Greek
v1.0.0Write Greek that sounds human. Not formal, not robotic, not AI-generated.
⭐ 2· 757·0 current·0 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the SKILL.md guidance: all instructions are about producing colloquial Greek. There are no unrelated environment variables, binaries, or install steps requested.
Instruction Scope
The SKILL.md stays within its stated purpose (how to write informal, natural Greek). It does grant the agent stylistic discretion (e.g., when to use fillers, profanity, Greeklish, truncations), which is expected for a style guide but may lead to offensive or inconsistent outputs if not constrained. The instructions do not ask the agent to read files, access the environment, or call external endpoints.
Install Mechanism
No install spec and no code files — lowest-risk instruction-only skill. Nothing will be downloaded or written to disk by the skill itself.
Credentials
The skill requires no environment variables, credentials, or config paths; requested access is proportional (none) to its stated goal.
Persistence & Privilege
The skill is not always-on and does not request elevated or persistent platform privileges. Autonomous invocation is allowed (platform default) but not combined with other red flags.
Assessment
This skill is instruction-only and internally consistent with its purpose: teaching the agent to write casual, native-sounding Greek. It does not request installs or secrets, so from a system-privilege perspective it is low risk. Considerations before installing: 1) The style guidance explicitly encourages fillers, truncations, slang, profanity, and Greeklish — review and test outputs if you need to avoid offensive language or maintain formality. 2) Because the rules give the agent discretion, results may vary in dialect, tone, or appropriateness; add guardrails if you will use this in user-facing or moderated contexts. 3) No code was present for scanner analysis (instruction-only), so behavior is fully determined by the agent runtime and your prompts; test with representative prompts to confirm it meets your expectations.Like a lobster shell, security has layers — review code before you run it.
latestvk9729m0sqmb1485azw5650y77x80xxgh
License
MIT-0
Free to use, modify, and redistribute. No attribution required.