g14wxz/supabase-observability-metrics
Configures Prometheus scraping, log drains, and observability for Supabase infrastructure monitoring.
97
97%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates specific capabilities (Prometheus scrape jobs, log drain pipelines, dashboards, alerting), uses natural trigger terms users would employ, and includes an explicit 'Use when...' clause with multiple trigger scenarios. The combination of Supabase-specific monitoring with Prometheus creates a well-defined niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: sets up Prometheus scrape jobs targeting Supabase metrics endpoint, configures log drain pipelines, establishes monitoring dashboards, and configures alerting baselines. | 3 / 3 |
Completeness | Clearly answers both 'what' (sets up Prometheus scrape jobs, configures log drain pipelines, establishes dashboards and alerting) and 'when' with an explicit 'Use when...' clause covering multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'Prometheus', 'scrape jobs', 'Supabase', 'metrics', 'log drain', 'monitoring dashboards', 'alerting', 'observability', 'production'. Good coverage of terms across the monitoring/observability domain specific to Supabase. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche combining Supabase + Prometheus + log drains + observability. The specificity of targeting Supabase metrics endpoints and log drain pipelines makes it very unlikely to conflict with generic monitoring or generic Supabase skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill with excellent actionability and workflow clarity. The phased approach with explicit HALT conditions, concrete YAML/bash examples, and a structured verification report make it very effective. The only minor weakness is the lengthy inline alert rules block and lack of references to supplementary materials for dashboard configuration mentioned in the skill description.
Suggestions
Consider referencing the alert rules YAML as a separate file link rather than inlining the full 40+ lines, or note that Claude should write it to disk directly.
The skill description mentions 'monitoring dashboards' but the content only covers Prometheus scrape jobs and alerts—consider adding a brief section or reference for dashboard setup (e.g., Grafana dashboard JSON).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. Every section serves a purpose—no explanations of what Prometheus is, what log drains are, or how YAML works. It assumes Claude's competence and jumps straight into actionable configuration. | 3 / 3 |
Actionability | Provides fully executable YAML configs, bash commands with loops, and complete alert rule definitions that are copy-paste ready with only placeholder substitution needed. Specific metric names, endpoints, and CLI commands are all concrete. | 3 / 3 |
Workflow Clarity | Clear four-phase sequence with explicit validation checkpoints: YAML syntax validation in Phase 1, drain status confirmation in Phase 2, metric family verification with HALT condition in Phase 3, and a comprehensive verification report with OPERATIONAL/DEGRADED status. Feedback loops and HALT conditions are well-placed for risky operations. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear phases and sections, but the alert rules YAML block is quite long inline. The alerts file content could potentially be referenced rather than fully inlined, and there are no references to external files for advanced configuration or dashboard setup mentioned in the description. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents