.claude/skills/gmail-wiki-ingestRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Triage a batch of the user's email against their personal knowledge wiki and hand the verdicts back to javis-server, which bands them into auto-ingest / review card / auto-discard. Runs daily on an in-container openclaw cron agent turn, and on demand when the user asks to "ingest my email" / "gmail
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/gmail-wiki-ingestRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/gmail-wiki-ingestRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/gmail-wiki-ingestRuntime, 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 @samuel-wei/gmail-wiki-ingestclawhub inspect @samuel-wei/gmail-wiki-ingest --version 0.3.0This 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.
sha256:935fc9c0f5c651972a3a7cf2041222a1b3b066597f6fec8813586b27ffccb17bpackage.jsonREADME.mdreferences/banding-and-trust.mdreferences/tool-contract.mdreferences/trigger-contract.mdscripts/gmail-wiki-ingest.jsskill-card.mdSKILL.mdtest/cli.test.jsgmail-wiki-ingest 0.3.0 - Overhauled documentation in SKILL.md to clarify the two-phase judgment flow using metadata-only email fetches and enforced server-side outcome processing. - Detailed the triggers, including daily and on-demand runs, and established strict empty-batch silence for non-intrusive operation. - Clarified usage of `fetch` and `submit` script commands and their expected inputs/outputs, forbidding omission or partial processing. - Expanded and formalized the category rubric for verdicts with strict boundaries and highlighted that only "correspondence" is retained. - Emphasized judging based solely on metadata (subject, sender, date, thread size) with no body/snippet access. - Stated that the skill does not own banding, trust, or any write operations, which remain server-side.