Skip to content
SkillModel-led1,016 tokens in use

ctf-writeup

Generates a short submission-style writeup for a solved CTF challenge, with metadata, a few steps, one complete solving script and the flag.

3,753 stars on the repository MIT Licenseljagiello/ctf-skills · ctf-writeup
npx skills add ljagiello/ctf-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing ctf-writeup costs

48tokens idle
1,016tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldeclared and detectednetworkdeclaredwrites filesdeclared

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter11/15
  • Structure22/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−2

    does this on the machine, as the frontmatter declares

    SKILL.md, line 36

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity88
  • Maintenance48
  • Community56
  • Maturity32
  • Momentum40

ctf-writeup produces one standardized writeup after a CTF challenge is solved. It gathers challenge metadata, exploit scripts and output from the session, then writes a writeup file from a fixed template.

The template keeps the text brief and reproducible: a summary, one to three short steps, a single script that runs from the challenge data to the flag, and the flag itself. A checklist and do and don’t lists help a teammate or organizer validate the solve quickly.

What You Get

  • A writeup.md file in a fixed submission format with frontmatter metadata
  • A summary, one to three solution steps and the flag
  • One complete solve script from the challenge data to the printed flag
  • A pre-submission checklist for metadata, reproducibility, runnable code and attribution

Common Use Cases

  • Handing a solve to a teammate or organizer for fast validation during a competition
  • Recording a finished challenge for a personal archive of solves
  • Standardizing the format of writeups across a team

What Makes It Unique

Many writeup templates invite long narrative. This one is built for speed in a live event: a short summary, at most a few steps, and a single script that reproduces the flag. It also tells the agent to keep the real flag unless the user asks for redaction and to leave out credentials and private infrastructure details.

Under The Hood

The skill is instructions only, with no scripts. The agent runs find and grep over the working directory to locate exploit scripts and flag-like strings, then writes a markdown file in the current directory. Its frontmatter allows shell, file edits, web fetch and web search, though the instructions themselves describe local file search and writing.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers