Email Triage

v0.1.2

Zero-trust email triage — prioritize inbox by sender trust tier, not arrival order. Surfaces paying customers immediately, batches newsletters, and applies a...

0· 62·0 current·0 all-time
bySteven Obiajulu@stevenobiajulu
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 and description claim a prioritization heuristic; the skill is instruction-only and asks for no binaries, installs, or credentials — all of which are proportionate to a purely heuristic triage helper.
Instruction Scope
SKILL.md confines actions to classifying and summarizing email using signals the agent's runtime already exposes (thread continuity, domain matches, corroborating signals). This stays within the stated purpose, but it depends on the runtime actually providing those email metadata/signals; the skill explicitly warns it won't fetch additional data sources, which is appropriate.
Install Mechanism
No install spec and no code files — instruction-only skill with lowest install risk.
Credentials
The skill declares no required environment variables, credentials, or config paths. That is proportional to the described behavior.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request persistent presence or modify other skills or system-wide settings.
Assessment
This skill appears coherent and low-risk: it provides heuristics for prioritizing email and doesn't ask for credentials or install code. Before enabling it, confirm what your agent/runtime already exposes (email metadata, thread context, known contacts, calendar/meeting signals) because the skill relies on those signals — if the runtime has broad mailbox access, the agent will process your email data to apply these rules. If you have privacy concerns, test the skill on a limited or non-sensitive mailbox first, and consider restricting the agent's permissions or disabling autonomous invocation for this skill in your agent settings.

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

latestvk9733fmsg9bh8xws0e4qsdjmvd84fw9r

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments