rant-translator
v1.0.0中文阴阳怪气 → 英文阴阳怪气神器！输入吐槽，自动输出温和版、原味阴阳版（中英双语）、美式/日式/韩式文化适配版 + 表情包建议 + 被封风险评估。跨平台发帖不翻车，年轻人专属吐槽机。
⭐ 0· 116·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description and SKILL.md consistently describe a text-rewriting/translation tool for sarcastic rants. It declares no binaries, env vars, or installs — all appropriate for a purely prompt-driven text transform.
Instruction Scope
Instructions are detailed and stay within the translator/rewriter scope (specific output format, variation styles, emoji suggestions, and risk scoring). Two items to note: (1) it suggests using 'memory' to recall prior user rants (which implies persistent context) while also claiming not to store user rants unless explicitly asked — this is a potential inconsistency that should be clarified in practice; (2) it offers optional network search for emoji if the user allows external tools, which expands runtime surface but is conditional on explicit permission.
Install Mechanism
Instruction-only skill with no install spec and no code files — lowest-risk install profile (nothing is written to disk by the skill itself).
Credentials
No environment variables, credentials, or config paths requested. The lack of sensitive requirements is proportional to a text-only rewriting/translation skill.
Persistence & Privilege
Skill is user-invocable and not forced-always-on. It does not request persistent system privileges. The SKILL.md's mention of using memory should be treated as a voluntary feature that must respect platform memory/consent controls.
Assessment
This skill appears to do exactly what it says: rewrite/translate sarcastic rants into multiple tones and give emoji and risk scores. Before installing, consider: (1) clarify memory usage — the doc mentions 'recalling previous rants' but also claims not to store inputs unless asked; confirm how/where context is saved and whether you must opt in; (2) the skill can optionally search the web for emoji/graphics if you permit network tools — only grant that if you trust the agent's network behavior; (3) the skill can generate edgy or borderline content by design — prefer the '温和版' when posting to public platforms to avoid moderation or account risk; (4) no credentials or installs are required, so there is no direct credential-exfiltration risk. If you want higher assurance, ask the developer how memory is implemented and whether any external calls are made by default.Like a lobster shell, security has layers — review code before you run it.
latestvk97ey2bwtyf53d7v23z0eq3bgs835db2
License
MIT-0
Free to use, modify, and redistribute. No attribution required.