View traces, spans, metrics, feedback, and telemetry health for Observal agents and MCPs. Use when the user wants to see recent traces, check metrics, view top items, submit ratings, or diagnose telemetry pipeline issues.
Scanned 5/27/2026
Install via CLI
openskills install BlazeUp-AI/Observal---
# SPDX-FileCopyrightText: 2026 Hemalatha Madeswaran <hemalathamadeswaran@gmail.com>
# SPDX-License-Identifier: AGPL-3.0-only
name: observal-ops
command: observal
description: View traces, spans, metrics, feedback, and telemetry health for Observal agents and MCPs. Use when the user wants to see recent traces, check metrics, view top items, submit ratings, or diagnose telemetry pipeline issues.
version: 2.0.0
owner: observal
---
# Observal Ops: Observability and Telemetry
## Critical Rules
1. **EXECUTE commands**: run them in your shell. Set timeout to 60 seconds.
2. **Pass `--output json`** on every command for stable, machine-readable output.
3. **When in doubt about a flag, run `<command> --help` first.**
---
## Procedure: Observe
```bash
observal ops overview --output json
observal ops metrics ITEM_NAME --type agent --output json
observal ops metrics ITEM_NAME --type mcp --watch
observal ops top --type agent --output json
observal ops top --type mcp --output json
observal ops traces --limit 20 --output json
observal ops traces --agent AGENT_NAME --output json
observal ops traces --mcp MCP_NAME --output json
observal ops spans TRACE_ID --output json
observal ops feedback ITEM_NAME --type mcp --output json
```
---
## Procedure: Rate Component
```bash
observal ops rate MCP_NAME --stars 5 --type mcp --comment 'Worked great'
observal ops rate AGENT_NAME --stars 4 --type agent
```
`--stars` (1-5) and `--type` are required. `--comment` is optional.
---
## Procedure: Telemetry Health
```bash
observal ops telemetry status
observal ops telemetry test
```
`status` is the reliable check: it queries server event counts and local SQLite buffer. `test` may return 404 on newer servers (legacy endpoint). If `status` shows events flowing, telemetry is healthy.
**Diagnosis:** status OK → healthy. No events → check `observal auth status`. Server reachable but no events → hooks not installed, suggest `observal doctor`.
---
## Output Contract
1. One sentence stating intent.
2. The exact command in a fenced code block.
3. The result: success / specific error.
4. The next action, or "done".
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.