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.
# 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
Step 2: Generate Write-up
Write the writeup file as writeup.md (or writeup-<challenge-name>.md) using the submission template below.
Templates
Submission Format
---
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}
\`\`\`
Guidance:
Prefer 1-3 short steps total
Keep code to the smallest complete solving script
Do not split "recover secret", "derive key", and "decrypt flag" into separate partial snippets
The script should start from the challenge data and end by printing the flag
Avoid long background sections
Avoid dead ends unless they explain a key pivot
Avoid multiple alternative solves; pick one clean path
Redact the flag only if the user explicitly asks for redaction
Flag handling matches request — keep the real flag unless the user asked for redaction
Reproducible steps — a reader can follow your writeup and reproduce the solution
Code is runnable — exploit scripts include all imports, correct variable names, and comments
No sensitive data — no real credentials, API keys, or private infrastructure details
Length stays concise — the writeup is short enough for fast review
Tools and versions noted — mention specific tool versions if behavior depends on them
Proper attribution — credit teammates, referenced writeups, or tools that were essential
Grammar and formatting — consistent heading levels, code blocks have language tags
Quality Guidelines
DO:
Explain just enough for fast verification
Include one complete solving path, not multiple alternative routes
Include one complete script that goes all the way to the final flag
Show actual output (truncated if very long) to prove the approach worked
Tag code blocks with language (python, bash, sql, etc.)
Keep the main path front-loaded so a reader can validate it quickly
DON'T:
Copy-paste raw terminal dumps without explanation
Paste several partial snippets that force the reader to reconstruct the final solve
Leave placeholder text in the final writeup
Include irrelevant tangents that don't contribute to the solution
Assume the reader knows the specific challenge setup
Challenge
$ARGUMENTS
1---2name: ctf-writeup3description: 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.4license: MIT5---67# CTF Write-up Generator89Generate a standardized submission-style CTF writeup for a solved challenge.1011Default behavior:1213- During an active competition, optimize for speed, clarity, and reproducibility14- Keep writeups short enough that a teammate or organizer can validate the solve quickly15- Always produce a `submission`-style writeup16- Prefer one complete solve script from challenge data to final flag1718## Workflow1920### Step 1: Gather Information2122Collect the following from the current session, challenge files, and user input:23241. **Challenge metadata** — name, CTF event, category, difficulty, points, flag format252. **Solution artifacts** — exploit scripts, payloads, screenshots, command output263. **Timeline** — key steps taken, dead ends, pivots2728```bash29# Scan for exploit scripts and artifacts30find . -name '*.py' -o -name '*.sh' -o -name 'exploit*' -o -name 'solve*' | head -2031# Check for flags in output files32grep -rniE '(flag|ctf|eno|htb|pico)\{' . 2>/dev/null33```3435### Step 2: Generate Write-up3637Write the writeup file as `writeup.md` (or `writeup-<challenge-name>.md`) using the submission template below.3839---4041## Templates4243### Submission Format4445```markdown46---47title: "<Challenge Name>"48ctf: "<CTF Event Name>"49date: YYYY-MM-DD50category: web|pwn|crypto|reverse|forensics|osint|malware|misc|ai-ml51difficulty: easy|medium|hard52points: <number>53flag_format: "flag{...}"54author: "<your name or team>"55---5657# <Challenge Name>5859## Summary6061<1-2 sentences: what the challenge was and the core technique. Keep it direct.>6263## Solution6465### Step 1: <Action>6667<Explain the key observation in 3-8 short lines. Keep it direct.>6869\`\`\`python70<one complete solving script from provided challenge data to printing the final flag>71\`\`\`7273### Step 2: <Action> (optional)7475<Only add this when a second short step genuinely helps readability, such as separating the core observation from final verification.>7677### Step 3: <Action> (optional)7879<Use only if the challenge really needs it. Keep the total number of steps small.>8081## Flag8283\`\`\`84flag{example_flag_here}85\`\`\`86```8788Guidance:8990- Prefer 1-3 short steps total91- Keep code to the smallest complete solving script92- Do not split "recover secret", "derive key", and "decrypt flag" into separate partial snippets93- The script should start from the challenge data and end by printing the flag94- Avoid long background sections95- Avoid dead ends unless they explain a key pivot96- Avoid multiple alternative solves; pick one clean path97- Redact the flag only if the user explicitly asks for redaction9899---100101## Best Practices Checklist102103Before finalizing the writeup, verify:104105- [ ] **Metadata complete** — title, CTF, date, category, difficulty, points, author all filled106- [ ] **Flag handling matches request** — keep the real flag unless the user asked for redaction107- [ ] **Reproducible steps** — a reader can follow your writeup and reproduce the solution108- [ ] **Code is runnable** — exploit scripts include all imports, correct variable names, and comments109- [ ] **No sensitive data** — no real credentials, API keys, or private infrastructure details110- [ ] **Length stays concise** — the writeup is short enough for fast review111- [ ] **Tools and versions noted** — mention specific tool versions if behavior depends on them112- [ ] **Proper attribution** — credit teammates, referenced writeups, or tools that were essential113- [ ] **Grammar and formatting** — consistent heading levels, code blocks have language tags114115## Quality Guidelines116117**DO:**118- Explain just enough for fast verification119- Include one complete solving path, not multiple alternative routes120- Include one complete script that goes all the way to the final flag121- Show actual output (truncated if very long) to prove the approach worked122- Tag code blocks with language (`python`, `bash`, `sql`, etc.)123- Keep the main path front-loaded so a reader can validate it quickly124125**DON'T:**126- Copy-paste raw terminal dumps without explanation127- Paste several partial snippets that force the reader to reconstruct the final solve128- Leave placeholder text in the final writeup129- Include irrelevant tangents that don't contribute to the solution130- Assume the reader knows the specific challenge setup131132## Challenge133134$ARGUMENTS
Run npx skillmds@latest add jiayaoqijia/ctf-writeup in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
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. It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free. This skill is licensed under MIT.
jiayaoqijia (@jiayaoqijia) published this skill. Their other Agent Skills are listed on their SkillMD profile.