Ctf Writeup

What it does

When your agent uses it

• Tasks that involve Capture the flag

Example prompts

• “Use the ctf-writeup skill to generate a single standardized submission-style CTF writeup for competition handoff and organizer review”
• “/ctf-writeup”

Requirements

• Python 3
• Compatibility (from SKILL.md): Requires filesystem-based agent (Claude Code or similar) with bash and Python 3.
• Pre-approved tools (allowed-tools): Bash, Read, Write, Edit, Glob, Grep, Task, WebFetch, WebSearch

Workflow steps

2 steps, taken from the step headings in SKILL.md.

1. 1Gather Information
2. 2Generate Write-up

What it can do on your machine

Read from SKILL.md and the folder at commit c332c7b. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash
  • Read
  • Write
  • Edit
  • Glob
  • Grep
  • Task
  • WebFetch
  • WebSearch

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires filesystem-based agent (Claude Code or similar) with bash and Python 3.

  From compatibility in the SKILL.md frontmatter.

Context cost

Ctf Writeup loads about 1.2k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 420 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~60

When it runs · the whole SKILL.md, loaded when a task matches

~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Task, WebFetch, WebSearch

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ljagiello/ctf-skills at commit c332c7b, republished under its MIT licence (© ljagiello). 420 words, ~1,194 tokens.

name

ctf-writeup

description

Generates a single standardized submission-style CTF writeup for competition handoff and organizer review. Use after solving a CTF challenge to document the solution steps, tools used, and lessons learned in a structured format.

allowed-tools

Bash, Read, Write, Edit, Glob, Grep, Task, WebFetch, WebSearch

compatibility

Requires filesystem-based agent (Claude Code or similar) with bash and Python 3.

license

MIT

metadata.user-invocable

true

metadata.argument-hint

[challenge-name]

# Scan for exploit scripts and artifacts
find . -name '*.py' -o -name '*.sh' -o -name 'exploit*' -o -name 'solve*' | head -20
# Check for flags in output files
grep -rniE '(flag|ctf|eno|htb|pico)\{' . 2>/dev/null

---
title: "<Challenge Name>"
ctf: "<CTF Event Name>"
date: YYYY-MM-DD
category: web|pwn|crypto|reverse|forensics|osint|malware|misc|ai-ml
difficulty: easy|medium|hard
points: <number>
flag_format: "flag{...}"
author: "<your name or team>"
---

# <Challenge Name>

## Summary

<1-2 sentences: what the challenge was and the core technique. Keep it direct.>

## Solution

### Step 1: <Action>

<Explain the key observation in 3-8 short lines. Keep it direct.>

\`\`\`python
<one complete solving script from provided challenge data to printing the final flag>
\`\`\`

### Step 2: <Action> (optional)

<Only add this when a second short step genuinely helps readability, such as separating the core observation from final verification.>

### Step 3: <Action> (optional)

<Use only if the challenge really needs it. Keep the total number of steps small.>

## Flag

\`\`\`
flag{example_flag_here}
\`\`\`

© ljagiello, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in ctf-writeup of ljagiello/ctf-skills.

Open the folder on GitHubat commit c332c7b