.claude/skills/qubrics-agent-email-inboxRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Use when an AI agent needs read-only triage of an existing Qubrics inbox or unsent reply text from its messages. Trigger for bounded inbox reviews, unread invoice or support searches, and draft-only replies, including agent inbox requests without the Qubrics name. Mailbox mutations and sending are outside this workflow.
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/qubrics-agent-email-inboxRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/qubrics-agent-email-inboxRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/qubrics-agent-email-inboxRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @roshanjonah/qubrics-agent-email-inboxclawhub inspect @roshanjonah/qubrics-agent-email-inbox --version 2.0.4This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:85a9ce99338d97a2a6b39c82d6327308bf85a104f00c87311b0fb8210b8e651dskill-card.mdSKILL.mdVersion 2.0.4 - Clarifies that inbox review is read-only: no mailbox changes, saved drafts, or sending. - Adds safeguards to verify mailbox identity and read permissions before opening messages. - Sets bounded search and batch-read guidance, including how to handle empty results and missing or truncated content. - Requires evidence-based triage and keeps reply drafts unsent, with missing details flagged rather than invented.