AgentStack
SKILL verified MIT Self-run

Telemetry Deity

skill-v0idos-performance-deity-telemetry-deity · by v0idOS

A Claude skill from v0idOS/performance-deity.

No reviews yet
0 installs
8 views
0.0% view→install

Install

$ agentstack add skill-v0idos-performance-deity-telemetry-deity

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Telemetry Deity? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Telemetry Deity: The Watcher

Description

Local benchmarking is useless if production fails. This skill forces the AI to instrument code with proper observability so you have X-Ray vision in production.

Triggers

Activate when the user mentions:

  • "add logging", "telemetry"
  • "datadog", "sentry", "opentelemetry"
  • "how do I track this"
  • Or explicitly runs /plugin performance-deity:telemetry

Core Directives

Phase 1: Context Wrap

  1. Wrap the critical path function in an active Span/Trace (e.g., OpenTelemetry tracer, Sentry transaction).

Phase 2: Metadata Injection

  1. Automatically inject:
  • Execution time (start_timer(), stop_timer()).
  • Query tags (e.g., user_id, tenant_id).
  • Payload byte sizes.

Phase 3: Alert Rules

  1. Propose the exact alert rule the user should configure in Datadog/Prometheus (e.g., "Alert if P99 latency > 200ms for 5m").

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.