ida-reverse

IDA Pro 逆向分析辅助技能。当用户提到逆向、反编译、分析二进制/PE/ELF/APK/DLL/SO、破解、找密码、漏洞分析、病毒分析、firmware 固件分析，或需要分析 exe/dll/so/elf/macho/sys 等文件时，务必使用此技能。 Ensure to use this skill when the user wants to analyze any binary file, regardless of whether they explicitly mention "IDA" or "reverse engineering". This includes requests like "看看这个exe", "分析这个dll", "帮我破解", "找一下密码", "这个软件怎么注册", etc. Use the bundled scripts (scripts/start.ps1, scripts/open.ps1) for deterministic server management and file opening — do NOT write ad-hoc PowerShell commands for these operations.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

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 content is highly actionable with concrete commands, a well-sequenced workflow, and robust validation/error-recovery feedback loops. Its weaknesses are conciseness (the inline 72-tool catalogue and known-issues section duplicate bundle content) and progressive disclosure, which could offload more detail to the existing reference file.

Suggestions

Move the full 72-tool catalogue into references/ida-mcp-cheatsheet.md and keep only the first-step survey tools inline, with a clear pointer to the cheatsheet for the rest.

Trim the '踩过的坑' known-issues narrative to the two highest-impact gotchas (schema validation workaround, lock-file/orphan-process cleanup), linking scripts for the rest.

Cross-link the reference file explicitly from the tool-list section (e.g., '完整 72 工具列表见 references/ida-mcp-cheatsheet.md') so progressive disclosure navigation is clearly signaled.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and largely avoids explaining concepts Claude already knows, but it is long and partly padded — the '踩过的坑' section and repeated script-output conventions duplicate information already conveyed in the script docs and the 72-tool catalogue could itself live in the reference.	2 / 3
Actionability	Provides fully executable PowerShell commands with concrete flags (-Path, -TimeoutSeconds, -NoAutoAnalysis), real tool call signatures (idapro_survey_binary(detail_level="minimal"), idapro_trace_data_flow(...)), and copy-paste-ready workflow steps with expected output tokens.	3 / 3
Workflow Clarity	A clear 7-step reverse-engineering workflow with explicit validation checkpoints (OK:72 / OK:filename:session_id / ERR:open_timeout_xxs), error-recovery fallbacks (temp-copy degradation, taskkill process cleanup), and a final MUST-pass self-check checklist.	3 / 3
Progressive Disclosure	The body does signal a real one-level reference (references/ida-mcp-cheatsheet.md) and bundle scripts, but it also inlines a large 72-tool catalogue and detailed script docs that overlap with those bundle files, so the SKILL.md is heavier than a pure overview pointer.	2 / 3
	Total	10 / 12 Passed

Description

90%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 a strong, bilingual trigger-rich statement that clearly answers both what and when with concrete example phrases. Its main weakness is specificity of capabilities — it describes the domain and file types but not multiple distinct concrete actions.

Suggestions

Add 2-3 concrete actions to the description (e.g., decompile, disassemble, trace cross-references/data flow, rename and comment functions) so capability specificity matches the body.

Tighten the bilingual redundancy: the Chinese and English trigger lists overlap heavily; a single consolidated trigger set would reduce verbosity without losing coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (IDA Pro reverse analysis) and lists concrete file types (exe/dll/so/elf/macho/sys), but the only concrete actions stated are 'analyze binary files' and 'use the bundled scripts'; it does not enumerate multiple specific actions like decompile, disassemble, or rename, which live in the body.	2 / 3
Completeness	Clearly answers what the skill does (IDA Pro reverse analysis) and when to use it, with explicit 'Use when...' / '务必使用此技能' trigger guidance and concrete example triggers.	3 / 3
Trigger Term Quality	Strong coverage of natural trigger phrases users would actually say, including '看看这个exe', '分析这个dll', '帮我破解', '找一下密码', '这个软件怎么注册', plus technical terms (PE/ELF/APK/DLL/SO, firmware, 病毒分析).	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (IDA Pro binary reverse engineering via the bundled idalib-mcp scripts) with distinct file-type and action triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: skills/ida-reverse/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.