Observal/Observal

Observal operates the Observal CLI for login, configuration, setup checks, inbox processing, teamspace management, and authenticated API access. Use it when you need to inspect local setup or run core account and inventory workflows.

Observal Admin administers Observal users, settings, diagnostics, review queues, security events, audit logs, SAML, SCIM, local server services, upgrades, rollback, and database migrations. Use it for privileged governance, submission decisions, identity configuration, security investigation, or server operations.

Observal Agents creates, validates, publishes, versions, and manages Observal Agents from the command line, including pulling, archiving, restoring, and transferring ownership. Use it when building, installing, or changing an Agent definition or managing its lifecycle.

Observal Ops inspects Observal traces, sessions, rankings, feedback, telemetry health, logs, and Agent insight reports. Use it when you need operational evidence, telemetry diagnosis, ratings, report generation, regression analysis, or recommendations grounded in Agent usage.

Observal Recovery recovers Observal session ingestion, manages CLI upgrades, downgrades and rollback, and performs explicit local Agent fallback when the server is unavailable. Use when the user asks to reconcile missed sessions, repair CLI version state, or continue locally after a confirmed connection or configuration failure.

Observal Registry searches, recommends, submits, installs, and manages Observal MCP servers, skills, hooks, prompts, and sandboxes. Use it to find components, publish them, install them into a harness, or manage their lifecycle.

Observal Registry CLI submits, browses, installs, edits, archives, restores, transfers, and manages co-authors for portable skill packages. It helps users manage AI agent skills across harnesses like Claude Code and pi.

Refactor Guide analyzes code and suggests refactoring improvements such as extracting repeated logic, reducing cyclomatic complexity, applying SOLID principles, and improving naming. Use it during code review to get before/after examples.

Security Auditor scans provided code for OWASP Top 10 vulnerabilities including SQL injection, XSS, SSRF, and broken authentication. It provides severity ratings and remediation steps with corrected code to use during code review.

Test Writer generates comprehensive unit tests for provided code, covering happy paths, edge cases, error handling, and boundary conditions. Use it to create pytest or Jest tests with mocks and aim for high branch coverage.