원클릭으로
readiness
Score how ready this brain is across the three layers, Capture, Brain, and Act. Read-only. Run it weekly and watch the score climb.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Score how ready this brain is across the three layers, Capture, Brain, and Act. Read-only. Run it weekly and watch the score climb.
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
Connect ClickUp tasks to the brain with a personal API token and a pull script, so open work lands in raw/. Use when the user manages tasks or projects in ClickUp.
Connect GitHub to the brain with the gh CLI, so pull-github.sh pulls repo activity (commits, issues) into raw/. Use when the user wants their code or repo activity captured.
Connect Gmail to the brain — the easy connector way (browser sign-in, no key) or as a saved local copy via the gws CLI. Use when the user wants their email readable by the brain.
Install the Google Workspace CLI (gws) and sign the user in, so the brain can pull Google Drive, Gmail, and Calendar into raw/ as local copies. Use when connecting any Google source as a saved local copy rather than a live connector.
Wire the brain's scripts to run on a schedule — pull, ingest, lint, backup — so it stays current on its own. Use after at least one source is connected and the user wants hands-off refresh.
Turn on backup and wire the brain to the user's tools, with them, one at a time. Run after /onboard, or any time to add a source. Sync first, then sources, then an optional schedule.
| name | readiness |
| description | Score how ready this brain is across the three layers, Capture, Brain, and Act. Read-only. Run it weekly and watch the score climb. |
A read-only health score for the brain, on our three layers. Do not change any files. Scan, score, and report. Three axes, about 33 points each, 100 total.
Capture (/33). Is data flowing in, and is it fresh? Check sources.md and raw/. Points for each connected source, for recent files in raw/, for a schedule that keeps it current, and for meetings being transcribed. Empty raw/ scores low.
Brain (/33). Is the wiki real and linked? Count pages in wiki/, check they use [[wikilinks]], flag orphan pages (nothing links to them), broken links, and stale pages (not updated in 60+ days). Confirm index.md, log.md, and overview.md exist and are current. A pile of raw files with no wiki pages scores low.
Act (/34). Can it do work? Count skills in .claude/skills/ and any agents, and check whether they actually read the wiki. Points for skills that run on a schedule without you asking. Zero skills scores low.
Keep it short. End with the single highest-leverage next step.