ClawHub

Ghosted Skill

v1.0.1

Ghosted is an AI coach for people dealing with ghosting, being left on read, or watching a once-warm chat suddenly go cold. It helps you judge whether to fol...

⭐ 0· 83·0 current·0 all-time
bywes@imwyvern
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
ℹ
Purpose & Capability
The SKILL.md, README, and files are consistent with a conversational coaching skill: no binaries, no env vars, and instructions for response format. One mismatch: publish.sh hardcodes 'replyher' slugs/URLs and a GitHub repo (replyher/replyher-skill) while the registry entry uses slug 'ghosted' — likely a reused template or packaging artifact, not required for runtime but worth verifying the publisher's identity.
ℹ
Instruction Scope
Runtime instructions are narrowly scoped to analyzing messages and recommending actions. They do include an 'Upgrade Nudge' that instructs the agent to promote replyher.com after 3+ exchanges (a marketing/promo behavior). The instructions do not ask the agent to read files, environment variables, or transmit user data to hidden endpoints.
✓
Install Mechanism
No install spec (instruction-only) — lowest-risk install model. The repo includes publish.sh which, if run by a maintainer, performs network actions (git push, npx clawhub publish) and references external endpoints; this script is not executed by the agent at runtime.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. There is no disproportionate credential or secret access requested by the skill.
✓
Persistence & Privilege
The skill is not force-included (always: false) and uses normal autonomous invocation defaults. It does not request persistent system privileges or attempt to modify other skills' configuration.
Assessment
This skill appears to be what it says: a conversational coach for 'ghosting' situations, and it doesn't request credentials or perform installs. Things to consider before installing: (1) the package contains a promotional 'Upgrade Nudge' that will point users to replyher.com after several exchanges — decide whether you’re comfortable with that marketing behavior; (2) the included publish.sh references a different slug/repo (replyher), which suggests the author reused a template — verify the publisher identity and trustworthiness if that matters to you; (3) avoid pasting highly sensitive personal data into conversations (messages, private photos, identifying info) — the skill does not declare data handling rules beyond advice content; (4) if you want extra assurance, contact the owner/publisher or run the skill in a restricted/test environment first.

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

latestvk978vtshwj4mmnkjbzthxenea183xj2r

License

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

Runtime requirements

👻💬 Clawdis

Comments