Replyher Skill
v1.4.0ReplyHer 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· 177·0 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
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (ReplyHer: message replies, screenshot reading, coaching) align with the SKILL.md and README. The skill is instruction-only and does not request unrelated credentials or binaries. Pro features (relationship memory, screenshot recognition) are mentioned as paid features in the README but are not implemented or requested by the skill itself.
Instruction Scope
SKILL.md stays on-topic: it instructs the agent how to decode messages, ask minimal follow-ups, and how to handle screenshots (read visible text and ask one key follow-up). It does not instruct reading system files, environment variables, or routing data to third-party endpoints. The screenshot handling assumes the platform supplies the image content to the model; the SKILL does not include steps that would exfiltrate data.
Install Mechanism
No install spec is included (instruction-only), so nothing is written to disk or downloaded during install. The only script present is publish.sh, which is an author helper to commit and publish to ClawHub/GitHub and is not executed as part of skill runtime.
Credentials
The skill declares no required environment variables, credentials, or config paths. This is proportionate to its stated purpose. There are mentions of external pro features and a marketing domain (replyher.com) in the README, but no runtime credential or network instructions that would require secrets.
Persistence & Privilege
Flags: always:false and default autonomous invocation allowed. The skill does not request permanent presence, nor does it modify other skills or system settings. Nothing in the files indicates it would store or persist agent-wide credentials.
Assessment
This skill appears internally consistent and low-risk from a technical footprint perspective. Before installing, consider: (1) Privacy: you will be pasting private messages and possibly screenshots — avoid sharing highly sensitive data (passwords, IDs, financial info). (2) External services: the README advertises a pro site (replyher.com) and features like "relationship memory" and "screenshot recognition"; if you later enable a paid/pro integration, verify its privacy policy and where your data is sent. (3) Platform handling of images: the SKILL.md assumes the platform provides image text to the model; confirm how your OpenClaw/agent host processes/uploads images. If you’re comfortable with those privacy considerations, the skill’s behavior matches its description.Like a lobster shell, security has layers — review code before you run it.
latestvk9789vv6jfz211x3cenc5y2w8n8475yv
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
💕🔥 Clawdis