メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | connect-clickup |
| description | 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. |
You're connecting the user's ClickUp so their tasks land in the brain. The user is not technical — do the typing, and never let them paste the token into the chat. It goes in a git-ignored file you reference, nothing more.
First, check the connector directory (https://claude.ai/directory) for a
ClickUp connector. If one exists, prefer it: add it, sign in, confirm with
/mcp, done — skip the rest. If there's no connector, use the token + pull-script
path below.
Walk them through it in ClickUp (they click, you don't):
pk_.Tell them not to paste the token into the chat. Create the git-ignored file for them to fill themselves (or have them paste it into their password manager and tell you the file path):
cat > scripts/clickup-token.env <<'EOF'
CLICKUP_TOKEN=pk_paste_yours_here
EOF
chmod 600 scripts/clickup-token.env
Confirm scripts/clickup-token.env is in .gitignore before anything commits.
The token never gets committed or printed back.
With the token set, the ClickUp API tells you the rest:
source scripts/clickup-token.env
curl -s -H "Authorization: $CLICKUP_TOKEN" https://api.clickup.com/api/v2/team
Pick the team they want and note its id. Spaces → folders → lists drill down
the same way (/team/<id>/space, /space/<id>/folder, …).
Copy scripts/pull-example.sh to scripts/pull-clickup.sh (or ask Claude to
write it): read the token from the env file, call the ClickUp API for their open
tasks, and write the JSON/markdown under raw/clickup. Run it once and confirm
files appear.
Mark the Tasks row in sources.md with today's date. Remind them they can re-run
/connect any time to add the next source.
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.
The full daily cycle: pull everything, ingest what's new, summarize. Use once a day.