写作风格转换
v1.0.0内容改写与风格模仿。当用户要求将文本改写成不同语气/风格时使用。触发词包括：鲁迅风、木心风、钱钟书、风格转写、改写成XX风格、模仿XX写作、整理文件、归类总结。
⭐ 2· 72·0 current·0 all-time
by@wuyiz51
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name and description (content style rewriting / author-style mimicry) align with the provided SKILL.md and the included references/writing-styles.md. The skill asks for no binaries, env vars, or external services, which is proportionate for a local instruction-only text transformation skill.
Instruction Scope
Runtime instructions are limited to: understand source text, select a target style, extract key points, and produce a rewrite according to the included style guide. The SKILL.md directs the agent to read the local references/writing-styles.md only; it does not instruct reading unrelated system files, contacting external endpoints, or accessing credentials.
Install Mechanism
No install spec and no code files beyond documentation. As an instruction-only skill, nothing is written to disk or downloaded. This is low-risk from an installation/execution perspective.
Credentials
The skill requires no environment variables, credentials, or config paths. Requested access is minimal and appropriate for the stated function.
Persistence & Privilege
always:false and default invocation settings are used. The skill does not request permanent presence or elevated privileges and does not modify other skills or system-wide settings.
Scan Findings in Context
[no-code-files] expected: The regex-based scanner had no code to analyze; the skill is instruction-only and includes only markdown reference files. This is expected for a documentation-driven text transformation skill.
Assessment
This skill appears coherent and low-risk from a technical/security standpoint. Before installing, consider legal and ethical points: (1) imitating a distinct living author's voice may raise copyright or impersonation concerns in some jurisdictions—prefer paraphrase and add a disclaimer that output is 'in the style of' rather than a literal impersonation; (2) monitor outputs for accidental verbatim reproduction of copyrighted text (the style guide is fine, but avoid copying protected passages); (3) if you plan to allow autonomous invocation, be aware the agent could produce sensitive or defamatory content when mimicking strong voices—add guardrails or review steps. If you want a deeper check, provide the runtime environment (model/policy constraints) or any planned downstream publishing workflow so I can assess additional operational risks.Like a lobster shell, security has layers — review code before you run it.
latestvk976ycnf4drs5f5fks3t1scwy983ym49
License
MIT-0
Free to use, modify, and redistribute. No attribution required.