Openclaw I18n Skill
v1.0.0Internationalization and localization layer for OpenClaw. Auto-detects language, enforces correct diacritics, formats dates/currency per locale, and pipes ou...
⭐ 0· 76·0 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 match the provided code: a local Python post-processor and language modules for Romanian and German. No unrelated environment variables, binaries, or cloud credentials are requested. Minor inconsistencies in metadata (SKILL.md and package.json/openclaw.plugin.json disagree on pricing and which languages are 'stable') but these are documentation issues rather than functional mismatches.
Instruction Scope
SKILL.md instructs the agent to run a local post-processor that removes stray non-Latin characters, enforces diacritics, normalizes whitespace, and applies conservative typo dictionaries. The code follows this behavior. Be aware: base.remove_non_latin_characters will remove non-Latin characters when they are glued to Latin text (intentionally designed), which can strip legitimate foreign tokens if they are provided without a separating space — SKILL.md documents this. The rules are conservative but deterministic; test with representative inputs to ensure no undesired removals or diacritic substitutions for your use case.
Install Mechanism
No automatic install spec is bundled; this is an instruction-only skill with included Python source. SKILL.md and README propose installing from ClawHub or manually cloning and pip installing requirements.txt. There are no downloads from untrusted URLs, no archive extracts, and no post-install scripts in the package metadata. (Note: package.json and SKILL.md conflict on pricing/free status; this is a documentation discrepancy.)
Credentials
The skill declares no required environment variables or credentials and the processor code does not access network or environment secrets. The only persistence mentioned is using OpenClaw's memory tools for language preferences, which is expected and proportional for a language-config feature.
Persistence & Privilege
always:false and disable-model-invocation:false (defaults) — the skill can be invoked by the agent (normal for skills) but it is not forced into every agent run. The skill does not attempt to modify other skills or system-wide configuration in the repository files.
Assessment
What to consider before installing:
- Functionality: This skill is coherent for i18n/post-processing: it runs locally, fixes diacritics, removes stray non-Latin chars when glued to Latin text, and normalizes whitespace. That behavior is intentional and documented.
- Test first: Run the included test suite and try sample outputs from your agents (especially edge cases with proper names, quoted foreign text, or intentionally mixed scripts) to ensure the post-processor doesn't remove or alter legitimate content you care about.
- Review code if you have strict data-handling needs: The visible Python modules contain no network calls or credential access, but you should grep the full package (including omitted files) for 'requests', 'socket', 'urllib', or subprocess usage if you require absolute certainty.
- Metadata inconsistencies: SKILL.md and package.json/openclaw.plugin.json disagree about pricing and which languages are "stable". Confirm the publisher and licensing if you depend on maintenance/support.
- False positives: The language-specific typo dictionaries contain some noisy or duplicated entries (especially in the German/Spanish modules). If you rely on verbatim outputs (legal text, code snippets, names), consider disabling or narrowing the post-processor for those contexts.
- Deployment: If you install via ClawHub, review the install source (bloommediacorporation-lab/openclaw-i18n-skill) and verify the repo is the intended upstream. If using manually, run the package's tests locally and inspect processor/requirements.txt before pip installing.
If you'd like, I can (a) scan the omitted files for network calls or subprocess use, (b) extract and summarize the requirements.txt, or (c) run a short checklist of code-pattern searches to increase confidence.Like a lobster shell, security has layers — review code before you run it.
latestvk97dsy7dv8v58ktd6ye2j41za183sm2b
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🌍 Clawdis
