Skip to content
SkillModel-led474 tokens in use

competition-custom-protocol-replay

A downstream CTF-sandbox skill for unknown protocols: it recovers framing, sequence and checksum rules and builds the smallest replay that reaches an accepted state.

44,996 stars on the repository MIT Licensezhaoxuya520/reverse-skill · CTF-Sandbox-Orchestrator/competition-custom-protocol-replay

Skill label

measured from its files

What installing competition-custom-protocol-replay costs

118tokens idle
474tokens in use
684tokens, 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

Nothing detected: no shell, network, file writes, git or credentials in its files.

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 →
Good
  • Frontmatter12/15
  • Structure23/25
  • Examples0/15
  • Output7/15
  • Size15/15
  • Resources7/15

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

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity96
  • Maintenance72
  • Community72
  • Maturity28
  • Momentum40

This skill is a specialization of the ctf-sandbox-orchestrator skill for challenges where the hard part is reproducing the exact message order and state needed for acceptance. The agent maps the session state machine, recovers framing and integrity fields, and keeps one canonical transcript of a successful exchange.

The skill states that it runs only after the orchestrator has set sandbox assumptions.

What You Get

  • A three-step workflow: map the session state machine, recover framing and integrity, build the minimal replay harness
  • A reference checklist ordering recovery as framing, sequence state, integrity fields, encoding or crypto boundary and transcript deltas
  • A rule to change one field or one message at a time while replaying
  • A hand-off rule to the broader PCAP skill when no stateful replay is needed

Common Use Cases

  • Decoding an unknown protocol captured in a CTF challenge
  • Building a replay harness that satisfies sequence and checksum rules in a lab
  • Showing the exact mutation that flips a session from rejected to accepted

What Makes It Unique

It goes past naming a protocol and requires an accepted replay or a meaningful state transition as proof. Its checklist separates transport segmentation from application messages, and warns against mixing messages from separate sessions into one model.

Under The Hood

The skill is instruction text only: a SKILL.md, one reference checklist and an agent configuration file. It ships no scripts. The method involves reading captures and sending test messages to a sandbox service, so the agent’s own tools run commands and open network connections in the environment the orchestrator set up. The skill does not fetch pages or call APIs on its own.

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