跳到正文
cccskills
免费在 GitHub 公开

observal-ops

Inspect Agent activity in Observal through execution records, sessions, ratings, logs, and insight reports. Use the evidence to investigate telemetry problems, costs, and performance regressions, then identify practical next steps while accounting for limited data.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Inspects Observal traces, sessions, rankings, feedback, telemetry health, logs, and Agent insight reports. Use when the user wants operational evidence, current activity, telemetry diagnosis, ratings, report generation, regression analysis, or recommendations grounded in Agent usage.

查看安装方法

适用场景

  • Reviewing recent Agent activity
  • Diagnosing missing telemetry
  • Investigating costs and performance regressions
  • Summarizing usage evidence for improvement

包含的文件(3)

  • SKILL.md2.6 KB
  • references/insight-reports.md3.5 KB
  • references/operational-workflows.md2.2 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Observing Observal

Execution contract

  1. Execute commands with a 60 second timeout. Use a longer timeout only for report generation or an intentional stream.
  2. Use machine output by default: add --output json whenever supported. Parse list envelopes, finite objects, and JSON Lines separately.
  3. Run --help before acting when a path or flag is uncertain.
  4. Start with the narrowest read that answers the question. Do not generate a new report when a completed report already suffices.
  5. Ground every conclusion in returned fields, report period, and sample size. Distinguish missing data from healthy data.
  6. Verify rating mutations and report generation results.
  7. Never repeat secrets or sensitive trace and log content unless the user explicitly requests the specific data and is authorized.
  8. After an uncertain rating or report-generation failure, read current state before retrying.

Choose the workflow

User intentRead
Sessions, traces, rankings, ratings, telemetry, or logsOperational workflows
Agent health, friction, costs, versions, regressions, or suggestionsInsight reports

Read the selected reference completely before executing.

Analysis rules

  • A zero exit status from telemetry diagnosis can still contain issues or warnings. Read the JSON health fields.
  • No events is not automatically a hook problem. Check authentication, server reachability, local outbox, and hook state in that order.
  • Quote report evidence accurately and say when session count is thin.
  • Only component_ref proves an insight suggestion maps to a Registry component. Never reconstruct a component identity from prose.
  • Lead with reuse suggestions before create-new suggestions.
  • For logs and traces, summarize the minimum sensitive content needed to answer the question.

Completion

Report the time range, filters, counts, health state, strongest evidence, uncertainty, and concrete next action. Do not present popularity fallback or sparse reports as personalized certainty.

评价

还没有评价。欢迎分享你的使用感受。

评论

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。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

observal

免费

Find and reuse organization-approved skills, prompts, tool connections, and Agents through Observal. Check existing installations, select resources suited to the task, and handle account setup, shared Agents, inbox items, and teamspace membership through the CLI.

中文简介正在准备中。当前显示英语简介。

  • Finding approved resources for a task
  • Checking installed skills and tool connections
  • Configuring login and the local Agent environment
Observal/Observal45752026年10月21日 更新

Administer Observal users, settings, submission reviews, identity configuration, and security investigations. Also manage local server upgrades, rollback, and database schema migrations, checking the resulting state and protecting sensitive values throughout privileged operations.

中文简介正在准备中。当前显示英语简介。

  • Managing users, permissions, and submission reviews
  • Configuring SAML sign-in and SCIM user provisioning
  • Investigating security events and audit logs
Observal/Observal45752026年10月21日 更新

Recover missed Observal session deliveries, upgrade or downgrade the command-line tool, and roll back version changes. After specified connection or configuration failures, it can also create local Agent files when explicitly requested.

中文简介正在准备中。当前显示英语简介。

  • Recover missed session deliveries
  • Upgrade or downgrade the CLI
  • Roll back a CLI version change
Observal/Observal45752026年10月21日 更新

Create and install Observal Agents, edit their definitions, and manage publication and version releases. The skill also supports forking approved Agents, archiving and restoring them, transferring ownership, and managing co-authors.

中文简介正在准备中。当前显示英语简介。

  • Create and publish an Agent
  • Install an existing Agent
  • Customize an approved Agent
Observal/Observal45752026年10月21日 更新

Find, evaluate, and install agent components from Observal, including skills, MCP servers, hooks, and prompts. For components you control, the skill also supports bulk submission, version management, archiving, restoration, ownership transfers, and co-author management.

中文简介正在准备中。当前显示英语简介。

  • Find and install components for an agent environment
  • Get component recommendations for current needs
  • Submit multiple components for review
Observal/Observal45752026年10月21日 更新

release

免费

Manage Observal maintainer releases, from creating release branches and backporting fixes to preparing preview and stable versions. Follow the existing release workflow to verify published artifacts, inspect release status, and recover interrupted or failed operations.

中文简介正在准备中。当前显示英语简介。

  • Creating a new release branch
  • Backporting merged fixes to maintained versions
  • Preparing alpha, beta, RC, and stable releases
Observal/Observal45752026年10月21日 更新

查看 Observal 的全部技能

报告此技能的问题