binary-diff

跨版本符号迁移与二进制差分。当你有旧版本的符号/逆向结果，需要快速迁移到新版本时使用。适用场景：内核缺 PDB 用旧版符号推导、程序更新后批量迁移函数名、应用更新后快速定位新偏移。核心方法：用 LLM 做结构化差异比对，程序化输入输出，成本极低（200 函数 ~1 元）。触发关键词：符号迁移、bindiff、跨版本、PDB 缺失、函数偏移迁移、symbol migration、binary diff、版本对比。

Quality

82%

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

65%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 highly actionable with concrete prompt/code/application guidance and a clear ordered workflow, but loses points for token duplication (inline vs reference prompt template), lack of an explicit validation feedback loop in the batch workflow, and an un-signaled reference file.

Suggestions

Remove the duplicate prompt template from the body and replace it with a clear, signaled reference (e.g. 'See [prompt-template.md](references/prompt-template.md) for the template, Python skeleton, and API config'), keeping only a brief variable table inline.

Add an explicit validation/feedback checkpoint in the workflow between the LLM comparison and application steps — e.g. parse YAML → spot-check a sample of mappings → on mismatch, retry or flag — to satisfy the batch-operation validation expectation.

Tighten the two 典型场景示例 walkthroughs or move them to a reference, since they largely restate the core workflow and inflate token usage.

Dimension	Reasoning	Score
Conciseness	Mostly high-signal (exact prompt template, variable tables, output schema, application actions), but the prompt template is duplicated between the body and references/prompt-template.md and the two full scenario walkthroughs restate parts of the workflow, so it could be tightened rather than earning 'every token earns its place'.	2 / 3
Actionability	Provides a copy-paste prompt template, a variable-filling table, a complete Python skeleton (httpx call + YAML extraction + apply_results), concrete idapro_rename/idapro_set_comments actions, and model/cost thresholds — fully executable guidance.	3 / 3
Workflow Clarity	The 5-step sequence (准备数据→批量导出→LLM比对→应用结果→迭代) and anchor/batch guidance are clearly ordered, but a batch operation lacks an explicit validate→fix→retry checkpoint inside the workflow (人工抽检 is only mentioned in notes), capping it below 3 per the batch-operations guideline.	2 / 3
Progressive Disclosure	Content is organized into sections and the reference (prompt-template.md) is only one level deep, but the reference is never explicitly linked/signaled from the body and the prompt template is duplicated inline, leaving navigation and content-splitting only partly realized.	2 / 3
	Total	9 / 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 strong: it states concrete capabilities, gives rich natural-language triggers in two languages, and explicitly couples what-it-does with when-to-use guidance in a distinct niche. No weaknesses warrant suggestions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '符号迁移与二进制差分', '用 LLM 做结构化差异比对', '程序化输入输出', '批量迁移函数名', '快速定位新偏移' — across several distinct scenarios, matching the 'lists multiple specific concrete actions' anchor rather than merely naming a domain.	3 / 3
Completeness	Explicitly answers both what ('跨版本符号迁移与二进制差分...用 LLM 做结构化差异比对') and when ('当你有旧版本的符号/逆向结果，需要快速迁移到新版本时使用' plus an 适用场景 list), giving explicit trigger guidance.	3 / 3
Trigger Term Quality	Provides a broad, natural keyword set a reverse-engineer would actually say — '符号迁移、bindiff、跨版本、PDB 缺失、函数偏移迁移、symbol migration、binary diff、版本对比' — covering common variations in both languages.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche — cross-version symbol migration leveraging existing old-version results — with distinct triggers unlikely to fire for unrelated skills.	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: skills/binary-diff/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.