菜单
Store an owner credential, request provisioning, or check skill access. Reusable credentials are consumed only by operation-specific trusted brokers and are never returned to the model.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use this to read AI Studio's live capability catalog and repository catalog, execute assistants, and work with decisions. Prefer the caller-bound OAuth connection; current scopes and repository/item/segment ACLs are enforced server-side on every request.
Resolve a district email address or a Google Chat `users/{id}` to the real person in the Peninsula SD directory — name, title, department. Use this whenever you are about to refer to someone by a raw email address or a Chat sender id, instead of guessing who they are.
Schedule an agent task to run later using Amazon EventBridge Scheduler — either a recurring cron/rate, OR a ONE-SHOT follow-up at a specific time. Use this for morning briefs, weekly summaries, reminders, cron jobs, AND ALSO for any "I'll get back to you in N minutes" promise you make to the user. Do NOT use OpenClaw's built-in cron subsystem; it is disabled in this deployment.
Google Workspace (Gmail, Calendar, Drive, Docs, Sheets, Slides, Meet, Chat) as the user's agent account. Use for reading or writing email, calendar events, files, or any Workspace data.
Read-only access to PSD's Redshift data warehouse, authenticated with the caller's Cognito identity. Lists tables, inspects schemas, runs RLS-rewritten SELECT queries, and manages cross-session "lessons" learned about the data. The MCP server enforces all access control — the skill simply forwards JSON-RPC calls with the right bearer token.
Read the caller's Plaud voice recordings — list/search recordings and fetch transcripts and AI summaries. Use for Plaud, voice memos, recorded meetings, "my recordings/notes", transcript or summary of a recording.
| name | psd-credentials |
| summary | Use the owner-bound credential broker without selecting an identity or accessing AWS directly. |
| description | Store an owner credential, request provisioning, or check skill access. Reusable credentials are consumed only by operation-specific trusted brokers and are never returned to the model. |
| allowed-tools | Bash(node:*) |
The model runtime has no Secrets Manager or database permissions. Each command uses a fixed local relay operation; the relay signs the exact request at the trusted boundary after the owner is verified.
Never pass --user, --owner-email, --user-email, or --user-id. Those
arguments are rejected. Plaintext credential get/list operations do not exist.
Store a credential for the verified owner:
node /opt/psd-skills/psd-credentials/put.js \
--name "<credential-name>" \
--value "<secret-value>"
Check a restricted-skill grant for the verified owner:
node /opt/psd-skills/psd-credentials/check_capability.js \
--capability "<capability-identifier>" \
[--skill-id "<psd_agent_skills-uuid>"]
The check exits 0 when granted, 3 when denied, and 1 on an internal
failure. Restricted skills must fail closed.
Request administrator provisioning:
node /opt/psd-skills/psd-credentials/request_new.js \
--name "<desired-credential-name>" \
--reason "<why this credential is needed>" \
[--skill-context "<which skill needs it>"]