Skip to content
SkillModel-led2,532 tokens in use

solve-challenge

The entry point of the ctf-skills collection: triages a CTF challenge, picks its category and routes it to the matching specialist skill.

3,753 stars on the repository MIT Licenseljagiello/ctf-skills · solve-challenge
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 solve-challenge costs

102tokens idle
2,532tokens in use
4,333tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. 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 detectednetworkdeclared and detectedwrites 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
  • Frontmatter15/15
  • Structure25/25
  • Examples15/15
  • Output15/15
  • Size13/15
  • Resources15/15

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 26
  • Reaches the network−5

    does this on the machine, as the frontmatter declares

    SKILL.md, line 58

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

solve-challenge is the dispatcher of the ctf-skills collection. Given a challenge bundle, a remote service, a suspicious file or only a vague description, it runs a first pass of recon, decides which category the challenge belongs to and invokes the matching ctf skill.

It also covers CTF platform handling (CTFd API or a browser driven through Playwright MCP), rules for pivoting when stuck, flag format validation, an evidence-based difficulty and model routing guide, and a final step that calls the writeup skill.

What You Get

  • A five-step workflow: platform detection, recon, categorization, category skill invocation and pivoting
  • Tables that map file extensions, description keywords and service behavior to a challenge category
  • A list of common multi-category challenge patterns, such as forensics plus crypto
  • A reference file with evidence-based difficulty scoring, stop-loss rules and escalation rules
  • Guidance on flag formats and on validating flag candidates before submitting

Common Use Cases

  • Starting a challenge when you only have a zip file and a short description
  • Navigating a CTFd platform through its API with a token you supply
  • Driving a JavaScript-rendered CTF site with Playwright MCP to read challenges and submit flags
  • Deciding when to stop a line of attack and switch category

What Makes It Unique

Other CTF skills hold techniques for one category. This one holds none of the deep techniques and instead decides which skill to use and when to switch. Its difficulty routing reference treats organizer labels as weak hints, requires verified evidence before treating a challenge as hard, and sets stop-loss and escalation rules plus a check before any flag submission.

Under The Hood

The skill is instructions plus one reference file, with no scripts of its own. It tells the agent to run recon commands such as file, strings, binwalk and checksec, connect to challenge hosts with nc and curl, call a CTFd API with a token the user provides, and drive a browser through Playwright MCP. It refers to an installer script at the repository root that installs tools, and to a router script that is not part of this skill folder. Its frontmatter allows shell, file writes, web fetch, web search and invoking other skills.

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