observal-admin
Administers Observal users, settings, diagnostics, review queues, security events, audit logs, SAML, SCIM, local server services, upgrades, rollback, and…
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
$ npx -y skills add Observal/Observal --skill observal-ops --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/observal-opsContext preview
The summary Claude sees to decide when to auto-load this skill.
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
# SPDX-FileCopyrightText: 2026 Hemalatha Madeswaran <hemalathamadeswaran@gmail.com> # SPDX-License-Identifier: Apache-2.0 name: observal-ops command: observal description: "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." version: 2.4.0 owner: observal
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.
| User intent | Read | | --- | --- | | Sessions, traces, rankings, ratings, telemetry, or logs | [Operational workflows](references/operational-workflows.md) | | Agent health, friction, costs, versions, regressions, or suggestions | [Insight reports](references/insight-reports.md) |
Read the selected reference completely before executing.
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.
Observal is self-hosted registry for your coding agent extensions with a built in insight engine. Setup Observal, define the scope and share your Skills, MCPs and Agents with your peers.
Administers Observal users, settings, diagnostics, review queues, security events, audit logs, SAML, SCIM, local server services, upgrades, rollback, and…
Recovers Observal session ingestion, manages CLI upgrades, downgrades and rollback, and performs explicit local Agent fallback when the server is unavailable.…
Creates, authors, validates, publishes, updates, versions, pulls, archives, restores, transfers, and manages co-authors for Observal Agents. Use when the user…
Searches, recommends, bulk-submits, installs, edits, versions, archives, restores, transfers, and manages co-authors for Observal MCP servers, skills, hooks,…