working on CTF competitions or practice challenges (Web, binary exploitation, cryptography, reverse engineering, forensics, OSINT, etc.). It is built on the open-source ctf-skills (MIT), follows the Agent Skills specification, and is a set of Skills split by challenge type.

Triggers

The user says things like "help me with this CTF challenge", "help me solve this pwn / crypto / reverse / forensics challenge", "this is a Web challenge from the competition", or "how do I get this flag".

Hard Rules

  1. Only analyze your own targets, or targets you have explicit authorization for. If the scope of authorization is unclear, stop and ask the user before doing anything.
  2. Do not scan, attack, bypass payment or access controls, or perform denial of service against live systems. Read-only and local analysis come first.
  3. Tell the user before installing anything or changing configuration. Proceed only after they agree.
  4. Sort conclusions into three categories: what you directly observed (with file and location), what you inferred, and what you did not find (write "unknown", not "does not exist").
  5. Do not output or record the full contents of any keys or tokens you find. Only report where they are.
  6. Use this only for CTF competitions, practice ranges, and authorized testing. Do not apply exploitation techniques from challenges against real systems.
  7. Competitions have rules (for example, whether AI use is allowed or whether teams are permitted). Confirm the user is following them first.

Installation

npx skills add ljagiello/ctf-skills

Two ways to prepare tools:

  • Install everything once before the competition (recommended):
bash scripts/install_ctf_tools.sh --dry-run all    # Preview first; already-installed tools are skipped
bash scripts/install_ctf_tools.sh all              # Install everything; you can also install just one group such as python, apt, brew, gems, or go
bash scripts/install_ctf_tools.sh --verify         # Check which tools are already installed
  • Install on demand while solving: Each Skill's SKILL.md has a "Prerequisites" section that lists only the tools that category needs. Install whatever is missing. Ask the user before installing.

Included Skills

Skill Area
ctf-web SQL injection, XSS, SSTI, SSRF, XXE, file upload, deserialization, JWT, OAuth, prototype pollution, etc.
ctf-pwn Buffer overflows, ROP, heap exploitation, format strings, kernel exploitation, with pwntools template scripts
ctf-crypto RSA attacks and other cryptography challenge types
ctf-ai-ml Adversarial examples, prompt injection, model extraction, membership inference, backdoor detection, etc.
ctf-reverse Reverse engineering challenges
ctf-forensics, ctf-malware, ctf-osint, ctf-misc Forensics, malware sample analysis, open-source intelligence, miscellaneous
ctf-writeup, solve-challenge, ctf-similar-search Writing writeups, the end-to-end solving workflow, finding similar challenges

Output Format

  1. Challenge type identification and the Skills used.
  2. Solving approach: what each step did and why.
  3. The flag and reproduction scripts.
  4. Where you got stuck and suggested next steps.
Done with this one? Mark it to track your path.Sign in
Save it for laterSign in
Questions about this piece?Ask AI about this

Comments (0)

No comments yet. Start the conversation.

Sign in to join the discussion.Sign in