ClawHub

Humaniseur Fr

v1.0.2

Remove AI-writing patterns from French text and inject voice, personality, and soul. Use when editing, reviewing, rewriting, or cleaning up French content th...

⭐ 0· 11·0 current·0 all-time
bySamuel Berthe@samber
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
CryptoCan make purchases
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description match the content of SKILL.md: it describes detecting and rewriting specific French AI-writing patterns and does not request unrelated resources, binaries, or credentials.
✓
Instruction Scope
SKILL.md confines runtime behavior to analyzing and rewriting provided French text and lists explicit patterns to remove; it does not instruct reading system files, accessing environment variables, or contacting external endpoints.
✓
Install Mechanism
No install spec and no code files — instruction-only — so nothing is downloaded or written to disk by the skill itself.
✓
Credentials
The skill requests no environment variables, credentials, or config paths; the scope of requested access is proportionate to a text-editing skill.
ℹ
Persistence & Privilege
always:false and disable-model-invocation:false (normal). The skill metadata includes allowed-tools such as Read/Edit/Write/Grep which would enable file/document edits when the agent runs it — expected for an editor skill but worth noting before enabling autonomous invocation.
Assessment
This is an instruction-only French text-editing skill and appears internally consistent. Before installing: (1) verify the GitHub homepage/author if you want provenance (the SKILL.md lists author 'samber' and a repo URL); (2) consider whether you trust the agent to edit files/documents — the skill's allowed-tools enable reading and writing content; (3) if you’re concerned about autonomous edits, restrict or review agent invocation policies (disable autonomous use or require user confirmation); (4) review sample outputs on the repo to ensure the rewriting style fits your needs.

Like a lobster shell, security has layers — review code before you run it.

latestvk978v81vamp7ae9rmvdsbve7js84kc0s

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Runtime requirements

🤖 Clawdis

Comments