CtrlK
BlogDocsLog inGet started
Tessl Logo

competition-custom-protocol-replay

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for custom binary or text protocol recovery, handshake reconstruction, framing, sequence control, checksums, stateful replay, and accepted-session reproduction. Use when the user asks to decode an unknown protocol, recover custom framing, build a replay harness, satisfy sequence or checksum rules, replay a captured session, or prove the smallest message order that reaches an accepted branch. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise, well-structured, and uses a real single-level reference for detail. It is weaker on actionability (checklist rather than executable harness/code) and lacks an explicit verification checkpoint for the replay-proof step.

Suggestions

Add a minimal, runnable replay harness skeleton (e.g., a short Python snippet framing a message, computing its checksum, and sending it) so the guidance is copy-paste executable rather than checklist-only.

Insert an explicit verification checkpoint in the workflow, such as 'Confirm acceptance by re-running the minimal transcript and asserting the server's accepted response/side effect before broad mutation.'

Show one concrete worked example of a 'change one field at a time' mutation that flips a rejected transcript to accepted, to make the decisive-branch proof actionable.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: no preamble about what protocols are, each line is an actionable directive, and the reference is deferred rather than inlined.

3 / 3

Actionability

Guidance is concrete in direction (recover framing, build minimal replay harness, mutate one field at a time) but stays at the checklist level with no executable code, commands, or worked examples; the anchor for score 2 fits 'some concrete guidance but incomplete.'

2 / 3

Workflow Clarity

Quick Start and a numbered Workflow give a clear sequence, but there are no explicit validation/verification checkpoints for the replay verification step (proving the accepted branch), which the rubric treats as a checkpoint gap capping this at 2.

2 / 3

Progressive Disclosure

A concise overview body points to one clearly signaled, single-level reference (references/custom-protocol-replay.md) that genuinely exists and holds the checklists, with no nested reference chains.

3 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, complete, and well-scoped to a downstream CTF specialization with an explicit precondition. It is dense but every clause earns its place and the third-person voice is maintained.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'handshake reconstruction, framing, sequence control, checksums, stateful replay, and accepted-session reproduction' — a broad, specific action set rather than vague language.

3 / 3

Completeness

Explicitly answers both what (the recovery/replay capabilities) and when (a clear 'Use when the user asks to...' clause plus a 'Use only after $ctf-sandbox-orchestrator...' precondition).

3 / 3

Trigger Term Quality

Covers natural user phrasings such as 'decode an unknown protocol,' 'recover custom framing,' 'build a replay harness,' and 'replay a captured session,' matching how a user would actually request this skill.

3 / 3

Distinctiveness Conflict Risk

The downstream precondition ('Use only after $ctf-sandbox-orchestrator has already established sandbox assumptions') carves a clear niche and routing rule, making triggering for the wrong skill unlikely.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
zhaoxuya520/reverse-skill
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.