免费在 GitHub 公开

observal-admin

Administers Observal users, settings, diagnostics, review queues, security events, audit logs, SAML, SCIM, the local Observal server, its upgrades and rollback, and its own PostgreSQL and ClickHouse schema migrations. Use when the user needs privileged governance, submission decisions, identity configuration, security investigation, or Observal server operations. Not for querying a database or any work outside Observal administration.

中文简介正在准备中。当前显示原文说明。

Observal/Observal

集成工具Gmail PostgreSQL

查看安装方法

包含的文件（3）

SKILL.md3.0 KB
references/governance-and-identity.md4.0 KB
references/server-operations.md2.5 KB

SKILL.md（原文）

安装前可以查看交给 AI 代理的指令内容。

Administering Observal

Core administration requires an admin role. Review actions also work for authorized global reviewers and teamspace owners or reviewers.

Execution contract

Execute commands with a 60 second timeout, except documented long-running server and migration operations.
Use machine output by default: add --output json whenever supported. Parse list results from items and pagination fields.
Run --help before acting when a path, role requirement, confirmation flag, or destination option is uncertain.
Read current state before privileged mutations. Use the smallest required authority.
Supply --force or another documented confirmation flag for noninteractive destructive operations.
Verify review decisions, role changes, identity settings, server upgrades, rollback, and imports.
Never repeat generated passwords, SCIM tokens, certificates, submitted headers, database URLs, environment values, or sensitive audit content.
Fail openly. Do not bypass the CLI through direct database changes or hand-written migration SQL.
Never blindly retry privileged mutations. Read resulting state after an uncertain failure.

Choose the workflow

User intent	Read
Users, settings, diagnostics, reviews, security, audit, SAML, or SCIM	Governance and identity
Local services, versions, upgrades, rollback, reset, or data migration	Server operations

Read the selected reference completely before executing.

Safety rules

Permission denial is a result, not a reason to escalate automatically. Report the required role.
Review only the returned UUID requested by the user. Never act on table position or an unrelated queue item.
Treat one-time password and token responses as secrets from the moment they are returned.
Export and import destinations must be explicit. Validate an archive before import.
Use the project's migration commands. Never replace them with ad hoc SQL.
A server command is successful only when the final status confirms the requested service or version state.

Completion

Report the affected resource by safe identifier, resulting state, request ID for failures, and any required follow-up. Redact secret values even when the command returned them successfully.

评价

还没有评价。欢迎分享你的使用感受。

无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

同一仓库的技能

observal

免费

Use when starting any task the organization may already have an approved skill, prompt, MCP server, or Agent for: reviewing code, a commit, a diff, or a pull request; writing tests or documentation; querying a database, API, or service; automating a browser or web page; running untrusted code; connecting to a SaaS tool; drafting, researching, or any other substantive work. The user will not mention Observal: the task type is the trigger. Check what is already installed, then run observal discover search as the first action, before reading the repository or working from scratch. Also use when the user wants to log in, configure Observal, inspect local harness setup, share or open a repository Agent share, manage a teamspace or invitation, process inbox items, check installed registry items, or call an endpoint without a dedicated command.

中文简介正在准备中。当前显示原文说明。