ClawHub

Text Humanizer Instruction Based

v0.1.0

Detect and rewrite AI-generated writing patterns, em dashes, rule-of-three lists, sycophantic openers, hollow buzzwords like "delve" and "landscape", and rep...

⭐ 0· 85·0 current·0 all-time
by@arbazex
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (detect and rewrite AI-style wording) align with the SKILL.md. The skill requires no binaries, no credentials, and has no install step — all proportionate for an instruction-only text-rewriting helper.
ℹ
Instruction Scope
The SKILL.md contains a detailed master list of 45 patterns and precise rewrite rules; it instructs the agent to read the whole input, infer purpose/audience if unstated, and apply rules silently (unless a detection report is requested). This behavior is consistent with the skill goal but means the agent may rewrite content without showing a step-by-step detection summary by default — users who want explicit change logs should request a report.
✓
Install Mechanism
No install spec or code is provided; this is an instruction-only skill, so nothing is written to disk or downloaded.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. There is no disproportionate access to secrets or external services.
✓
Persistence & Privilege
always is false and the skill does not request elevated or persistent system presence. It is user-invocable and can be invoked autonomously per platform defaults, which is normal for skills of this type.
Assessment
This skill is coherent with its stated purpose and does not request credentials or downloads. Consider that it will rewrite input text according to its internal rule set and may change tone or nuance — review outputs before using in sensitive contexts (job applications, legal/medical text, or anything where precise wording matters). If you want an explicit list of detected 'tells' rather than silent edits, ask the skill for a detection report. If you are concerned about autonomous invocation by an agent, control when the skill is enabled and monitor actions that send edited text externally.

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

latestvk977f33qjxe3qr84scmrsz4k2183a6cp

License

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

Runtime requirements

✍️ Clawdis

Comments