ClawHub

Replyher Skill Pub

v1.5.0

ReplyHer is an AI reply and message coach for people who need the right chat response fast. It helps you decode texting context, read screenshots, generate c...

⭐ 0· 242·0 current·0 all-time
bywes@imwyvern
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, README, and SKILL.md consistently describe a texting-reply coach. No environment variables, binaries, or config paths are requested that would be inconsistent with this purpose.
✓
Instruction Scope
SKILL.md gives detailed guidance for analyzing messages and screenshots and how to ask minimal follow-ups. The instructions reference reading screenshots and inferring UI, which is coherent for a reply/screenshot-analysis skill and do not instruct reading unrelated system files or secrets.
✓
Install Mechanism
This is an instruction-only skill with no install spec. The only executable file is publish.sh (a developer publish script) which is not part of runtime and only invokes git/npx for publishing; it does not affect runtime behavior.
✓
Credentials
No required environment variables, credentials, or config paths are declared or used. The skill does not request any secrets or unrelated service access.
✓
Persistence & Privilege
always is false and disable-model-invocation is the default (model can invoke autonomously), which is normal. The skill does not request permanent system presence or modify other skills' configs.
Assessment
This skill appears internally consistent for messaging coaching, but consider the following before installing: (1) Privacy — the skill asks you to paste messages or upload screenshots; avoid sending sensitive personal data, account credentials, or images containing IDs/financial info. (2) Data handling — SKILL.md does not state whether processing happens locally or remotely; if you need guarantees, ask the skill/provider or check the platform's privacy docs. (3) Source trust — the skill has no homepage and an unknown source/owner ID; if provenance matters, seek a published repository or vendor info. (4) Autonomous invocation — the skill may be invoked by the agent during conversations; if you prefer manual use only, disable autonomous invocation in your agent settings. (5) Content limits — this is coaching, not professional counseling or legal advice; treat outputs as suggestions and verify sensitive responses yourself.

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

latestvk978sz4n3c2dzggykccmga8j8x84szbz

License

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

Runtime requirements

💕🔥 Clawdis

Comments