Ctf Writeup

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: MIT5compatibility: Requires filesystem-based agent (Claude Code or similar) with bash and Python 3.6allowed-tools: Bash Read Write Edit Glob Grep Task WebFetch WebSearch7metadata:8  user-invocable: "true"9  argument-hint: "[challenge-name]"10---11 12# CTF Write-up Generator13 14Generate a standardized submission-style CTF writeup for a solved challenge.15 16Default behavior:17 18- During an active competition, optimize for speed, clarity, and reproducibility19- Keep writeups short enough that a teammate or organizer can validate the solve quickly20- Always produce a `submission`-style writeup21- Prefer one complete solve script from challenge data to final flag22 23## Workflow24 25### Step 1: Gather Information26 27Collect the following from the current session, challenge files, and user input:28 291. **Challenge metadata** — name, CTF event, category, difficulty, points, flag format302. **Solution artifacts** — exploit scripts, payloads, screenshots, command output313. **Timeline** — key steps taken, dead ends, pivots32 33```bash34# Scan for exploit scripts and artifacts35find . -name '*.py' -o -name '*.sh' -o -name 'exploit*' -o -name 'solve*' | head -2036# Check for flags in output files37grep -rniE '(flag|ctf|eno|htb|pico)\{' . 2>/dev/null38```39 40### Step 2: Generate Write-up41 42Write the writeup file as `writeup.md` (or `writeup-<challenge-name>.md`) using the submission template below.43 44---45 46## Templates47 48### Submission Format49 50```markdown51---52title: "<Challenge Name>"53ctf: "<CTF Event Name>"54date: YYYY-MM-DD55category: web|pwn|crypto|reverse|forensics|osint|malware|misc56difficulty: easy|medium|hard57points: <number>58flag_format: "flag{...}"59author: "<your name or team>"60---61 62# <Challenge Name>63 64## Summary65 66<1-2 sentences: what the challenge was and the core technique. Keep it direct.>67 68## Solution69 70### Step 1: <Action>71 72<Explain the key observation in 3-8 short lines. Keep it direct.>73 74\`\`\`python75<one complete solving script from provided challenge data to printing the final flag>76\`\`\`77 78### Step 2: <Action> (optional)79 80<Only add this when a second short step genuinely helps readability, such as separating the core observation from final verification.>81 82### Step 3: <Action> (optional)83 84<Use only if the challenge really needs it. Keep the total number of steps small.>85 86## Flag87 88\`\`\`89flag{example_flag_here}90\`\`\`91```92 93Guidance:94 95- Prefer 1-3 short steps total96- Keep code to the smallest complete solving script97- Do not split "recover secret", "derive key", and "decrypt flag" into separate partial snippets98- The script should start from the challenge data and end by printing the flag99- Avoid long background sections100- Avoid dead ends unless they explain a key pivot101- Avoid multiple alternative solves; pick one clean path102- Redact the flag only if the user explicitly asks for redaction103 104---105 106## Best Practices Checklist107 108Before finalizing the writeup, verify:109 110- [ ] **Metadata complete** — title, CTF, date, category, difficulty, points, author all filled111- [ ] **Flag handling matches request** — keep the real flag unless the user asked for redaction112- [ ] **Reproducible steps** — a reader can follow your writeup and reproduce the solution113- [ ] **Code is runnable** — exploit scripts include all imports, correct variable names, and comments114- [ ] **No sensitive data** — no real credentials, API keys, or private infrastructure details115- [ ] **Length stays concise** — the writeup is short enough for fast review116- [ ] **Tools and versions noted** — mention specific tool versions if behavior depends on them117- [ ] **Proper attribution** — credit teammates, referenced writeups, or tools that were essential118- [ ] **Grammar and formatting** — consistent heading levels, code blocks have language tags119 120## Quality Guidelines121 122**DO:**123- Explain just enough for fast verification124- Include one complete solving path, not multiple alternative routes125- Include one complete script that goes all the way to the final flag126- Show actual output (truncated if very long) to prove the approach worked127- Tag code blocks with language (`python`, `bash`, `sql`, etc.)128- Keep the main path front-loaded so a reader can validate it quickly129 130**DON'T:**131- Copy-paste raw terminal dumps without explanation132- Paste several partial snippets that force the reader to reconstruct the final solve133- Leave placeholder text in the final writeup134- Include irrelevant tangents that don't contribute to the solution135- Assume the reader knows the specific challenge setup136 137## Challenge138 139$ARGUMENTS