메뉴
One-time Gmail setup: scan 3 months of inbox history to build gmail-rules.md with sender patterns, importance signals, and cleanup rules. Use when setting up Gmail automation for the first time or refreshing email rules.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | gmail-bootstrap |
| description | One-time Gmail setup: scan 3 months of inbox history to build gmail-rules.md with sender patterns, importance signals, and cleanup rules. Use when setting up Gmail automation for the first time or refreshing email rules. |
Vault path: Read from ${CLAUDE_PLUGIN_ROOT}/brain-os.config.md
Scans your last 3 months of inbox to learn your email patterns and generates gmail-rules.md — the rules file that the Gmail triage system uses.
Scan inbox history via tsx ${CLAUDE_PLUGIN_ROOT}/skills/gmail-bootstrap/scripts/gmail-bootstrap.ts:
Analyze patterns:
Generate rules file at {vault}/business/intelligence/gmail-rules.md:
# Gmail Rules
<!-- Auto-generated by /gmail-bootstrap on YYYY-MM-DD -->
<!-- Edit freely — the triage system reads this file every run -->
## Always Important (save to vault + flag for reply)
- from:client@domain.com — replied 12 times
- from:investor@vc.com — replied 8 times, starred 3
## Important (read, but auto-archive if no action in 24h)
- from:team@company.com — read always, replied sometimes
## Informational (auto-archive)
- from:newsletter@substack.com — read occasionally, never replied
- from:updates@github.com — read 20%, never replied
## Auto-delete + Filter
- from:promo@spam.com — never opened across 15 emails
## Custom Rules
<!-- Add your own patterns below -->
/syncSafe to re-run anytime. Will regenerate the rules file but preserve the ## Custom Rules section that you edited manually.
Follow skill-spec.md § 11. Append to {vault}/daily/skill-outcomes/gmail-bootstrap.log:
{date} | gmail-bootstrap | bootstrap | ~/work/brain-os-plugin | business/intelligence/gmail-rules.md | commit:{hash} | {result}
result: pass if rules generated and saved, fail if API errors or scan incompleteAnalyze skill outcomes + user corrections để propose self-improvements. Triggers: 'improve', 'skill learning', 'why does this skill keep getting it wrong', '/improve [skill-name]'.
Close or merge a pull request the right way via a 4-step hygiene sequence whose order is load-bearing. Use when the user closes, merges, wraps up, lands, or finishes a PR — 'close this PR', 'merge and clean up', 'land this', 'wrap up the PR' — even if they don't spell out all four steps.
Nightly vault maintenance — fix broken wiki-links, detect orphan pages, sync directory indexes, flag stale GH-issue tasks. Use cho: vault maintenance, broken links, orphan pages, nightly cron, lint vault.
Use when mastering a book's content through autonomous extraction, validation against NotebookLM, and knowledge extension
Ultimate autonomous goal→proof loop: auto-grill a fuzzy goal, slice the grounded decisions into a parent PRD + tracer-bullet children, implement each with a TDD evaluator-regenerate loop, then deliver a per-acceptance-criterion PROOF report. Triggers: '/autodev <goal>', 'build this with proof while I'm away', 'autonomously ship and prove this'. For queue-and-walk-away (no drive-to-done, no proof) use /afk; to clarify with a human in the loop use /grill.
Use when verifying ingested book knowledge against NotebookLM, checking verification status, or managing audit flags before absorbing