Name: reverse-engineer
Rating: 49.6 (1 reviews)
Author: administrakt0r

reverse-engineer

Expert reverse engineer specializing in binary analysis, disassembly, decompilation, and software analysis. Masters IDA Pro, Ghidra, radare2, x64dbg, and modern RE toolchains.

Quality

54%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/reverse-engineer/SKILL.md

The canonical home for this skill is reverse-engineer in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

38%Weight 40%Scale 1-5

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

The body is well-sectioned and offers some concrete commands and code, but it is padded with concepts Claude already knows, lacks validation feedback loops, and relies on a broken reference to a nonexistent playbook. Trimming known-concept explanations and either creating or removing the missing reference would improve it most.

Suggestions

Remove or relocate the Calling Conventions and Common Code Patterns sections — these are concepts Claude already knows and inflate the token budget.

Fix progressive disclosure: either create `resources/implementation-playbook.md` or drop the reference, and move bulk reference material (examples, patterns) into bundled reference files one level deep.

Add explicit validation/verification checkpoints to the methodology (e.g., 'Confirm findings by re-running under the debugger; if behavior mismatches static analysis, revisit Phase 2').

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the Calling Conventions and Code Pattern Recognition sections re-explain concepts Claude already knows, and the boilerplate 'Use/Do not use this skill when' blocks plus a stray unclosed code fence add padding.	2 / 5
Actionability	Genuine executable commands appear in the examples (`file`, `checksec`, `gdb break strcmp`, `dumpbin /exports`) and real C snippets, but the methodology and Response Approach are abstract directives ('Apply relevant best practices and validate outcomes') rather than executable steps.	3 / 5
Workflow Clarity	A clear four-phase sequence (Reconnaissance → Static → Dynamic → Documentation) with numbered steps is present, but there are no explicit validation checkpoints or fix-retry feedback loops, only an implicit 'validate outcomes' mention.	3 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the sole external pointer, `resources/implementation-playbook.md`, references a missing file, while reference-style material (calling conventions, code patterns) is inlined rather than split out.	2 / 5
	Total	10 / 20 Passed

Description

70%Weight 40%Scale 1-5

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 and well-targeted to a distinct RE niche with strong tool-based triggers, but it omits any 'when to use' guidance, capping completeness. Adding an explicit Use-when clause covering natural triggers (malware analysis, CTF binaries, deobfuscation) would raise it substantially.

Suggestions

Append an explicit 'Use when...' clause naming natural triggers such as malware analysis, CTF binary challenges, deobfuscation, or vulnerability research.

Drop the redundant 'and software analysis' which adds no concrete capability beyond the named actions.

Add a couple of common synonyms/file cues (e.g., 'ELF/PE binaries', 'cracking') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ('binary analysis, disassembly, decompilation') plus specific tools, but the trailing 'software analysis' is generic padding, leaving minor coverage gaps short of comprehensive.	4 / 5
Completeness	Provides a clear 'what' (binary analysis, disassembly, decompilation, tool mastery) but no 'Use when...' trigger clause, so per the guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes natural domain terms ('reverse engineer', 'disassembly', 'decompilation') and strong tool triggers (IDA Pro, Ghidra, radare2, x64dbg), though common synonyms like 'malware analysis', 'CTF', or 'deobfuscation' are missing.	4 / 5
Distinctiveness Conflict Risk	A clearly bounded reverse-engineering niche anchored by named specialized tools (IDA Pro, Ghidra, radare2, x64dbg) gives it distinct triggers with minimal overlap risk; voice is appropriately third person.	5 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/reverse-engineer/SKILL.md
Commit: 57c135b

Reviewed: 2 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.