Real Skill packageSource verifiedClawHub registry

gmail-wiki-ingest

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

Identity and source

Publisher attributionSamuelWeiregistry owner unverified by skillvetai
Functional categorySearch, Research & Knowledgeautomatically inferred · 59% rule confidence
Package forminstruction with code9 recorded files
Canonical sourceClawHub registryclawhub:samuel-wei:gmail-wiki-ingest
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/31/2026.claude/skills/gmail-wiki-ingest

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/31/2026.agents/skills/gmail-wiki-ingest

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/31/2026skills/gmail-wiki-ingest

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

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-ingest
clawhub inspect @samuel-wei/gmail-wiki-ingest --version 0.3.0

Security evidence

SkillVetAI static result: no findings detected

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
9 / 9 inspected as text
Checked
8/31/2026, 12:46:38 PM
Scanner
0.1.3
Policy
1.0.3
4 inferred permission indicators
  • network access — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • external write action — automatically inferred
3 dependency and API indicators
  • api: apps.apple.com
  • api: clawhub.ai
  • api: javis-server
External clawhub result: suspicious

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.

Evidence checked
8/31/2026, 9:01:34 AM
Release binding
Matches this record
  • skillspector: clean
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:935fc9c0f5c651972a3a7cf2041222a1b3b066597f6fec8813586b27ffccb17b
Show up to 9 recorded paths
  • package.json
  • README.md
  • references/banding-and-trust.md
  • references/tool-contract.md
  • references/trigger-contract.md
  • scripts/gmail-wiki-ingest.js
  • skill-card.md
  • SKILL.md
  • test/cli.test.js

Source changelog

gmail-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.