radare2

Use this skill whenever the user wants to analyze binaries with radare2/r2 from the command line, including reverse engineering, disassembly, function analysis, strings/import inspection, patching, binary diffing, hex inspection, or r2 scripting. Also use it when the user mentions PE/ELF/Mach-O/DEX/WASM files together with CLI analysis, `rabin2`, `rasm2`, `radiff2`, `r2pipe`, or asks for radare2 command help on Windows/Linux/macOS.

Quality

90%

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

81%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.

Highly actionable and well-sequenced content with strong validation gates and feedback loops for destructive operations. The main weakness is conciseness: inline command reference duplicates the cheatsheet bundle, and governance boilerplate could be trimmed.

Suggestions

Move the '常用子工具' inline command reference into references/cheatsheet.md and replace it with a one-line pointer to avoid duplicating the same rabin2/rasm2/radiff2/rahash2/rax2 examples in two places.

Tighten the 硬门禁/Evidence/MUST governance text — consolidate the repeated MUST/MUST NOT clauses into a single concise gate so the same rule is not restated across multiple sections.

Reference scripts/recon.sh in the body alongside recon.ps1 so the Linux/macOS equivalent bundle file is discoverable, not just the Windows script.

Dimension	Reasoning	Score
Conciseness	The body is command-dense and avoids explaining concepts Claude already knows, but it inlines a '常用子工具' command reference that largely duplicates references/cheatsheet.md, and the governance/Evidence/MUST boilerplate is verbose and could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready commands throughout — 'rabin2 -I/-z/-i/-E', 'r2 -A -q -c "afl;iz;ii;q"', the recon.ps1 invocation with exact flags, and patch commands 'wa nop'/'wx'/'wq' cover the common cases.	5 / 5
Workflow Clarity	Six clearly sequenced workflows plus a numbered '推荐分析顺序', with explicit validation gates (硬门禁 requiring Evidence before deep-dive), feedback loops (IAT-repair failure → E-iat-repair-fail → dynamic), and a completion self-check checklist for destructive/batch steps.	5 / 5
Progressive Disclosure	A dedicated '内置资源' section clearly signals one-level-deep references to references/cheatsheet.md and scripts/recon.ps1, but the inlined subtool command reference duplicates the cheatsheet and scripts/recon.sh is a bundle file not referenced in the body.	4 / 5
	Total	17 / 20 Passed

Description

100%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.

A strong, specific description that clearly states capabilities, includes rich natural trigger terms with synonyms and file formats, and explicitly covers both what and when. Third-person voice is preserved and it stays concise rather than padded.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'reverse engineering, disassembly, function analysis, strings/import inspection, patching, binary diffing, hex inspection, or r2 scripting' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (analyze binaries with radare2/r2 from the CLI incl. RE/disasm/patching/...) and 'when' via two concrete 'Use this skill whenever...' / 'Also use it when...' trigger clauses.	5 / 5
Trigger Term Quality	Comprehensive natural terms including synonyms ('radare2/r2'), file formats ('PE/ELF/Mach-O/DEX/WASM'), subtool names ('rabin2', 'rasm2', 'radiff2', 'r2pipe'), and platforms ('Windows/Linux/macOS') that users would actually say.	5 / 5
Distinctiveness Conflict Risk	Anchored to a clear niche (radare2 CLI binary analysis) with distinct tool- and format-level triggers, giving minimal conflict risk with adjacent reverse-engineering skills.	5 / 5
	Total	20 / 20 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: skills/radare2/SKILL.md
Commit: 3ae5c59

Reviewed: ~2 hours 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.