メニュー
Interact with Google Docs & Drive — read, edit, search, comment, share, create docs, list/pull/push content. Use whenever JP wants to read or modify a Google Doc or Drive file (fetch a doc's text, leave a comment, find a file, etc.).
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
How to invoke the Codex CLI (`codex`) from the shell. Read this BEFORE shelling out to `codex` for any nontrivial task — it covers calling the real binary (not the Superconductor wrapper, which hangs) and capturing output with `-o` so the answer doesn't get buried in the agent-session stream.
Batch-process Asana tickets — bugs and small / well-specified features — tagged jpa-bugfixes-today into PRs. Spawns a subagent per ticket in parallel worktrees with Codex plan-review and diff-review.
Interact with Asana — tasks, My Tasks, projects, sections, tags, users, workspaces. Use whenever JP wants to read or modify Asana data (look up or edit a task, list My Tasks, comment, find a project, etc.).
Query Better Stack Telemetry logs — errors, warnings, full-text search, request traces, tail, stats. Use whenever JP wants to look at logs or investigate the context around a failure (what happened around an error, logs for a request id, recent errors, etc.).
Interact with Sentry — issues, errors, events, traces, releases, projects, dashboards. Use whenever JP wants to read or modify Sentry data (triage an issue, look up an error, inspect a trace, manage a release, etc.).
Run parallel local + remote PR reviews, then synthesize all findings
| name | gdoc |
| description | Interact with Google Docs & Drive — read, edit, search, comment, share, create docs, list/pull/push content. Use whenever JP wants to read or modify a Google Doc or Drive file (fetch a doc's text, leave a comment, find a file, etc.). |
Use the gdoc CLI — a CLI for Google Docs & Drive.
Run gdoc -h for the top-level commands, then gdoc <command> --help to drill in. Add --json for machine-readable output.
Google Docs can have multiple tabs (left-sidebar), each effectively its own document body, and gdoc cat can silently miss tabs — it sometimes prints # Tab 1 markers and sometimes drops whole tabs with no indication (observed on v0.7.6, where it returned an old "(ignore)" tab and never showed the "Final Copy" tab the user's link pointed at).
?tab=t.XXXX param pins a specific tab — that tab is the one that matters. Don't ignore the param.gdoc cat on a doc that has (or might have) tabs, enumerate them via the Docs API using gdoc's own stored OAuth creds (~/.config/gdoc/token.json, venv python /Users/jpaddison/.local/share/uv/tools/gdoc/bin/python3):
documents().get(documentId=…, includeTabsContent=True) → walk tabs[].tabProperties (tabId, title, nested childTabs), match the URL's tab id, and extract that tab's documentTab.body.content.