competition-reverse-pwn

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for reverse engineering, malware, DFIR, firmware, pwnable, and native exploit challenges. Use when the user asks to reverse a binary, unpack a sample, inspect a memory dump or PCAP, recover malware behavior, debug a crash, or build or verify an exploit chain under sandbox assumptions. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

72%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 lean and well-structured with clean progressive disclosure to a verified reference, but actionability and workflow clarity are held back by the absence of named tools/commands and explicit validate->retry feedback loops for risky reverse/pwn operations.

Suggestions

Add named triage and exploit tools/commands (e.g., `file`, `strings`, `binwalk`, `checksec`, `r2`/`radare2`, `gdb`+pwndbg) and one short worked example so guidance is executable rather than categorical (raises actionability).

Add an explicit validate->fix->retry loop for risky steps — e.g., 'Only proceed to exploit construction after the primitive reproduces from a clean baseline; if reproduction fails, revisit the decode edge or mitigation mapping' (raises workflow_clarity).

Add a pass/fail checkpoint after instrumentation or patching (re-verify the primitive from a clean baseline) to satisfy the destructive-operations validation requirement (raises workflow_clarity).

Dimension	Reasoning	Score
Conciseness	Lean, terse bullets with no padding or explanation of concepts Claude already knows ('Start with passive triage: type, headers, sections, imports, strings, entropy, resources'); every token earns its place, matching the lean/efficient anchor.	3 / 3
Actionability	Concrete methodology guidance is present ('Record the primitive, controllable bytes, leak source, target object, and final artifact separately'), but no named tools, commands, or worked examples appear, leaving guidance actionable-but-incomplete rather than copy-paste ready; not level 3 for that reason, and not level 1 because the steps are specific rather than vague.	2 / 3
Workflow Clarity	A clear 5-step Quick Start and 2-phase Workflow exist with one verification step ('Reproduce the artifact or primitive from a clean baseline'), but there is no explicit validate->fix->retry feedback loop for the destructive/risky operations (sample execution, exploit dev), capping at 2 per the destructive-operations guideline; not level 1 because the sequence is present and ordered.	2 / 3
Progressive Disclosure	The overview body points to a single, clearly signaled one-level reference ('Load `references/reverse-pwn.md`' — verified to exist) with content appropriately split, plus navigation to sibling skills; not level 2 because the reference is one level deep and well-signaled rather than inline-bloated or nested.	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, and complete with an explicit 'Use when' clause and a strong routing constraint that makes it distinctive. It is a strong example of a downstream-skill description, written in the required third person.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'reverse a binary, unpack a sample, inspect a memory dump or PCAP, recover malware behavior, debug a crash, or build or verify an exploit chain' — matching the multiple-specific-actions anchor; not level 2 because it enumerates concrete actions beyond merely naming a domain.	3 / 3
Completeness	Answers 'what' ('CTF-sandbox workflow for reverse engineering, malware, DFIR, firmware, pwnable, and native exploit challenges') and 'when' with an explicit 'Use when the user asks to...' clause; not level 2 because the trigger is explicit rather than merely implied.	3 / 3
Trigger Term Quality	Uses phrasing a CTF user would naturally say ('reverse a binary', 'unpack a sample', 'inspect a memory dump or PCAP', 'debug a crash'), giving good coverage across reverse/DFIR/pwn; not level 2 because it spans multiple natural variations rather than a single keyword.	3 / 3
Distinctiveness Conflict Risk	Clear niche reinforced by 'Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here', which delegates triggering to the orchestrator; not level 2 because the routing constraint and explicit sibling steering make overlap unlikely despite the broad domain list.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zhaoxuya520/reverse-skill
Path: CTF-Sandbox-Orchestrator/competition-reverse-pwn/SKILL.md
Commit: 6aa1362

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.