ClawHub

Communication Skill

v0.1.0

Helps craft context-aware, empathetic messages by synthesizing conversation history, emotional cues, and relationship dynamics for clear, effective communica...

⭐ 3· 3.7k·16 current·18 all-time
by@aatmaan1
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
The skill's name and SKILL.md describe a communication/drafting assistant that gathers conversational context, applies communication principles, and crafts responses. It does not request unrelated binaries, environment variables, or config paths — the capabilities it asks for (gathering conversation context, user notes) align with a messaging/communication helper.
ℹ
Instruction Scope
Instructions ask the agent to 'gather' context including conversation history, parallel threads, connected sources, and user notes when available. That is coherent for a communication skill, but it implies the agent may access any connected apps or notes the user has granted the agent access to. The skill does not instruct reading arbitrary system files or exfiltrating data to third-party endpoints.
✓
Install Mechanism
No install spec or code files are present; this is instruction-only, so nothing is downloaded or written to disk by the skill itself.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths. The SKILL.md’s references to user-defined principles and connected sources are configuration / context expectations rather than demands for secrets, so the requested scope is proportional to the purpose.
✓
Persistence & Privilege
always is false and the skill is user-invocable; model invocation is enabled (the platform default). The skill does not request permanent presence or modify other skills or system settings.
Assessment
This skill appears coherent and low-risk, but it is designed to use whatever conversation history or connected notes the agent already has access to. Before enabling it, check which connectors (email, Slack, drive, notes apps) the agent can read and be comfortable with those permissions. Test the skill on non-sensitive drafts first, and if you prefer tighter control, disable or limit connectors so the skill only sees the messages/notes you explicitly paste or grant it during a session. Also remember autonomous invocation is normal on the platform — if you do not want the agent to run this skill without your explicit prompt, adjust agent settings that control autonomous skill invocation.

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

latestvk973v4rw9hnq93f75nq26114j5808fnb

License

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

Comments